[ { "id": 1, "theme": "Preference expression and bot identity", "title": "RFC 9309: Robots Exclusion Protocol", "url": "https://www.rfc-editor.org/rfc/rfc9309.html", "page": 1, "folder": "01 - Preference expression and bot identity", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.rfc-editor.org', port=443): Max retries exceeded with url: /rfc/rfc9309.html (Caused by NameResolutionError(\"HTTPSConnection(host='www.rfc-editor.org', port=443): Failed to resolve 'www.rfc-editor.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/001.html", "final_url": "https://www.rfc-editor.org/rfc/rfc9309.html", "result": "epub", "text_characters": 17811, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "01 - Preference expression and bot identity/01 - RFC 9309- Robots Exclusion Protocol.epub", "note": "", "epub_bytes": 8744, "citation": "RFC 9309: Robots Exclusion Protocol — Koster at al., RFC Editor (IETF), 2022", "attribution": "Koster at al., RFC Editor (IETF), 2022", "combined_figures": 0 }, { "id": 2, "theme": "Preference expression and bot identity", "title": "A Vocabulary For Expressing AI Usage Preferences", "url": "https://datatracker.ietf.org/doc/draft-ietf-aipref-vocab/", "page": 1, "folder": "01 - Preference expression and bot identity", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='datatracker.ietf.org', port=443): Max retries exceeded with url: /doc/html/draft-ietf-aipref-vocab (Caused by NameResolutionError(\"HTTPSConnection(host='datatracker.ietf.org', port=443): Failed to resolve 'datatracker.ietf.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/002.html", "final_url": "https://datatracker.ietf.org/doc/draft-ietf-aipref-vocab/", "result": "epub", "text_characters": 23442, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "01 - Preference expression and bot identity/02 - A Vocabulary For Expressing AI Usage Preferences.epub", "note": "", "epub_bytes": 13050, "citation": "A Vocabulary For Expressing AI Usage Preferences — Paul Keller and Martin Thomson, IETF AI Preferences Working Group, 2026", "attribution": "Paul Keller and Martin Thomson, IETF AI Preferences Working Group, 2026", "combined_figures": 0 }, { "id": 3, "theme": "Preference expression and bot identity", "title": "HTTP Message Signatures for automated traffic", "url": "https://datatracker.ietf.org/doc/draft-ietf-webbotauth-httpsig-protocol/", "page": 1, "folder": "01 - Preference expression and bot identity", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='datatracker.ietf.org', port=443): Max retries exceeded with url: /doc/html/draft-ietf-webbotauth-httpsig-protocol (Caused by NameResolutionError(\"HTTPSConnection(host='datatracker.ietf.org', port=443): Failed to resolve 'datatracker.ietf.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/003.html", "final_url": "https://datatracker.ietf.org/doc/draft-ietf-webbotauth-httpsig-protocol/", "result": "epub", "text_characters": 73696, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "01 - Preference expression and bot identity/03 - HTTP Message Signatures for automated traffic.epub", "note": "", "epub_bytes": 34620, "citation": "HTTP Message Signatures for automated traffic — Thibault Meunier, IETF Web Bot Auth Working Group, 2026", "attribution": "Thibault Meunier, IETF Web Bot Auth Working Group, 2026", "combined_figures": 0 }, { "id": 4, "theme": "Preference expression and bot identity", "title": "Anonymous Bot Authentication: Authorization and Rate Limiting for Web Agents", "url": "https://datatracker.ietf.org/doc/draft-rescorla-anonymous-webbotauth/", "page": 1, "folder": "01 - Preference expression and bot identity", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='datatracker.ietf.org', port=443): Max retries exceeded with url: /doc/html/draft-rescorla-anonymous-webbotauth (Caused by NameResolutionError(\"HTTPSConnection(host='datatracker.ietf.org', port=443): Failed to resolve 'datatracker.ietf.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/004.html", "final_url": "https://datatracker.ietf.org/doc/draft-rescorla-anonymous-webbotauth/", "result": "epub", "text_characters": 25079, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "01 - Preference expression and bot identity/04 - Anonymous Bot Authentication- Authorization and Rate Limiting for Web Agents.epub", "note": "", "epub_bytes": 13991, "citation": "Anonymous Bot Authentication: Authorization and Rate Limiting for Web Agents — Richard Barnes and Eric Rescorla, IETF Internet-Draft, 2026", "attribution": "Richard Barnes and Eric Rescorla, IETF Internet-Draft, 2026", "combined_figures": 0 }, { "id": 5, "theme": "Preference expression and bot identity", "title": "CC Signals: A preference signals framework to protect the commons", "url": "https://zenodo.org/records/17544011", "page": 1, "folder": "01 - Preference expression and bot identity", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='zenodo.org', port=443): Max retries exceeded with url: /records/17544011 (Caused by NameResolutionError(\"HTTPSConnection(host='zenodo.org', port=443): Failed to resolve 'zenodo.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/005-full.pdf", "final_url": "https://zenodo.org/records/17544011/files/CC%20Signals_%20A%20preference%20signals%20framework%20to%20protect%20open%20research%20in%20the%20age%20of%20AI.pdf?download=1", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 10, "conversion": "PDF text with embedded original pages", "epub": "01 - Preference expression and bot identity/05 - CC Signals- A preference signals framework to protect the commons.epub", "epub_bytes": 518174, "citation": "CC Signals: A preference signals framework to protect the commons — Monica Granados, Zenodo / Creative Commons, 2025", "attribution": "Monica Granados, Zenodo / Creative Commons, 2025", "combined_figures": 4 }, { "id": 6, "theme": "Preference expression and bot identity", "title": "Attribution in the Age of AI", "url": "https://creativecommons.org/2026/07/24/attribution-in-the-age-of-ai/", "page": 1, "folder": "01 - Preference expression and bot identity", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='creativecommons.org', port=443): Max retries exceeded with url: /2026/07/24/attribution-in-the-age-of-ai/ (Caused by NameResolutionError(\"HTTPSConnection(host='creativecommons.org', port=443): Failed to resolve 'creativecommons.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/006.html", "final_url": "https://creativecommons.org/2026/07/24/attribution-in-the-age-of-ai/", "result": "epub", "text_characters": 17711, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "01 - Preference expression and bot identity/06 - Attribution in the Age of AI.epub", "note": "", "epub_bytes": 11847, "citation": "Attribution in the Age of AI — Hardinges and Bejan, Creative Commons, 2026", "attribution": "Hardinges and Bejan, Creative Commons, 2026", "combined_figures": 0 }, { "id": 7, "theme": "Preference expression and bot identity", "title": "PACT: Anonymous Credentials for the Web", "url": "https://hacks.mozilla.org/2026/06/pact-anonymous-credentials-for-the-web/", "page": 1, "folder": "01 - Preference expression and bot identity", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='hacks.mozilla.org', port=443): Max retries exceeded with url: /2026/06/pact-anonymous-credentials-for-the-web/ (Caused by NameResolutionError(\"HTTPSConnection(host='hacks.mozilla.org', port=443): Failed to resolve 'hacks.mozilla.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/007.html", "final_url": "https://hacks.mozilla.org/2026/06/pact-anonymous-credentials-for-the-web/", "result": "epub", "text_characters": 23662, "images_saved": 5, "images_missing": 5, "conversion": "Web article extraction", "epub": "01 - Preference expression and bot identity/07 - PACT- Anonymous Credentials for the Web.epub", "note": "", "epub_bytes": 779784, "citation": "PACT: Anonymous Credentials for the Web — Jackson, Mozilla Hacks, 2026", "attribution": "Jackson, Mozilla Hacks, 2026", "combined_figures": 0 }, { "id": 8, "theme": "Preference expression and bot identity", "title": "Moving past bots vs. humans", "url": "https://blog.cloudflare.com/past-bots-and-humans/", "page": 2, "folder": "01 - Preference expression and bot identity", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='blog.cloudflare.com', port=443): Max retries exceeded with url: /past-bots-and-humans/ (Caused by NameResolutionError(\"HTTPSConnection(host='blog.cloudflare.com', port=443): Failed to resolve 'blog.cloudflare.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/008.html", "final_url": "https://blog.cloudflare.com/past-bots-and-humans/", "result": "epub", "text_characters": 24296, "images_saved": 8, "images_missing": 0, "conversion": "Web article extraction", "epub": "01 - Preference expression and bot identity/08 - Moving past bots vs. humans.epub", "note": "", "epub_bytes": 173635, "citation": "Moving past bots vs. humans — Thibault Meunier, Cloudflare, 2026", "attribution": "Thibault Meunier, Cloudflare, 2026", "combined_figures": 0 }, { "id": 9, "theme": "Evidence of agent behavior and impact", "title": "Measuring AI agent autonomy in practice", "url": "https://www.anthropic.com/research/measuring-agent-autonomy", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.anthropic.com', port=443): Max retries exceeded with url: /research/measuring-agent-autonomy (Caused by NameResolutionError(\"HTTPSConnection(host='www.anthropic.com', port=443): Failed to resolve 'www.anthropic.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/009.html", "final_url": "https://www.anthropic.com/research/measuring-agent-autonomy", "result": "epub", "text_characters": 39494, "images_saved": 7, "images_missing": 0, "conversion": "Web article extraction", "epub": "02 - Evidence of agent behavior and impact/09 - Measuring AI agent autonomy in practice.epub", "note": "", "epub_bytes": 704197, "citation": "Measuring AI agent autonomy in practice — McCain et al., Anthropic, 2026", "attribution": "McCain et al., Anthropic, 2026", "combined_figures": 0 }, { "id": 10, "theme": "Evidence of agent behavior and impact", "title": "AI in Search Reduces Publisher Referrals Without Improving User Experience: Experimental Evidence", "url": "https://arxiv.org/abs/2608.18352", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2608.18352 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/010.pdf", "final_url": "https://arxiv.org/abs/2608.18352", "result": "epub", "pages": 46, "conversion": "PDF text with embedded original pages", "epub": "02 - Evidence of agent behavior and impact/10 - AI in Search Reduces Publisher Referrals Without Improving User Experience- Experimental Evidence.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 6171756, "citation": "AI in Search Reduces Publisher Referrals Without Improving User Experience: Experimental Evidence — Wang et al., arXiv, 2026", "attribution": "Wang et al., arXiv, 2026", "combined_figures": 19 }, { "id": 11, "theme": "Evidence of agent behavior and impact", "title": "Scrapers selectively respect robots.txt directives: evidence from a large-scale empirical study", "url": "https://arxiv.org/abs/2505.21733", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2505.21733 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/011.pdf", "final_url": "https://arxiv.org/abs/2505.21733", "result": "epub", "pages": 17, "conversion": "PDF text with embedded original pages", "epub": "02 - Evidence of agent behavior and impact/11 - Scrapers selectively respect robots.txt directives- evidence from a large-scale empirical study.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 3144989, "citation": "Scrapers selectively respect robots.txt directives: evidence from a large-scale empirical study — Kim et al., arXiv, 2025", "attribution": "Kim et al., arXiv, 2025", "combined_figures": 7 }, { "id": 12, "theme": "Evidence of agent behavior and impact", "title": "Quo Vadis, Crawlers? Progress and what’s next on safeguarding our infrastructure", "url": "https://diff.wikimedia.org/2026/03/26/quo-vadis-crawlers-progress-and-whats-next-on-safeguarding-our-infrastructure/", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='diff.wikimedia.org', port=443): Max retries exceeded with url: /2026/03/26/quo-vadis-crawlers-progress-and-whats-next-on-safeguarding-our-infrastructure/ (Caused by NameResolutionError(\"HTTPSConnection(host='diff.wikimedia.org', port=443): Failed to resolve 'diff.wikimedia.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/012.html", "final_url": "https://diff.wikimedia.org/2026/03/26/quo-vadis-crawlers-progress-and-whats-next-on-safeguarding-our-infrastructure/", "result": "epub", "text_characters": 7890, "images_saved": 3, "images_missing": 0, "conversion": "Web article extraction", "epub": "02 - Evidence of agent behavior and impact/12 - Quo Vadis, Crawlers- Progress and what’s next on safeguarding our infrastructure.epub", "note": "", "epub_bytes": 182239, "citation": "Quo Vadis, Crawlers? Progress and what’s next on safeguarding our infrastructure — Mueller et al., Wikimedia Foundation, 2026", "attribution": "Mueller et al., Wikimedia Foundation, 2026", "combined_figures": 0 }, { "id": 13, "theme": "Evidence of agent behavior and impact", "title": "New Report: 30% of South African Publishers Block AI Crawlers via Robots.txt", "url": "https://www.ctrl-j.info/news/new-report-protocol-gap-south-africa", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.ctrl-j.info', port=443): Max retries exceeded with url: /news/new-report-protocol-gap-south-africa (Caused by NameResolutionError(\"HTTPSConnection(host='www.ctrl-j.info', port=443): Failed to resolve 'www.ctrl-j.info' ([Errno -2] Name or service not known)\"))", "source": "_sources/013.html", "final_url": "https://www.ctrl-j.info/news/new-report-protocol-gap-south-africa", "result": "epub", "text_characters": 2648, "images_saved": 3, "images_missing": 0, "conversion": "Web article extraction", "epub": "02 - Evidence of agent behavior and impact/13 - New Report- 30 percent of South African Publishers Block AI Crawlers via Robots.txt.epub", "note": "", "epub_bytes": 383779, "citation": "New Report: 30% of South African Publishers Block AI Crawlers via Robots.txt — CTRL+J / Journalism Relay Project, 2026", "attribution": "CTRL+J / Journalism Relay Project, 2026", "combined_figures": 0 }, { "id": 14, "theme": "Evidence of agent behavior and impact", "title": "Signals at Scale", "url": "https://www.signalsatscale.com/reports.html", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.signalsatscale.com', port=443): Max retries exceeded with url: /reports.html (Caused by NameResolutionError(\"HTTPSConnection(host='www.signalsatscale.com', port=443): Failed to resolve 'www.signalsatscale.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/014-full.pdf", "final_url": "https://www.signalsatscale.com/downloads/signals-at-scale-report-sep2026.pdf", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 88, "conversion": "PDF text with embedded original pages", "epub": "02 - Evidence of agent behavior and impact/14 - Signals at Scale.epub", "epub_bytes": 15833108, "citation": "Signals at Scale — Caswell and Fang, Signals at Scale, 2026", "attribution": "Caswell and Fang, Signals at Scale, 2026", "combined_figures": 3 }, { "id": 15, "theme": "Evidence of agent behavior and impact", "title": "2026 State of AI Traffic: Cyberthreat Benchmarks", "url": "https://www.humansecurity.com/learn/resources/2026-state-of-ai-traffic-cyberthreat-benchmarks/", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.humansecurity.com', port=443): Max retries exceeded with url: /learn/resources/2026-state-of-ai-traffic-cyberthreat-benchmarks/ (Caused by NameResolutionError(\"HTTPSConnection(host='www.humansecurity.com', port=443): Failed to resolve 'www.humansecurity.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/015-full.pdf", "final_url": "https://www.humansecurity.com/wp-content/uploads/HUMAN_Report_2026-State-of-AI-Traffic-and-Cyberthreat-Benchmark.pdf", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 47, "conversion": "PDF text with embedded original pages", "epub": "02 - Evidence of agent behavior and impact/15 - 2026 State of AI Traffic- Cyberthreat Benchmarks.epub", "epub_bytes": 5573231, "citation": "2026 State of AI Traffic: Cyberthreat Benchmarks — HUMAN Security, 2026 (registration required)", "attribution": "HUMAN Security, 2026 (registration required)", "combined_figures": 85 }, { "id": 16, "theme": "Evidence of agent behavior and impact", "title": "State of the Bots, Q1–Q2 2026", "url": "https://tollbit.com/state-of-the-bots/q1-q2-2026/", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='tollbit.com', port=443): Max retries exceeded with url: /state-of-the-bots/q1-q2-2026/ (Caused by NameResolutionError(\"HTTPSConnection(host='tollbit.com', port=443): Failed to resolve 'tollbit.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/016-rendered.html", "final_url": "https://tollbit.com/state-of-the-bots/", "note": "", "result": "epub", "text_characters": 26036, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "02 - Evidence of agent behavior and impact/16 - State of the Bots, Q1–Q2 2026.epub", "epub_bytes": 13480, "citation": "State of the Bots, Q1–Q2 2026 — TollBit, 2026", "attribution": "TollBit, 2026", "combined_figures": 0 }, { "id": 17, "theme": "Evidence of agent behavior and impact", "title": "News Integrity in AI Assistants", "url": "https://www.ebu.ch/Report/MIS-BBC/NI_AI_2025.pdf", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.ebu.ch', port=443): Max retries exceeded with url: /Report/MIS-BBC/NI_AI_2025.pdf (Caused by NameResolutionError(\"HTTPSConnection(host='www.ebu.ch', port=443): Failed to resolve 'www.ebu.ch' ([Errno -2] Name or service not known)\"))", "source": "_sources/017.pdf", "final_url": "https://www.ebu.ch/Report/MIS-BBC/NI_AI_2025.pdf", "result": "epub", "pages": 69, "conversion": "PDF text with embedded original pages", "epub": "02 - Evidence of agent behavior and impact/17 - News Integrity in AI Assistants.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 8638281, "citation": "News Integrity in AI Assistants — Archer and De Tender, EBU and BBC, 2025", "attribution": "Archer and De Tender, EBU and BBC, 2025", "combined_figures": 12 }, { "id": 18, "theme": "Evidence of agent behavior and impact", "title": "Generative AI and News Report 2025", "url": "https://reutersinstitute.politics.ox.ac.uk/generative-ai-and-news-report-2025-how-people-think-about-ais-role-journalism-and-society", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='reutersinstitute.politics.ox.ac.uk', port=443): Max retries exceeded with url: /generative-ai-and-news-report-2025-how-people-think-about-ais-role-journalism-and-society (Caused by NameResolutionError(\"HTTPSConnection(host='reutersinstitute.politics.ox.ac.uk', port=443): Failed to resolve 'reutersinstitute.politics.ox.ac.uk' ([Errno -2] Name or service not known)\"))", "source": "_sources/018.html", "final_url": "https://reutersinstitute.politics.ox.ac.uk/generative-ai-and-news-report-2025-how-people-think-about-ais-role-journalism-and-society", "result": "epub", "text_characters": 75575, "images_saved": 1, "images_missing": 3, "conversion": "Web article extraction", "epub": "02 - Evidence of agent behavior and impact/18 - Generative AI and News Report 2025.epub", "note": "", "epub_bytes": 247421, "citation": "Generative AI and News Report 2025 — Felix Simon, et al., Reuters Institute, 2025", "attribution": "Felix Simon, et al., Reuters Institute, 2025", "combined_figures": 0 }, { "id": 19, "theme": "Evidence of agent behavior and impact", "title": "How Crawlers Impact the Operations of the Wikimedia Projects", "url": "https://diff.wikimedia.org/2025/04/01/how-crawlers-impact-the-operations-of-the-wikimedia-projects/", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='diff.wikimedia.org', port=443): Max retries exceeded with url: /2025/04/01/how-crawlers-impact-the-operations-of-the-wikimedia-projects/ (Caused by NameResolutionError(\"HTTPSConnection(host='diff.wikimedia.org', port=443): Failed to resolve 'diff.wikimedia.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/019.html", "final_url": "https://diff.wikimedia.org/2025/04/01/how-crawlers-impact-the-operations-of-the-wikimedia-projects/", "result": "epub", "text_characters": 6961, "images_saved": 3, "images_missing": 0, "conversion": "Web article extraction", "epub": "02 - Evidence of agent behavior and impact/19 - How Crawlers Impact the Operations of the Wikimedia Projects.epub", "note": "", "epub_bytes": 314469, "citation": "How Crawlers Impact the Operations of the Wikimedia Projects — Mueller, et al., Wikimedia Foundation, 2025", "attribution": "Mueller, et al., Wikimedia Foundation, 2025", "combined_figures": 0 }, { "id": 20, "theme": "Evidence of agent behavior and impact", "title": "The Protocol Gap", "url": "https://journalismrelay.org/resources/protocol-gap-report", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='journalismrelay.org', port=443): Max retries exceeded with url: /resources/protocol-gap-report (Caused by NameResolutionError(\"HTTPSConnection(host='journalismrelay.org', port=443): Failed to resolve 'journalismrelay.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/020-full.pdf", "final_url": "https://journalismrelay.org/static/robotstxt/The%20Protocol%20Gap-Brazil-Report_260305_EN.pdf", "result": "epub", "pages": 13, "conversion": "PDF text with embedded original pages", "epub": "02 - Evidence of agent behavior and impact/20 - The Protocol Gap.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 2227951, "citation": "The Protocol Gap — Journalism Relay Project, 2026", "attribution": "Journalism Relay Project, 2026", "combined_figures": 5 }, { "id": 21, "theme": "Evidence of agent behavior and impact", "title": "DECEPTICON: How Dark Patterns Manipulate Web Agents", "url": "https://arxiv.org/abs/2512.22894", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2512.22894 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/021.pdf", "final_url": "https://arxiv.org/abs/2512.22894", "result": "epub", "pages": 35, "conversion": "PDF text with embedded original pages", "epub": "02 - Evidence of agent behavior and impact/21 - DECEPTICON- How Dark Patterns Manipulate Web Agents.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 6227970, "citation": "DECEPTICON: How Dark Patterns Manipulate Web Agents — Cuvin et al., arXiv, 2025", "attribution": "Cuvin et al., arXiv, 2025", "combined_figures": 13 }, { "id": 22, "theme": "Evidence of agent behavior and impact", "title": "How Do Data Owners Say No? A Case Study of Data Consent Mechanisms in Web-Scraped Vision-Language AI Training Datasets", "url": "https://arxiv.org/pdf/2511.08637", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2511.08637 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/022.pdf", "final_url": "https://arxiv.org/pdf/2511.08637", "result": "epub", "pages": 23, "conversion": "PDF text with embedded original pages", "epub": "02 - Evidence of agent behavior and impact/22 - How Do Data Owners Say No- A Case Study of Data Consent Mechanisms in Web-Scraped Vision-Language AI Training Datasets.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 3818358, "citation": "How Do Data Owners Say No? A Case Study of Data Consent Mechanisms in Web-Scraped Vision-Language AI Training Datasets - Lee et al., arXiv, 2025", "attribution": "Lee et al., arXiv, 2025", "combined_figures": 14 }, { "id": 23, "theme": "Evidence of agent behavior and impact", "title": "Web Crawler Restrictions, AI Training Datasets & Political Biases", "url": "https://arxiv.org/pdf/2510.09031", "page": 2, "folder": "02 - Evidence of agent behavior and impact", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2510.09031 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/023.pdf", "final_url": "https://arxiv.org/pdf/2510.09031", "result": "epub", "pages": 8, "conversion": "PDF text with embedded original pages", "epub": "02 - Evidence of agent behavior and impact/23 - Web Crawler Restrictions, AI Training Datasets & Political Biases.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 1939180, "citation": "Web Crawler Restrictions, AI Training Datasets & Political Biases - Bouchaud and Ramaciotti, arXiv, 2025", "attribution": "Bouchaud and Ramaciotti, arXiv, 2025", "combined_figures": 8 }, { "id": 24, "theme": "Between publishers and platforms", "title": "Creepy AI Crawlers Are Turning the Internet into a Haunted House", "url": "https://www.techpolicy.press/creepy-ai-crawlers-are-turning-the-internet-into-a-haunted-house/", "page": 2, "folder": "03 - Between publishers and platforms", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.techpolicy.press', port=443): Max retries exceeded with url: /creepy-ai-crawlers-are-turning-the-internet-into-a-haunted-house/ (Caused by NameResolutionError(\"HTTPSConnection(host='www.techpolicy.press', port=443): Failed to resolve 'www.techpolicy.press' ([Errno -2] Name or service not known)\"))", "source": "_sources/024.html", "final_url": "https://www.techpolicy.press/creepy-ai-crawlers-are-turning-the-internet-into-a-haunted-house/", "result": "epub", "text_characters": 16442, "images_saved": 6, "images_missing": 0, "conversion": "Web article extraction", "epub": "03 - Between publishers and platforms/24 - Creepy AI Crawlers Are Turning the Internet into a Haunted House.epub", "note": "", "epub_bytes": 655975, "citation": "Creepy AI Crawlers Are Turning the Internet into a Haunted House — I and Cath, Tech Policy Press, 2025", "attribution": "I and Cath, Tech Policy Press, 2025", "combined_figures": 0 }, { "id": 25, "theme": "Between publishers and platforms", "title": "Same gatekeepers, new tollbooths in the AI content licensing market", "url": "https://www.brookings.edu/articles/same-gatekeepers-new-tollbooths-in-the-ai-content-licensing-market/", "page": 3, "folder": "03 - Between publishers and platforms", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.brookings.edu', port=443): Max retries exceeded with url: /articles/same-gatekeepers-new-tollbooths-in-the-ai-content-licensing-market/ (Caused by NameResolutionError(\"HTTPSConnection(host='www.brookings.edu', port=443): Failed to resolve 'www.brookings.edu' ([Errno -2] Name or service not known)\"))", "source": "_sources/025.html", "final_url": "https://www.brookings.edu/articles/same-gatekeepers-new-tollbooths-in-the-ai-content-licensing-market/", "result": "epub", "text_characters": 15970, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "03 - Between publishers and platforms/25 - Same gatekeepers, new tollbooths in the AI content licensing market.epub", "note": "", "epub_bytes": 11231, "citation": "Same gatekeepers, new tollbooths in the AI content licensing market — Courtney Radsch, Brookings Institution, 2026", "attribution": "Courtney Radsch, Brookings Institution, 2026", "combined_figures": 0 }, { "id": 26, "theme": "Between publishers and platforms", "title": "Forget it. Publishers can’t leave Google. That’s a problem", "url": "https://digitalcontentnext.org/blog/2026/08/27/forget-it-publishers-cant-leave-google-thats-a-problem/", "page": 3, "folder": "03 - Between publishers and platforms", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='digitalcontentnext.org', port=443): Max retries exceeded with url: /blog/2026/08/27/forget-it-publishers-cant-leave-google-thats-a-problem/ (Caused by NameResolutionError(\"HTTPSConnection(host='digitalcontentnext.org', port=443): Failed to resolve 'digitalcontentnext.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/026.html", "final_url": "https://digitalcontentnext.org/blog/2026/08/27/forget-it-publishers-cant-leave-google-thats-a-problem/", "result": "epub", "text_characters": 8243, "images_saved": 1, "images_missing": 0, "conversion": "Web article extraction", "epub": "03 - Between publishers and platforms/26 - Forget it. Publishers can’t leave Google. That’s a problem.epub", "note": "", "epub_bytes": 41718, "citation": "Forget it. Publishers can’t leave Google. That’s a problem — Jason Kint, Digital Content Next, 2026", "attribution": "Jason Kint, Digital Content Next, 2026", "combined_figures": 0 }, { "id": 27, "theme": "Between publishers and platforms", "title": "Cloudflare’s Troubling Shift From Guardian to Gatekeeper", "url": "https://techpolicy.press/cloudflares-troubling-shift-from-guardian-to-gatekeeper", "page": 3, "folder": "03 - Between publishers and platforms", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='techpolicy.press', port=443): Max retries exceeded with url: /cloudflares-troubling-shift-from-guardian-to-gatekeeper (Caused by NameResolutionError(\"HTTPSConnection(host='techpolicy.press', port=443): Failed to resolve 'techpolicy.press' ([Errno -2] Name or service not known)\"))", "source": "_sources/027.html", "final_url": "https://techpolicy.press/cloudflares-troubling-shift-from-guardian-to-gatekeeper", "result": "epub", "text_characters": 12183, "images_saved": 4, "images_missing": 0, "conversion": "Web article extraction", "epub": "03 - Between publishers and platforms/27 - Cloudflare’s Troubling Shift From Guardian to Gatekeeper.epub", "note": "", "epub_bytes": 436066, "citation": "Cloudflare’s Troubling Shift From Guardian to Gatekeeper — Hogg and Hwang, Tech Policy Press, 2025", "attribution": "Hogg and Hwang, Tech Policy Press, 2025", "combined_figures": 0 }, { "id": 28, "theme": "Between publishers and platforms", "title": "News/Media Alliance Applauds AI Bot Transparency Bill Introduction", "url": "https://www.newsmediaalliance.org/stealth-bot-prohibition-act-introduction/", "page": 3, "folder": "03 - Between publishers and platforms", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.newsmediaalliance.org', port=443): Max retries exceeded with url: /stealth-bot-prohibition-act-introduction/ (Caused by NameResolutionError(\"HTTPSConnection(host='www.newsmediaalliance.org', port=443): Failed to resolve 'www.newsmediaalliance.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/028.html", "final_url": "https://www.newsmediaalliance.org/stealth-bot-prohibition-act-introduction/", "result": "epub", "text_characters": 4897, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "03 - Between publishers and platforms/28 - News-Media Alliance Applauds AI Bot Transparency Bill Introduction.epub", "note": "", "epub_bytes": 5606, "citation": "News/Media Alliance Applauds AI Bot Transparency Bill Introduction — Danielle Coffey, News/Media Alliance, 2026", "attribution": "Danielle Coffey, News/Media Alliance, 2026", "combined_figures": 0 }, { "id": 29, "theme": "Between publishers and platforms", "title": "The Agentic Web Requires New Normative Infrastructure", "url": "https://arxiv.org/abs/2606.10711", "page": 3, "folder": "03 - Between publishers and platforms", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2606.10711 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/029.pdf", "final_url": "https://arxiv.org/abs/2606.10711", "result": "epub", "pages": 21, "conversion": "PDF text with embedded original pages", "epub": "03 - Between publishers and platforms/29 - The Agentic Web Requires New Normative Infrastructure.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 5002395, "citation": "The Agentic Web Requires New Normative Infrastructure — Pattison et al., arXiv, 2026", "attribution": "Pattison et al., arXiv, 2026", "combined_figures": 1 }, { "id": 30, "theme": "Between publishers and platforms", "title": "Exploring Must-Carry for the News in the Platform Economy", "url": "https://www.osce.org/files/f/documents/1/2/597645.pdf", "page": 3, "folder": "03 - Between publishers and platforms", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.osce.org', port=443): Max retries exceeded with url: /files/f/documents/1/2/597645.pdf (Caused by NameResolutionError(\"HTTPSConnection(host='www.osce.org', port=443): Failed to resolve 'www.osce.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/030.pdf", "final_url": "https://www.osce.org/files/f/documents/1/2/597645.pdf", "result": "epub", "pages": 16, "conversion": "PDF text with embedded original pages", "epub": "03 - Between publishers and platforms/30 - Exploring Must-Carry for the News in the Platform Economy.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 3181710, "citation": "Exploring Must-Carry for the News in the Platform Economy — Courtney Radsch and Anya Schiffrin, OSCE, 2025", "attribution": "Courtney Radsch and Anya Schiffrin, OSCE, 2025", "combined_figures": 32 }, { "id": 31, "theme": "Between publishers and platforms", "title": "Same Gatekeepers, New Tollbooths: Mapping the AI Content Licensing Market", "url": "https://static1.squarespace.com/static/5efcb64b1cf16e4c487b2f61/t/6a297a9d053faa630717cd01/1781103281806/Same+Gatekeepers+New+Tollbooths-CMDG.pdf", "page": 3, "folder": "03 - Between publishers and platforms", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='static1.squarespace.com', port=443): Max retries exceeded with url: /static/5efcb64b1cf16e4c487b2f61/t/6a297a9d053faa630717cd01/1781103281806/Same+Gatekeepers+New+Tollbooths-CMDG.pdf (Caused by NameResolutionError(\"HTTPSConnection(host='static1.squarespace.com', port=443): Failed to resolve 'static1.squarespace.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/031.pdf", "final_url": "https://static1.squarespace.com/static/5efcb64b1cf16e4c487b2f61/t/6a297a9d053faa630717cd01/1781103281806/Same+Gatekeepers+New+Tollbooths-CMDG.pdf", "result": "epub", "pages": 23, "conversion": "PDF text with embedded original pages", "epub": "03 - Between publishers and platforms/31 - Same Gatekeepers, New Tollbooths- Mapping the AI Content Licensing Market.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 3896519, "citation": "Same Gatekeepers, New Tollbooths: Mapping the AI Content Licensing Market — Courtney Radsch and Karina Montoya, Center for Journalism & Liberty, 2026", "attribution": "Courtney Radsch and Karina Montoya, Center for Journalism & Liberty, 2026", "combined_figures": 3 }, { "id": 32, "theme": "Between publishers and platforms", "title": "Consent in Crisis: The Rapid Decline of the AI Data Commons", "url": "https://www.dataprovenance.org/Consent_in_Crisis.pdf", "page": 3, "folder": "03 - Between publishers and platforms", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.dataprovenance.org', port=443): Max retries exceeded with url: /Consent_in_Crisis.pdf (Caused by NameResolutionError(\"HTTPSConnection(host='www.dataprovenance.org', port=443): Failed to resolve 'www.dataprovenance.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/032.pdf", "final_url": "https://www.dataprovenance.org/Consent_in_Crisis.pdf", "result": "epub", "pages": 41, "conversion": "PDF text with embedded original pages", "epub": "03 - Between publishers and platforms/32 - Consent in Crisis- The Rapid Decline of the AI Data Commons.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 7094101, "citation": "Consent in Crisis: The Rapid Decline of the AI Data Commons - Longpre et al., Data Provenance Initiative, 2023", "attribution": "Longpre et al., Data Provenance Initiative, 2023", "combined_figures": 15 }, { "id": 33, "theme": "Licensing", "title": "People Inc.’s Jon Roberts on the AI licensing boom – and the revenue lag", "url": "https://digiday.com/media/people-incs-jon-roberts-on-the-ai-licensing-boom-and-the-revenue-lag/", "page": 3, "folder": "04 - Licensing", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='digiday.com', port=443): Max retries exceeded with url: /media/people-incs-jon-roberts-on-the-ai-licensing-boom-and-the-revenue-lag/ (Caused by NameResolutionError(\"HTTPSConnection(host='digiday.com', port=443): Failed to resolve 'digiday.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/033.html", "final_url": "https://digiday.com/media/people-incs-jon-roberts-on-the-ai-licensing-boom-and-the-revenue-lag/", "result": "epub", "text_characters": 6841, "images_saved": 4, "images_missing": 0, "conversion": "Web article extraction", "epub": "04 - Licensing/33 - People Inc.’s Jon Roberts on the AI licensing boom – and the revenue lag.epub", "note": "", "epub_bytes": 118188, "citation": "People Inc.’s Jon Roberts on the AI licensing boom – and the revenue lag — Guaglione, Digiday, 2026", "attribution": "Guaglione, Digiday, 2026", "combined_figures": 0 }, { "id": 34, "theme": "Licensing", "title": "How AI Companies Can Pay Fair Rates for the Content They Need", "url": "https://hbr.org/2026/06/how-ai-companies-can-pay-fair-rates-for-the-content-they-need", "page": 3, "folder": "04 - Licensing", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='hbr.org', port=443): Max retries exceeded with url: /2026/06/how-ai-companies-can-pay-fair-rates-for-the-content-they-need (Caused by NameResolutionError(\"HTTPSConnection(host='hbr.org', port=443): Failed to resolve 'hbr.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/034.html", "final_url": "https://hbr.org/2026/06/how-ai-companies-can-pay-fair-rates-for-the-content-they-need", "result": "partial", "text_characters": 873, "images_saved": 1, "images_missing": 0, "conversion": "Web article extraction", "epub": "04 - Licensing/34 - How AI Companies Can Pay Fair Rates for the Content They Need.epub", "note": "Only the publicly accessible summary and opening excerpt were available; the full article requires publisher access.", "epub_bytes": 301655, "citation": "How AI Companies Can Pay Fair Rates for the Content They Need — Raul Castro Fernandez and Glen Weyl, Harvard Business Review, 2026", "attribution": "Raul Castro Fernandez and Glen Weyl, Harvard Business Review, 2026", "combined_figures": 0 }, { "id": 35, "theme": "Licensing", "title": "Really Simple Licensing (RSL) 1.0 Specification", "url": "https://rslstandard.org/rsl", "page": 3, "folder": "04 - Licensing", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='rslstandard.org', port=443): Max retries exceeded with url: /rsl (Caused by NameResolutionError(\"HTTPSConnection(host='rslstandard.org', port=443): Failed to resolve 'rslstandard.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/035.html", "final_url": "https://rslstandard.org/rsl", "result": "epub", "text_characters": 116013, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "04 - Licensing/35 - Really Simple Licensing (RSL) 1.0 Specification.epub", "note": "", "epub_bytes": 38381, "citation": "Really Simple Licensing (RSL) 1.0 Specification — Boyer et al., RSL Collective, 2025", "attribution": "Boyer et al., RSL Collective, 2025", "combined_figures": 0 }, { "id": 36, "theme": "Licensing", "title": "The economics of copyright and AI — Empirical evidence and optimal policy", "url": "https://www.europarl.europa.eu/thinktank/en/document/IUST_STU(2025)778859", "page": 3, "folder": "04 - Licensing", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.europarl.europa.eu', port=443): Max retries exceeded with url: /thinktank/en/document/IUST_STU(2025)778859 (Caused by NameResolutionError(\"HTTPSConnection(host='www.europarl.europa.eu', port=443): Failed to resolve 'www.europarl.europa.eu' ([Errno -2] Name or service not known)\"))", "source": "_sources/036-full.pdf", "final_url": "https://www.europarl.europa.eu/RegData/etudes/STUD/2025/778859/IUST_STU(2025)778859_EN.pdf", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 53, "conversion": "PDF text with embedded original pages", "epub": "04 - Licensing/36 - The economics of copyright and AI — Empirical evidence and optimal policy.epub", "epub_bytes": 8299909, "citation": "The economics of copyright and AI — Empirical evidence and optimal policy — Christian Peukert, European Parliament, Policy Department for Justice, Civil Liberties and Institutional Affairs (JURI), 2025", "attribution": "Christian Peukert, European Parliament, Policy Department for Justice, Civil Liberties and Institutional Affairs (JURI), 2025", "combined_figures": 7 }, { "id": 37, "theme": "Licensing", "title": "Building Toward a Sustainable Content Economy for the Agentic Web", "url": "https://about.ads.microsoft.com/en/blog/post/february-2026/building-toward-a-sustainable-content-economy-for-the-agentic-web", "page": 3, "folder": "04 - Licensing", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='about.ads.microsoft.com', port=443): Max retries exceeded with url: /en/blog/post/february-2026/building-toward-a-sustainable-content-economy-for-the-agentic-web (Caused by NameResolutionError(\"HTTPSConnection(host='about.ads.microsoft.com', port=443): Failed to resolve 'about.ads.microsoft.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/037.html", "final_url": "https://about.ads.microsoft.com/en/blog/post/february-2026/building-toward-a-sustainable-content-economy-for-the-agentic-web", "result": "epub", "text_characters": 4222, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "04 - Licensing/37 - Building Toward a Sustainable Content Economy for the Agentic Web.epub", "note": "", "epub_bytes": 5393, "citation": "Building Toward a Sustainable Content Economy for the Agentic Web — Frank, Microsoft Advertising Blog, 2026", "attribution": "Frank, Microsoft Advertising Blog, 2026", "combined_figures": 0 }, { "id": 38, "theme": "Licensing", "title": "Is There a Middle Ground in the Tug of War Between News Publishers and AI Firms? Part 1: Framing the Problem", "url": "https://publicknowledge.org/is-there-a-middle-ground-in-the-tug-of-war-between-news-publishers-and-ai-firms-part-1-framing-the-problem/", "page": 4, "folder": "04 - Licensing", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='publicknowledge.org', port=443): Max retries exceeded with url: /is-there-a-middle-ground-in-the-tug-of-war-between-news-publishers-and-ai-firms-part-1-framing-the-problem/ (Caused by NameResolutionError(\"HTTPSConnection(host='publicknowledge.org', port=443): Failed to resolve 'publicknowledge.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/038.html", "final_url": "https://publicknowledge.org/is-there-a-middle-ground-in-the-tug-of-war-between-news-publishers-and-ai-firms-part-1-framing-the-problem/", "result": "epub", "text_characters": 17456, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "04 - Licensing/38 - Is There a Middle Ground in the Tug of War Between News Publishers and AI Firms- Part 1- Framing the Problem.epub", "note": "", "epub_bytes": 12136, "citation": "Is There a Middle Ground in the Tug of War Between News Publishers and AI Firms? Part 1: Framing the Problem — Lisa Macpherson, Public Knowledge, 2025", "attribution": "Lisa Macpherson, Public Knowledge, 2025", "combined_figures": 0 }, { "id": 39, "theme": "Licensing", "title": "Part 2: Framing Solutions", "url": "https://publicknowledge.org/is-there-a-middle-ground-in-the-tug-of-war-between-news-publishers-and-ai-firms-part-2-framing-solutions/", "page": 4, "folder": "04 - Licensing", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='publicknowledge.org', port=443): Max retries exceeded with url: /is-there-a-middle-ground-in-the-tug-of-war-between-news-publishers-and-ai-firms-part-2-framing-solutions/ (Caused by NameResolutionError(\"HTTPSConnection(host='publicknowledge.org', port=443): Failed to resolve 'publicknowledge.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/039.html", "final_url": "https://publicknowledge.org/is-there-a-middle-ground-in-the-tug-of-war-between-news-publishers-and-ai-firms-part-2-framing-solutions/", "result": "epub", "text_characters": 32401, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "04 - Licensing/39 - Part 2- Framing Solutions.epub", "note": "", "epub_bytes": 18852, "citation": "Part 2: Framing Solutions — Lisa Macpherson, Public Knowledge, 2025", "attribution": "Lisa Macpherson, Public Knowledge, 2025", "combined_figures": 0 }, { "id": 40, "theme": "Payment and market design", "title": "Market Design for AI: Beyond the Copyright Binary", "url": "https://arxiv.org/abs/2606.12260", "page": 4, "folder": "05 - Payment and market design", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2606.12260 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/040.pdf", "final_url": "https://arxiv.org/abs/2606.12260", "result": "epub", "pages": 40, "conversion": "PDF text with embedded original pages", "epub": "05 - Payment and market design/40 - Market Design for AI- Beyond the Copyright Binary.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 7365236, "citation": "Market Design for AI: Beyond the Copyright Binary — Dai et al., arXiv, 2026", "attribution": "Dai et al., arXiv, 2026", "combined_figures": 0 }, { "id": 41, "theme": "Payment and market design", "title": "Content Independence Day, one year on: building the business model for the agentic Internet", "url": "https://blog.cloudflare.com/agentic-internet-bot-report/", "page": 4, "folder": "05 - Payment and market design", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='blog.cloudflare.com', port=443): Max retries exceeded with url: /agentic-internet-bot-report/ (Caused by NameResolutionError(\"HTTPSConnection(host='blog.cloudflare.com', port=443): Failed to resolve 'blog.cloudflare.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/041.html", "final_url": "https://blog.cloudflare.com/agentic-internet-bot-report/", "result": "epub", "text_characters": 16348, "images_saved": 8, "images_missing": 0, "conversion": "Web article extraction", "epub": "05 - Payment and market design/41 - Content Independence Day, one year on- building the business model for the agentic Internet.epub", "note": "", "epub_bytes": 253947, "citation": "Content Independence Day, one year on: building the business model for the agentic Internet — Weiss et al., Cloudflare Blog, 2026", "attribution": "Weiss et al., Cloudflare Blog, 2026", "combined_figures": 0 }, { "id": 42, "theme": "Payment and market design", "title": "Incentivizing Quality Text Generation via Statistical Contracts", "url": "https://arxiv.org/abs/2406.11118", "page": 4, "folder": "05 - Payment and market design", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2406.11118 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/042.pdf", "final_url": "https://arxiv.org/abs/2406.11118", "result": "epub", "pages": 25, "conversion": "PDF text with embedded original pages", "epub": "05 - Payment and market design/42 - Incentivizing Quality Text Generation via Statistical Contracts.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 4070872, "citation": "Incentivizing Quality Text Generation via Statistical Contracts - Sait et al., arXiv, 2024", "attribution": "Sait et al., arXiv, 2024", "combined_figures": 2 }, { "id": 43, "theme": "Payment and market design", "title": "The Trust Fabric: Decentralized Interoperability and Economic Coordination for the Agentic Web", "url": "https://arxiv.org/pdf/2507.07901", "page": 4, "folder": "05 - Payment and market design", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2507.07901 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/043.pdf", "final_url": "https://arxiv.org/pdf/2507.07901", "result": "epub", "pages": 25, "conversion": "PDF text with embedded original pages", "epub": "05 - Payment and market design/43 - The Trust Fabric- Decentralized Interoperability and Economic Coordination for the Agentic Web.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 3280355, "citation": "The Trust Fabric: Decentralized Interoperability and Economic Coordination for the", "attribution": "", "combined_figures": 18 }, { "id": 44, "theme": "Attribution, telemetry, and demand signals", "title": "SPUR Content Telemetry", "url": "https://github.com/SPUR-Coalition/telemetry", "page": 4, "folder": "06 - Attribution, telemetry, and demand signals", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='github.com', port=443): Max retries exceeded with url: /SPUR-Coalition/telemetry (Caused by NameResolutionError(\"HTTPSConnection(host='github.com', port=443): Failed to resolve 'github.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/044.html", "final_url": "https://github.com/SPUR-Coalition/telemetry", "result": "epub", "text_characters": 11368, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "06 - Attribution, telemetry, and demand signals/44 - SPUR Content Telemetry.epub", "note": "Includes the linked repository overview (README); linked repository files remain online.", "epub_bytes": 7800, "citation": "SPUR Content Telemetry — SPUR Coalition, 2026", "attribution": "SPUR Coalition, 2026", "combined_figures": 0 }, { "id": 45, "theme": "Attribution, telemetry, and demand signals", "title": "Best Practice on Generative and Agentic AI usage metrics", "url": "https://www.countermetrics.org/code-of-practice/best-practice/bp-ai/", "page": 4, "folder": "06 - Attribution, telemetry, and demand signals", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.countermetrics.org', port=443): Max retries exceeded with url: /code-of-practice/best-practice/bp-ai/ (Caused by NameResolutionError(\"HTTPSConnection(host='www.countermetrics.org', port=443): Failed to resolve 'www.countermetrics.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/045.html", "final_url": "https://www.countermetrics.org/code-of-practice/best-practice/bp-ai/", "result": "epub", "text_characters": 14768, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "06 - Attribution, telemetry, and demand signals/45 - Best Practice on Generative and Agentic AI usage metrics.epub", "note": "", "epub_bytes": 8502, "citation": "Best Practice on Generative and Agentic AI usage metrics — COUNTER Code of Practice, Release 5.1.1, 2026", "attribution": "COUNTER Code of Practice, Release 5.1.1, 2026", "combined_figures": 0 }, { "id": 46, "theme": "Attribution, telemetry, and demand signals", "title": "AI News Audit: How AI Models Use and Distribute Canadian Journalism", "url": "https://mediatechdemocracy.com/en/publications/ai-news-audit_2026/", "page": 4, "folder": "06 - Attribution, telemetry, and demand signals", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='mediatechdemocracy.com', port=443): Max retries exceeded with url: /en/publications/ai-news-audit_2026/ (Caused by NameResolutionError(\"HTTPSConnection(host='mediatechdemocracy.com', port=443): Failed to resolve 'mediatechdemocracy.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/046-full.pdf", "final_url": "https://mediatechdemocracy.com/files/publications/ai-news-audit_2026.pdf", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 21, "conversion": "PDF text with embedded original pages", "epub": "06 - Attribution, telemetry, and demand signals/46 - AI News Audit- How AI Models Use and Distribute Canadian Journalism.epub", "epub_bytes": 3812257, "citation": "AI News Audit: How AI Models Use and Distribute Canadian Journalism — Taylor Owen and Aengus Bridgman, McGill University, 2026", "attribution": "Taylor Owen and Aengus Bridgman, McGill University, 2026", "combined_figures": 6 }, { "id": 47, "theme": "Attribution, telemetry, and demand signals", "title": "We Need Google Trends for AI", "url": "https://www.techpolicy.press/we-need-google-trends-for-ai/", "page": 4, "folder": "06 - Attribution, telemetry, and demand signals", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.techpolicy.press', port=443): Max retries exceeded with url: /we-need-google-trends-for-ai/ (Caused by NameResolutionError(\"HTTPSConnection(host='www.techpolicy.press', port=443): Failed to resolve 'www.techpolicy.press' ([Errno -2] Name or service not known)\"))", "source": "_sources/047.html", "final_url": "https://www.techpolicy.press/we-need-google-trends-for-ai/", "result": "epub", "text_characters": 14598, "images_saved": 5, "images_missing": 0, "conversion": "Web article extraction", "epub": "06 - Attribution, telemetry, and demand signals/47 - We Need Google Trends for AI.epub", "note": "", "epub_bytes": 397358, "citation": "We Need Google Trends for AI — Marsh, Tech Policy Press, 2026", "attribution": "Marsh, Tech Policy Press, 2026", "combined_figures": 0 }, { "id": 48, "theme": "Attribution, telemetry, and demand signals", "title": "How we use AI in our journalism", "url": "https://www.axios.com/about/ai", "page": 4, "folder": "06 - Attribution, telemetry, and demand signals", "supplementary": false, "status": "supplied", "source": "redown/Axios - Artificial Intelligence Statement.pdf", "final_url": "https://www.axios.com/about/ai", "result": "epub", "note": "Full text from the PDF supplied by the user. Original PDF pages are embedded for reference. Website menus, unrelated recommendations, and print-page overlap were removed from the reading text.", "citation": "How we use AI in our journalism — Axios, 2026", "attribution": "Axios, 2026", "conversion": "User-supplied PDF, reflowable text and original pages", "epub": "06 - Attribution, telemetry, and demand signals/48 - How we use AI in our journalism.epub", "epub_bytes": 392025, "pages": 6, "combined_figures": 0 }, { "id": 49, "theme": "Attribution, telemetry, and demand signals", "title": "Building Trust in AI-Mediated Knowledge", "url": "https://sites.mit.edu/vraix/", "page": 4, "folder": "06 - Attribution, telemetry, and demand signals", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='sites.mit.edu', port=443): Max retries exceeded with url: /vraix/ (Caused by NameResolutionError(\"HTTPSConnection(host='sites.mit.edu', port=443): Failed to resolve 'sites.mit.edu' ([Errno -2] Name or service not known)\"))", "source": "_sources/049.html", "final_url": "https://sites.mit.edu/vraix/", "result": "epub", "text_characters": 6330, "images_saved": 0, "images_missing": 3, "conversion": "Web article extraction", "epub": "06 - Attribution, telemetry, and demand signals/49 - Building Trust in AI-Mediated Knowledge.epub", "note": "", "epub_bytes": 6283, "citation": "Building Trust in AI-Mediated Knowledge — MIT VRAIX, 2026", "attribution": "MIT VRAIX, 2026", "combined_figures": 0 }, { "id": 50, "theme": "Information quality and pluralism", "title": "Synthetic Sources?: Auditing Generative Search Engine Citations for Evidence of AI-Generated Sources", "url": "https://arxiv.org/abs/2605.23684", "page": 4, "folder": "07 - Information quality and pluralism", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2605.23684 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/050.pdf", "final_url": "https://arxiv.org/abs/2605.23684", "result": "epub", "pages": 22, "conversion": "PDF text with embedded original pages", "epub": "07 - Information quality and pluralism/50 - Synthetic Sources-- Auditing Generative Search Engine Citations for Evidence of AI-Generated Sources.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 4535188, "citation": "Synthetic Sources?: Auditing Generative Search Engine Citations for Evidence of AI-Generated Sources — Allaham and Diakopoulos, arXiv, 2026", "attribution": "Allaham and Diakopoulos, arXiv, 2026", "combined_figures": 6 }, { "id": 51, "theme": "Information quality and pluralism", "title": "AI Information Map", "url": "https://journalismresearch.org/ai-pluralism-monitor/", "page": 4, "folder": "07 - Information quality and pluralism", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='journalismresearch.org', port=443): Max retries exceeded with url: /ai-pluralism-monitor/ (Caused by NameResolutionError(\"HTTPSConnection(host='journalismresearch.org', port=443): Failed to resolve 'journalismresearch.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/051.html", "final_url": "https://journalismresearch.org/ai-pluralism-monitor/", "result": "epub", "text_characters": 11961, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "07 - Information quality and pluralism/51 - AI Information Map.epub", "note": "", "epub_bytes": 7573, "citation": "AI Information Map — Media and Journalism Research Center, 2026", "attribution": "Media and Journalism Research Center, 2026", "combined_figures": 0 }, { "id": 52, "theme": "Information quality and pluralism", "title": "How public datasets constrain the development of diversity-aware news recommender systems, and what law could do about it", "url": "https://arxiv.org/pdf/2510.05952", "page": 4, "folder": "07 - Information quality and pluralism", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2510.05952 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/052.pdf", "final_url": "https://arxiv.org/pdf/2510.05952", "result": "epub", "pages": 18, "conversion": "PDF text with embedded original pages", "epub": "07 - Information quality and pluralism/52 - How public datasets constrain the development of diversity-aware news recommender systems, and what law could do about it.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 3066111, "citation": "How public datasets constrain the development of diversity-aware news recommender", "attribution": "", "combined_figures": 1 }, { "id": 53, "theme": "Information quality and pluralism", "title": "The algorithm’s grip: how digital gatekeepers are reshaping media pluralism", "url": "https://iicintermedia.org/vol-53-issue-4/the-algorithms-grip-how-digital-gatekeepers-are-reshaping-media-pluralism/", "page": 4, "folder": "07 - Information quality and pluralism", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='iicintermedia.org', port=443): Max retries exceeded with url: /vol-53-issue-4/the-algorithms-grip-how-digital-gatekeepers-are-reshaping-media-pluralism/ (Caused by NameResolutionError(\"HTTPSConnection(host='iicintermedia.org', port=443): Failed to resolve 'iicintermedia.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/053.html", "final_url": "https://iicintermedia.org/vol-53-issue-4/the-algorithms-grip-how-digital-gatekeepers-are-reshaping-media-pluralism/", "result": "epub", "text_characters": 21539, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "07 - Information quality and pluralism/53 - The algorithm’s grip- how digital gatekeepers are reshaping media pluralism.epub", "note": "", "epub_bytes": 11700, "citation": "The algorithm’s grip: how digital gatekeepers are reshaping media pluralism - Intermedia, 2025", "attribution": "Intermedia, 2025", "combined_figures": 0 }, { "id": 54, "theme": "Information quality and pluralism", "title": "Restraining the formation of filter bubbles with algorithmic affordances: Toward more balanced information consumption and decreased attitude extremity", "url": "https://asistdl.onlinelibrary.wiley.com/doi/epdf/10.1002/asi.24988?saml_referrer", "page": 5, "folder": "07 - Information quality and pluralism", "supplementary": false, "status": "failed", "error": "HTTPSConnectionPool(host='asistdl.onlinelibrary.wiley.com', port=443): Max retries exceeded with url: /doi/epdf/10.1002/asi.24988?saml_referrer (Caused by NameResolutionError(\"HTTPSConnection(host='asistdl.onlinelibrary.wiley.com', port=443): Failed to resolve 'asistdl.onlinelibrary.wiley.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/054.html", "final_url": "https://asistdl.onlinelibrary.wiley.com/doi/epdf/10.1002/asi.24988?saml_referrer", "result": "unavailable", "note": "The source blocks automated access (HTTP 403); no full text retrieved.", "citation": "Restraining the formation of filter bubbles with algorithmic affordances: Toward more balanced information consumption and decreased attitude extremity - Jiang et al. Journal of the Association for Information Science and Technology, 2025", "attribution": "Jiang et al. Journal of the Association for Information Science and Technology, 2025" }, { "id": 55, "theme": "Agents, loyalty, and fiduciary responsibility", "title": "AI Alignment and Fiduciary Obligation", "url": "https://arxiv.org/abs/2608.02660", "page": 5, "folder": "08 - Agents, loyalty, and fiduciary responsibility", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2608.02660 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/055.pdf", "final_url": "https://arxiv.org/abs/2608.02660", "result": "epub", "pages": 13, "conversion": "PDF text with embedded original pages", "epub": "08 - Agents, loyalty, and fiduciary responsibility/55 - AI Alignment and Fiduciary Obligation.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 3726238, "citation": "AI Alignment and Fiduciary Obligation — Lange, AIES 2026, 2026", "attribution": "Lange, AIES 2026, 2026", "combined_figures": 0 }, { "id": 56, "theme": "Agents, loyalty, and fiduciary responsibility", "title": "Encoding Loyalty Principles into AI Agents' Behavior", "url": "https://innovation.consumerreports.org/encoding-loyalty-principles-into-ai-agents-behavior/", "page": 5, "folder": "08 - Agents, loyalty, and fiduciary responsibility", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='innovation.consumerreports.org', port=443): Max retries exceeded with url: /encoding-loyalty-principles-into-ai-agents-behavior/ (Caused by NameResolutionError(\"HTTPSConnection(host='innovation.consumerreports.org', port=443): Failed to resolve 'innovation.consumerreports.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/056.html", "final_url": "https://innovation.consumerreports.org/encoding-loyalty-principles-into-ai-agents-behavior/", "result": "epub", "text_characters": 14393, "images_saved": 0, "images_missing": 5, "conversion": "Web article extraction", "epub": "08 - Agents, loyalty, and fiduciary responsibility/56 - Encoding Loyalty Principles into AI Agents' Behavior.epub", "note": "", "epub_bytes": 9771, "citation": "Encoding Loyalty Principles into AI Agents' Behavior — Cheong, Innovation at Consumer Reports, 2025", "attribution": "Cheong, Innovation at Consumer Reports, 2025", "combined_figures": 0 }, { "id": 57, "theme": "Agents, loyalty, and fiduciary responsibility", "title": "Build Agent Advocates, Not Platform Agents", "url": "https://arxiv.org/abs/2505.04345", "page": 5, "folder": "08 - Agents, loyalty, and fiduciary responsibility", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2505.04345 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/057.pdf", "final_url": "https://arxiv.org/abs/2505.04345", "result": "epub", "pages": 17, "conversion": "PDF text with embedded original pages", "epub": "08 - Agents, loyalty, and fiduciary responsibility/57 - Build Agent Advocates, Not Platform Agents.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 4251578, "citation": "Build Agent Advocates, Not Platform Agents — Kapoor et al., arXiv, 2025", "attribution": "Kapoor et al., arXiv, 2025", "combined_figures": 1 }, { "id": 58, "theme": "Agents, loyalty, and fiduciary responsibility", "title": "The moral case for using language model agents for recommendation", "url": "https://www.tandfonline.com/doi/full/10.1080/0020174X.2025.2515579", "page": 5, "folder": "08 - Agents, loyalty, and fiduciary responsibility", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.tandfonline.com', port=443): Max retries exceeded with url: /doi/full/10.1080/0020174X.2025.2515579 (Caused by NameResolutionError(\"HTTPSConnection(host='www.tandfonline.com', port=443): Failed to resolve 'www.tandfonline.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/058-full.pdf", "final_url": "https://arxiv.org/pdf/2410.12123", "note": "Open-access author preprint; may differ from the published version. Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 22, "conversion": "PDF text with embedded original pages", "epub": "08 - Agents, loyalty, and fiduciary responsibility/58 - The moral case for using language model agents for recommendation.epub", "epub_bytes": 3533981, "citation": "The moral case for using language model agents for recommendation — Lazar et al., Inquiry, 2025 (paywalled)", "attribution": "Lazar et al., Inquiry, 2025 (paywalled)", "combined_figures": 2 }, { "id": 59, "theme": "Agents, loyalty, and fiduciary responsibility", "title": "Who Do AI Agents Work For? Power and Control in the Next Internet", "url": "https://www.openmarketsinstitute.org/publications/who-do-ai-agents-work-for", "page": 5, "folder": "08 - Agents, loyalty, and fiduciary responsibility", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.openmarketsinstitute.org', port=443): Max retries exceeded with url: /publications/who-do-ai-agents-work-for (Caused by NameResolutionError(\"HTTPSConnection(host='www.openmarketsinstitute.org', port=443): Failed to resolve 'www.openmarketsinstitute.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/059-full.pdf", "final_url": "https://static1.squarespace.com/static/5e449c8c3ef68d752f3e70dc/t/6a1deaa45ead0411b1ccebf0/1780345508178/Who+Do+AI+Agents+Work+For-Hubbard-OMI-June2026-WEB-2.pdf", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 29, "conversion": "PDF text with embedded original pages", "epub": "08 - Agents, loyalty, and fiduciary responsibility/59 - Who Do AI Agents Work For- Power and Control in the Next Internet.epub", "epub_bytes": 4478645, "citation": "Who Do AI Agents Work For? Power and Control in the Next Internet — Hubbard, Open Markets Institute, 2026", "attribution": "Hubbard, Open Markets Institute, 2026", "combined_figures": 2 }, { "id": 60, "theme": "Publishers building for agents", "title": "NLWeb", "url": "https://github.com/nlweb-ai/NLWeb", "page": 5, "folder": "09 - Publishers building for agents", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='github.com', port=443): Max retries exceeded with url: /nlweb-ai/NLWeb (Caused by NameResolutionError(\"HTTPSConnection(host='github.com', port=443): Failed to resolve 'github.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/060.html", "final_url": "https://github.com/nlweb-ai/NLWeb", "result": "epub", "text_characters": 5283, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "09 - Publishers building for agents/60 - NLWeb.epub", "note": "Includes the linked repository overview (README); linked repository files remain online.", "epub_bytes": 5954, "citation": "NLWeb — R.V. Guha, 2026", "attribution": "R.V. Guha, 2026", "combined_figures": 0 }, { "id": 61, "theme": "Publishers building for agents", "title": "Axios preps new Axios Direct feeds for AI models, agents as revenue tops 2026 goal", "url": "https://digiday.com/media/axios-preps-new-axios-direct-feeds-for-ai-models-agents-as-revenue-tops-2026-goal/", "page": 5, "folder": "09 - Publishers building for agents", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='digiday.com', port=443): Max retries exceeded with url: /media/axios-preps-new-axios-direct-feeds-for-ai-models-agents-as-revenue-tops-2026-goal/ (Caused by NameResolutionError(\"HTTPSConnection(host='digiday.com', port=443): Failed to resolve 'digiday.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/061.html", "final_url": "https://digiday.com/media/axios-preps-new-axios-direct-feeds-for-ai-models-agents-as-revenue-tops-2026-goal/", "result": "epub", "text_characters": 6543, "images_saved": 4, "images_missing": 0, "conversion": "Web article extraction", "epub": "09 - Publishers building for agents/61 - Axios preps new Axios Direct feeds for AI models, agents as revenue tops 2026 goal.epub", "note": "", "epub_bytes": 158064, "citation": "Axios preps new Axios Direct feeds for AI models, agents as revenue tops 2026 goal — Peterson, Digiday, 2026", "attribution": "Peterson, Digiday, 2026", "combined_figures": 0 }, { "id": 62, "theme": "Publishers building for agents", "title": "New AI-powered tools connect locals to trusted community resources", "url": "https://www.torontotoday.ca/local/more-news/new-ai-powered-tools-connect-locals-to-trusted-community-resources-12785229", "page": 5, "folder": "09 - Publishers building for agents", "supplementary": false, "status": "supplied", "source": "redown/New AI-powered tools will help connect locals to trusted community resources - TorontoToday.ca.pdf", "final_url": "https://www.torontotoday.ca/local/more-news/new-ai-powered-tools-connect-locals-to-trusted-community-resources-12785229", "result": "epub", "note": "Full text from the PDF supplied by the user. Original PDF pages are embedded for reference. Website menus, unrelated recommendations, and print-page overlap were removed from the reading text.", "citation": "New AI-powered tools connect locals to trusted community resources — Village Media, Toronto Today, 2026", "attribution": "Village Media, Toronto Today, 2026", "conversion": "User-supplied PDF, reflowable text and original pages", "epub": "09 - Publishers building for agents/62 - New AI-powered tools connect locals to trusted community resources.epub", "epub_bytes": 484215, "pages": 4, "combined_figures": 1 }, { "id": 63, "theme": "Publishers building for agents", "title": "After the Feed", "url": "https://newpublic.org/afterthefeed", "page": 5, "folder": "09 - Publishers building for agents", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='newpublic.org', port=443): Max retries exceeded with url: /afterthefeed (Caused by NameResolutionError(\"HTTPSConnection(host='newpublic.org', port=443): Failed to resolve 'newpublic.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/063-report.pdf", "final_url": "https://doc-0c-bs-slides.googleusercontent.com/export/8o20gl0mgtl0fnnbn5ic4njno4/7k26a9bv1ecfsf3u5q6cefo7jk/1791183085000/105250506097979753968/*/1z5KiIEeQetnF7kJBYihCYoSWr3S0Mj1qK3LVuifIsqU?exportFormat=pdf", "result": "epub", "pages": 82, "conversion": "PDF text with embedded original pages", "epub": "09 - Publishers building for agents/63 - After the Feed.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 5287107, "citation": "After the Feed — Pariser et al., New_Public, 2026", "attribution": "Pariser et al., New_Public, 2026", "combined_figures": 64 }, { "id": 64, "theme": "Publishers building for agents", "title": "AI Agents Are Coming for News. Can Publishers Reclaim Control?", "url": "https://www.cjr.org/tow_center/ai-agents-are-coming-for-news-can-publishers-reclaim-control.php", "page": 5, "folder": "09 - Publishers building for agents", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.cjr.org', port=443): Max retries exceeded with url: /tow_center/ai-agents-are-coming-for-news-can-publishers-reclaim-control.php (Caused by NameResolutionError(\"HTTPSConnection(host='www.cjr.org', port=443): Failed to resolve 'www.cjr.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/064.html", "final_url": "https://www.cjr.org/tow_center/ai-agents-are-coming-for-news-can-publishers-reclaim-control.php", "result": "epub", "text_characters": 7281, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "09 - Publishers building for agents/64 - AI Agents Are Coming for News. Can Publishers Reclaim Control-.epub", "note": "", "epub_bytes": 7958, "citation": "AI Agents Are Coming for News. Can Publishers Reclaim Control? - Chandrasekar and Jaźwińska, Columbia Jorunalism Review, 2026", "attribution": "Chandrasekar and Jaźwińska, Columbia Jorunalism Review, 2026", "combined_figures": 0 }, { "id": 65, "theme": "Publishers building for agents", "title": "Jaźwińska", "url": "https://www.cjr.org/author/klaudia-jazwinska", "page": 5, "folder": "09 - Publishers building for agents", "supplementary": true, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.cjr.org', port=443): Max retries exceeded with url: /author/klaudia-jazwinska (Caused by NameResolutionError(\"HTTPSConnection(host='www.cjr.org', port=443): Failed to resolve 'www.cjr.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/065.html", "final_url": "https://www.cjr.org/author/klaudia-jazwinska", "result": "epub", "text_characters": 606, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "09 - Publishers building for agents/65 - Jaźwińska.epub", "note": "Supplementary author-profile link from the syllabus.", "epub_bytes": 3445, "combined_figures": 0 }, { "id": 66, "theme": "Publishers building for agents", "title": "Some thoughts on Agent Ecosystems", "url": "https://docs.google.com/document/d/1rZIRGPIocijz2v_Fx3V6ZcNkb5Fq9i-9q9d920-DtPE/", "page": 5, "folder": "09 - Publishers building for agents", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='docs.google.com', port=443): Max retries exceeded with url: /document/d/1rZIRGPIocijz2v_Fx3V6ZcNkb5Fq9i-9q9d920-DtPE/export?format=epub (Caused by NameResolutionError(\"HTTPSConnection(host='docs.google.com', port=443): Failed to resolve 'docs.google.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/066.epub", "final_url": "https://docs.google.com/document/d/1rZIRGPIocijz2v_Fx3V6ZcNkb5Fq9i-9q9d920-DtPE/", "result": "epub", "epub": "09 - Publishers building for agents/66 - Some thoughts on Agent Ecosystems.epub", "conversion": "Publisher EPUB export", "citation": "Some thoughts on Agent Ecosystems — R.V. Guha, 2026", "attribution": "R.V. Guha, 2026", "combined_figures": 0 }, { "id": 67, "theme": "Open protocols and interfaces", "title": "Model Context Protocol Specification, revision 2026-07-28", "url": "https://modelcontextprotocol.io/specification/2026-07-28", "page": 5, "folder": "10 - Open protocols and interfaces", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='modelcontextprotocol.io', port=443): Max retries exceeded with url: /specification/2026-07-28 (Caused by NameResolutionError(\"HTTPSConnection(host='modelcontextprotocol.io', port=443): Failed to resolve 'modelcontextprotocol.io' ([Errno -2] Name or service not known)\"))", "source": "_sources/067.html", "final_url": "https://modelcontextprotocol.io/specification/2026-07-28", "result": "epub", "text_characters": 4169, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "10 - Open protocols and interfaces/67 - Model Context Protocol Specification, revision 2026-07-28.epub", "note": "This EPUB contains the linked specification overview page; its external section links remain online.", "epub_bytes": 5496, "citation": "Model Context Protocol Specification, revision 2026-07-28 — Agentic AI Foundation, 2026", "attribution": "Agentic AI Foundation, 2026", "combined_figures": 0 }, { "id": 68, "theme": "Open protocols and interfaces", "title": "Linux Foundation Announces the Formation of the Agentic AI Foundation (AAIF)", "url": "https://www.linuxfoundation.org/press/linux-foundation-announces-the-formation-of-the-agentic-ai-foundation", "page": 5, "folder": "10 - Open protocols and interfaces", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.linuxfoundation.org', port=443): Max retries exceeded with url: /press/linux-foundation-announces-the-formation-of-the-agentic-ai-foundation (Caused by NameResolutionError(\"HTTPSConnection(host='www.linuxfoundation.org', port=443): Failed to resolve 'www.linuxfoundation.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/068.html", "final_url": "https://www.linuxfoundation.org/press/linux-foundation-announces-the-formation-of-the-agentic-ai-foundation", "result": "epub", "text_characters": 12073, "images_saved": 1, "images_missing": 0, "conversion": "Web article extraction", "epub": "10 - Open protocols and interfaces/68 - Linux Foundation Announces the Formation of the Agentic AI Foundation (AAIF).epub", "note": "", "epub_bytes": 55716, "citation": "Linux Foundation Announces the Formation of the Agentic AI Foundation (AAIF) — The Linux Foundation, 2025", "attribution": "The Linux Foundation, 2025", "combined_figures": 0 }, { "id": 69, "theme": "Open protocols and interfaces", "title": "Governance Gaps in Agent Interoperability Protocols: What MCP, A2A, and ACP Cannot Express", "url": "https://arxiv.org/abs/2606.31498", "page": 6, "folder": "10 - Open protocols and interfaces", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2606.31498 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/069.pdf", "final_url": "https://arxiv.org/abs/2606.31498", "result": "epub", "pages": 7, "conversion": "PDF text with embedded original pages", "epub": "10 - Open protocols and interfaces/69 - Governance Gaps in Agent Interoperability Protocols- What MCP, A2A, and ACP Cannot Express.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 1533160, "citation": "Governance Gaps in Agent Interoperability Protocols: What MCP, A2A, and ACP Cannot Express — Kang and Diponegoro, arXiv (preprint), 2026", "attribution": "Kang and Diponegoro, arXiv (preprint), 2026", "combined_figures": 1 }, { "id": 70, "theme": "Open protocols and interfaces", "title": "Why the AI Policy Debate Should Focus More on the Harness and Protocol Layers", "url": "https://techpolicy.press/why-the-ai-policy-debate-should-focus-more-on-the-harness-and-protocol-layers", "page": 6, "folder": "10 - Open protocols and interfaces", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='techpolicy.press', port=443): Max retries exceeded with url: /why-the-ai-policy-debate-should-focus-more-on-the-harness-and-protocol-layers (Caused by NameResolutionError(\"HTTPSConnection(host='techpolicy.press', port=443): Failed to resolve 'techpolicy.press' ([Errno -2] Name or service not known)\"))", "source": "_sources/070.html", "final_url": "https://techpolicy.press/why-the-ai-policy-debate-should-focus-more-on-the-harness-and-protocol-layers", "result": "epub", "text_characters": 45859, "images_saved": 3, "images_missing": 0, "conversion": "Web article extraction", "epub": "10 - Open protocols and interfaces/70 - Why the AI Policy Debate Should Focus More on the Harness and Protocol Layers.epub", "note": "", "epub_bytes": 541556, "citation": "Why the AI Policy Debate Should Focus More on the Harness and Protocol Layers — Justin Hendrix, Tech Policy Press, 2026", "attribution": "Justin Hendrix, Tech Policy Press, 2026", "combined_figures": 0 }, { "id": 71, "theme": "Open protocols and interfaces", "title": "OpenClaw Shows AI Agents Don’t Need to Be Vertically Integrated", "url": "https://techpolicy.press/openclaw-shows-ai-agents-dont-need-to-be-vertically-integrated", "page": 6, "folder": "10 - Open protocols and interfaces", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='techpolicy.press', port=443): Max retries exceeded with url: /openclaw-shows-ai-agents-dont-need-to-be-vertically-integrated (Caused by NameResolutionError(\"HTTPSConnection(host='techpolicy.press', port=443): Failed to resolve 'techpolicy.press' ([Errno -2] Name or service not known)\"))", "source": "_sources/071.html", "final_url": "https://techpolicy.press/openclaw-shows-ai-agents-dont-need-to-be-vertically-integrated", "result": "epub", "text_characters": 7545, "images_saved": 3, "images_missing": 0, "conversion": "Web article extraction", "epub": "10 - Open protocols and interfaces/71 - OpenClaw Shows AI Agents Don’t Need to Be Vertically Integrated.epub", "note": "", "epub_bytes": 146574, "citation": "OpenClaw Shows AI Agents Don’t Need to Be Vertically Integrated — FitzGerald, Tech Policy Press, 2026", "attribution": "FitzGerald, Tech Policy Press, 2026", "combined_figures": 0 }, { "id": 72, "theme": "Market structure", "title": "Artificial Intelligence, Competition, and Welfare", "url": "https://www.nber.org/papers/w34444", "page": 6, "folder": "11 - Market structure", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.nber.org', port=443): Max retries exceeded with url: /papers/w34444 (Caused by NameResolutionError(\"HTTPSConnection(host='www.nber.org', port=443): Failed to resolve 'www.nber.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/072-full.pdf", "final_url": "https://www.nber.org/system/files/working_papers/w34444/revisions/w34444.rev0.pdf", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 47, "conversion": "PDF text with embedded original pages", "epub": "11 - Market structure/72 - Artificial Intelligence, Competition, and Welfare.epub", "epub_bytes": 6539548, "citation": "Artificial Intelligence, Competition, and Welfare — Fiona Scott Morton and Susan Athey, NBER, 2025", "attribution": "Fiona Scott Morton and Susan Athey, NBER, 2025", "combined_figures": 1 }, { "id": 73, "theme": "Market structure", "title": "Artificial Power: 2025 Landscape Report", "url": "https://ainowinstitute.org/publications/research/ai-now-2025-landscape-report", "page": 6, "folder": "11 - Market structure", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='ainowinstitute.org', port=443): Max retries exceeded with url: /publications/research/ai-now-2025-landscape-report (Caused by NameResolutionError(\"HTTPSConnection(host='ainowinstitute.org', port=443): Failed to resolve 'ainowinstitute.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/073-full.pdf", "final_url": "https://ainowinstitute.org/wp-content/uploads/2025/06/FINAL-20250609_AINowLandscapeReport_Full.pdf", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 123, "conversion": "PDF text with embedded original pages", "epub": "11 - Market structure/73 - Artificial Power- 2025 Landscape Report.epub", "epub_bytes": 28635466, "citation": "Artificial Power: 2025 Landscape Report — Brennan, AI Now Institute, 2025", "attribution": "Brennan, AI Now Institute, 2025", "combined_figures": 39 }, { "id": 74, "theme": "Market structure", "title": "Taming the Hyperscalers", "url": "https://www.openmarketsinstitute.eu/publications/report-taming-the-hyperscalers", "page": 6, "folder": "11 - Market structure", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.openmarketsinstitute.eu', port=443): Max retries exceeded with url: /publications/report-taming-the-hyperscalers (Caused by NameResolutionError(\"HTTPSConnection(host='www.openmarketsinstitute.eu', port=443): Failed to resolve 'www.openmarketsinstitute.eu' ([Errno -2] Name or service not known)\"))", "source": "_sources/074-full.pdf", "final_url": "https://static1.squarespace.com/static/5e449c8c3ef68d752f3e70dc/t/698b5879862ad038dcc47a0f/1770739833199/eucloudpaper+%283%29.pdf", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 12, "conversion": "PDF text with embedded original pages", "epub": "11 - Market structure/74 - Taming the Hyperscalers.epub", "epub_bytes": 2137779, "citation": "Taming the Hyperscalers — George Colville and Max von Thun, Open Markets Institute Europe, 2026", "attribution": "George Colville and Max von Thun, Open Markets Institute Europe, 2026", "combined_figures": 4 }, { "id": 75, "theme": "Market structure", "title": "Human Native is joining Cloudflare", "url": "https://blog.cloudflare.com/human-native-joins-cloudflare/", "page": 6, "folder": "11 - Market structure", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='blog.cloudflare.com', port=443): Max retries exceeded with url: /human-native-joins-cloudflare/ (Caused by NameResolutionError(\"HTTPSConnection(host='blog.cloudflare.com', port=443): Failed to resolve 'blog.cloudflare.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/075.html", "final_url": "https://blog.cloudflare.com/human-native-joins-cloudflare/", "result": "epub", "text_characters": 4955, "images_saved": 1, "images_missing": 0, "conversion": "Web article extraction", "epub": "11 - Market structure/75 - Human Native is joining Cloudflare.epub", "note": "", "epub_bytes": 215620, "citation": "Human Native is joining Cloudflare — Allen and Smith, Cloudflare Blog, 2026", "attribution": "Allen and Smith, Cloudflare Blog, 2026", "combined_figures": 0 }, { "id": 76, "theme": "Market structure", "title": "Governing the Algorithmic City", "url": "https://onlinelibrary.wiley.com/doi/10.1111/papa.12279?af=R", "page": 6, "folder": "11 - Market structure", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='onlinelibrary.wiley.com', port=443): Max retries exceeded with url: /doi/10.1111/papa.12279?af=R (Caused by NameResolutionError(\"HTTPSConnection(host='onlinelibrary.wiley.com', port=443): Failed to resolve 'onlinelibrary.wiley.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/076-full.pdf", "final_url": "https://arxiv.org/pdf/2410.20720", "note": "Open-access author preprint; may differ from the published version. Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 52, "conversion": "PDF text with embedded original pages", "epub": "11 - Market structure/76 - Governing the Algorithmic City.epub", "epub_bytes": 9660962, "citation": "Governing the Algorithmic City — Lazar, Philosophy & Public Affairs, 2025", "attribution": "Lazar, Philosophy & Public Affairs, 2025", "combined_figures": 4 }, { "id": 77, "theme": "Market structure", "title": "Communicative Justice and the Distribution of Attention", "url": "https://knightcolumbia.org/content/communicative-justice-and-the-distribution-of-attention", "page": 6, "folder": "11 - Market structure", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='knightcolumbia.org', port=443): Max retries exceeded with url: /content/communicative-justice-and-the-distribution-of-attention (Caused by NameResolutionError(\"HTTPSConnection(host='knightcolumbia.org', port=443): Failed to resolve 'knightcolumbia.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/077.html", "final_url": "https://knightcolumbia.org/content/communicative-justice-and-the-distribution-of-attention", "result": "epub", "text_characters": 179105, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "11 - Market structure/77 - Communicative Justice and the Distribution of Attention.epub", "note": "", "epub_bytes": 63532, "citation": "Communicative Justice and the Distribution of Attention — Lazar, Knight First Amendment Institute, 2025", "attribution": "Lazar, Knight First Amendment Institute, 2025", "combined_figures": 0 }, { "id": 78, "theme": "Market structure", "title": "AI looks competitive. Is an oligopoly coming anyway?", "url": "https://modeleconomy.substack.com/p/ai-looks-competitive-is-an-oligopoly", "page": 6, "folder": "11 - Market structure", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='modeleconomy.substack.com', port=443): Max retries exceeded with url: /p/ai-looks-competitive-is-an-oligopoly (Caused by NameResolutionError(\"HTTPSConnection(host='modeleconomy.substack.com', port=443): Failed to resolve 'modeleconomy.substack.com' ([Errno -2] Name or service not known)\"))", "source": "_sources/078.html", "final_url": "https://modeleconomy.substack.com/p/ai-looks-competitive-is-an-oligopoly", "result": "epub", "text_characters": 9771, "images_saved": 2, "images_missing": 0, "conversion": "Web article extraction", "epub": "11 - Market structure/78 - AI looks competitive. Is an oligopoly coming anyway-.epub", "note": "", "epub_bytes": 143912, "citation": "AI looks competitive. Is an oligopoly coming anyway? — Max von Thun and Roa Powell, Model Economy Substack, 2026", "attribution": "Max von Thun and Roa Powell, Model Economy Substack, 2026", "combined_figures": 0 }, { "id": 79, "theme": "Remedies and interventions", "title": "Designing Europe’s Search Data Sharing Rules for Competition in the AI Era", "url": "https://kgi.georgetown.edu/research-and-commentary/designing-europes-search-data-sharing-rules-for-competition-in-the-ai-era/", "page": 6, "folder": "12 - Remedies and interventions", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='kgi.georgetown.edu', port=443): Max retries exceeded with url: /research-and-commentary/designing-europes-search-data-sharing-rules-for-competition-in-the-ai-era/ (Caused by NameResolutionError(\"HTTPSConnection(host='kgi.georgetown.edu', port=443): Failed to resolve 'kgi.georgetown.edu' ([Errno -2] Name or service not known)\"))", "source": "_sources/079.html", "final_url": "https://kgi.georgetown.edu/research-and-commentary/designing-europes-search-data-sharing-rules-for-competition-in-the-ai-era/", "result": "epub", "text_characters": 10434, "images_saved": 0, "images_missing": 0, "conversion": "Web article extraction", "epub": "12 - Remedies and interventions/79 - Designing Europe’s Search Data Sharing Rules for Competition in the AI Era.epub", "note": "", "epub_bytes": 8517, "citation": "Designing Europe’s Search Data Sharing Rules for Competition in the AI Era — Alissa Cooper, Knight-Georgetown Institute, 2026", "attribution": "Alissa Cooper, Knight-Georgetown Institute, 2026", "combined_figures": 0 }, { "id": 80, "theme": "Remedies and interventions", "title": "Commission provides guidance to Google for AI interoperability on Android and sharing of Google Search data under the Digital Markets Act", "url": "https://ec.europa.eu/commission/presscorner/detail/en/ip_26_1634", "page": 6, "folder": "12 - Remedies and interventions", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='ec.europa.eu', port=443): Max retries exceeded with url: /commission/presscorner/detail/en/ip_26_1634 (Caused by NameResolutionError(\"HTTPSConnection(host='ec.europa.eu', port=443): Failed to resolve 'ec.europa.eu' ([Errno -2] Name or service not known)\"))", "source": "_sources/080-full.pdf", "final_url": "https://ec.europa.eu/commission/presscorner/api/files/document/print/en/ip_26_1634/IP_26_1634_EN.pdf", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 3, "conversion": "PDF text with embedded original pages", "epub": "12 - Remedies and interventions/80 - Commission provides guidance to Google for AI interoperability on Android and sharing of Google Search data under the Digital Markets Act.epub", "epub_bytes": 500199, "citation": "Commission provides guidance to Google for AI interoperability on Android and sharing of Google Search data under the Digital Markets Act — European Commission Press corner, 2026", "attribution": "European Commission Press corner, 2026", "combined_figures": 2 }, { "id": 81, "theme": "Remedies and interventions", "title": "Commission imposes interim measures on Meta to preserve free access to WhatsApp for rival AI assistants", "url": "https://ec.europa.eu/commission/presscorner/detail/en/ip_26_1276", "page": 6, "folder": "12 - Remedies and interventions", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='ec.europa.eu', port=443): Max retries exceeded with url: /commission/presscorner/detail/en/ip_26_1276 (Caused by NameResolutionError(\"HTTPSConnection(host='ec.europa.eu', port=443): Failed to resolve 'ec.europa.eu' ([Errno -2] Name or service not known)\"))", "source": "_sources/081-full.pdf", "final_url": "https://ec.europa.eu/commission/presscorner/api/files/document/print/en/ip_26_1276/IP_26_1276_EN.pdf", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "result": "epub", "pages": 2, "conversion": "PDF text with embedded original pages", "epub": "12 - Remedies and interventions/81 - Commission imposes interim measures on Meta to preserve free access to WhatsApp for rival AI assistants.epub", "epub_bytes": 465139, "citation": "Commission imposes interim measures on Meta to preserve free access to WhatsApp for rival AI assistants — European Commission Press corner, 2026", "attribution": "European Commission Press corner, 2026", "combined_figures": 2 }, { "id": 82, "theme": "Remedies and interventions", "title": "AI agents: the Autorité de la concurrence issues its opinion on the competitive functioning of the AI agents sector (Opinion 26-A-05)", "url": "https://www.autoritedelaconcurrence.fr/en/press-release/ai-agents-autorite-de-la-concurrence-issues-its-opinion-competitive-functioning-ai", "page": 6, "folder": "12 - Remedies and interventions", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.autoritedelaconcurrence.fr', port=443): Max retries exceeded with url: /en/press-release/ai-agents-autorite-de-la-concurrence-issues-its-opinion-competitive-functioning-ai (Caused by NameResolutionError(\"HTTPSConnection(host='www.autoritedelaconcurrence.fr', port=443): Failed to resolve 'www.autoritedelaconcurrence.fr' ([Errno -2] Name or service not known)\"))", "source": "_sources/082.html", "final_url": "https://www.autoritedelaconcurrence.fr/en/press-release/ai-agents-autorite-de-la-concurrence-issues-its-opinion-competitive-functioning-ai", "result": "epub", "text_characters": 20060, "images_saved": 7, "images_missing": 0, "conversion": "Web article extraction", "epub": "12 - Remedies and interventions/82 - AI agents- the Autorité de la concurrence issues its opinion on the competitive functioning of the AI agents sector (Opinion 26-A-05).epub", "note": "", "epub_bytes": 1649534, "citation": "AI agents: the Autorité de la concurrence issues its opinion on the competitive functioning of the AI agents sector (Opinion 26-A-05) — Autorité de la concurrence, 2026", "attribution": "Autorité de la concurrence, 2026", "combined_figures": 0 }, { "id": 83, "theme": "Remedies and interventions", "title": "CMA strengthens proposals allowing people choice over their search service", "url": "https://www.gov.uk/government/news/cma-strengthens-proposals-allowing-people-choice-over-their-search-service", "page": 7, "folder": "12 - Remedies and interventions", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.gov.uk', port=443): Max retries exceeded with url: /government/news/cma-strengthens-proposals-allowing-people-choice-over-their-search-service (Caused by NameResolutionError(\"HTTPSConnection(host='www.gov.uk', port=443): Failed to resolve 'www.gov.uk' ([Errno -2] Name or service not known)\"))", "source": "_sources/083.html", "final_url": "https://www.gov.uk/government/news/cma-strengthens-proposals-allowing-people-choice-over-their-search-service", "result": "epub", "text_characters": 3553, "images_saved": 1, "images_missing": 0, "conversion": "Web article extraction", "epub": "12 - Remedies and interventions/83 - CMA strengthens proposals allowing people choice over their search service.epub", "note": "", "epub_bytes": 13051, "citation": "CMA strengthens proposals allowing people choice over their search service — Competition and Markets Authority, 2026", "attribution": "Competition and Markets Authority, 2026", "combined_figures": 0 }, { "id": 84, "theme": "Remedies and interventions", "title": "The Google Remedies Turn Landmark Verdicts Into a Whimper", "url": "https://www.techpolicy.press/the-google-remedies-turn-landmark-verdicts-into-a-whimper/", "page": 7, "folder": "12 - Remedies and interventions", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='www.techpolicy.press', port=443): Max retries exceeded with url: /the-google-remedies-turn-landmark-verdicts-into-a-whimper/ (Caused by NameResolutionError(\"HTTPSConnection(host='www.techpolicy.press', port=443): Failed to resolve 'www.techpolicy.press' ([Errno -2] Name or service not known)\"))", "source": "_sources/084.html", "final_url": "https://www.techpolicy.press/the-google-remedies-turn-landmark-verdicts-into-a-whimper/", "result": "epub", "text_characters": 7060, "images_saved": 3, "images_missing": 0, "conversion": "Web article extraction", "epub": "12 - Remedies and interventions/84 - The Google Remedies Turn Landmark Verdicts Into a Whimper.epub", "note": "", "epub_bytes": 280613, "citation": "The Google Remedies Turn Landmark Verdicts Into a Whimper — Vaheesan, Tech Policy Press, 2026", "attribution": "Vaheesan, Tech Policy Press, 2026", "combined_figures": 0 }, { "id": 85, "theme": "Remedies and interventions", "title": "AI Regulation: Competition, Arbitrage & Regulatory Capture", "url": "https://scholarship.law.georgetown.edu/facpub/2647/", "page": 7, "folder": "12 - Remedies and interventions", "supplementary": false, "status": "supplied", "source": "redown/AI Regulation_ Competition Arbitrage & Regulatory Capture.pdf", "final_url": "https://scholarship.law.georgetown.edu/facpub/2647/", "result": "epub", "conversion": "User-supplied PDF, reflowable text and original pages", "epub": "12 - Remedies and interventions/85 - AI Regulation- Competition, Arbitrage & Regulatory Capture.epub", "note": "Full text from the PDF supplied by the user. Original PDF pages are embedded for reference.", "epub_bytes": 3722368, "citation": "AI Regulation: Competition, Arbitrage & Regulatory Capture —Filippo Lancieri, Theoretical Inquiries in Law 26(1), 239–262, 2025", "attribution": "", "pages": 25, "combined_figures": 3 }, { "id": 86, "theme": "Remedies and interventions", "title": "Toward an OSI-Inspired Stack for Agentic AI: From Fragmented Frameworks to Open Standards", "url": "https://www.researchgate.net/publication/400616318_Toward_an_OSI-Inspired_Stack_for_Agentic_AI_From_Fragmented_Frameworks_to_Open_Standards", "page": 7, "folder": "12 - Remedies and interventions", "supplementary": false, "status": "supplied", "source": "redown/Toward_an_OSI_Inspired_Interoperability_Stack_for_Agentic_AI__From_Fragmented_Frameworks_to_Open_Standards-5-2.pdf", "final_url": "https://zenodo.org/api/records/17099410/files/Toward_an_OSI_Inspired_Interoperability_Stack_for_Agentic_AI__From_Fragmented_Frameworks_to_Open_Standards-5.pdf/content", "note": "Full text from the PDF supplied by the user. Original PDF pages are embedded for reference.", "result": "epub", "pages": 12, "conversion": "User-supplied PDF, reflowable text and original pages", "epub": "12 - Remedies and interventions/86 - Toward an OSI-Inspired Stack for Agentic AI- From Fragmented Frameworks to Open Standards.epub", "epub_bytes": 2543963, "citation": "Toward an OSI-Inspired Stack for Agentic AI: From Fragmented Frameworks to Open Standards - Rodrigo-Ginés, National University of Distance Education (preprint), 2025", "attribution": "Rodrigo-Ginés, National University of Distance Education (preprint), 2025", "supplied_pdf_matches_existing": true, "combined_figures": 0 }, { "id": 87, "theme": "Remedies and interventions", "title": "Rodrigo-Ginés", "url": "https://www.researchgate.net/profile/Francisco-Javier-Rodrigo-Gines?_tp=eyJjb250ZXh0Ijp7ImZpcnN0UGFnZSI6InB1YmxpY2F0aW9uIiwicGFnZSI6InB1YmxpY2F0aW9uIn19", "page": 7, "folder": "12 - Remedies and interventions", "supplementary": true, "status": "failed", "error": "HTTPSConnectionPool(host='www.researchgate.net', port=443): Max retries exceeded with url: /profile/Francisco-Javier-Rodrigo-Gines?_tp=eyJjb250ZXh0Ijp7ImZpcnN0UGFnZSI6InB1YmxpY2F0aW9uIiwicGFnZSI6InB1YmxpY2F0aW9uIn19 (Caused by NameResolutionError(\"HTTPSConnection(host='www.researchgate.net', port=443): Failed to resolve 'www.researchgate.net' ([Errno -2] Name or service not known)\"))", "source": "_sources/087.html", "final_url": "https://www.researchgate.net/profile/Francisco-Javier-Rodrigo-Gines?_tp=eyJjb250ZXh0Ijp7ImZpcnN0UGFnZSI6InB1YmxpY2F0aW9uIiwicGFnZSI6InB1YmxpY2F0aW9uIn19", "result": "unavailable", "note": "The source blocks automated access (HTTP 403); no full text retrieved." }, { "id": 88, "theme": "Remedies and interventions", "title": "Position: Collaborative Agentic AI Needs Interoperability Across Ecosystems", "url": "https://arxiv.org/abs/2505.21550", "page": 7, "folder": "12 - Remedies and interventions", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='arxiv.org', port=443): Max retries exceeded with url: /pdf/2505.21550 (Caused by NameResolutionError(\"HTTPSConnection(host='arxiv.org', port=443): Failed to resolve 'arxiv.org' ([Errno -2] Name or service not known)\"))", "source": "_sources/088.pdf", "final_url": "https://arxiv.org/abs/2505.21550", "result": "epub", "pages": 13, "conversion": "PDF text with embedded original pages", "epub": "12 - Remedies and interventions/88 - Position- Collaborative Agentic AI Needs Interoperability Across Ecosystems.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 3294971, "citation": "Position: Collaborative Agentic AI Needs Interoperability Across Ecosystems - Sharma et al., arXiv, 2025", "attribution": "Sharma et al., arXiv, 2025", "combined_figures": 4 }, { "id": 89, "theme": "Remedies and interventions", "title": "AI Neutrality", "url": "https://cdn.vanderbilt.edu/vu-URL/wp-content/uploads/sites/412/2026/01/28222934/AI-Neutrality-.pdf", "page": 7, "folder": "12 - Remedies and interventions", "supplementary": false, "status": "downloaded", "error": "HTTPSConnectionPool(host='cdn.vanderbilt.edu', port=443): Max retries exceeded with url: /vu-URL/wp-content/uploads/sites/412/2026/01/28222934/AI-Neutrality-.pdf (Caused by NameResolutionError(\"HTTPSConnection(host='cdn.vanderbilt.edu', port=443): Failed to resolve 'cdn.vanderbilt.edu' ([Errno -2] Name or service not known)\"))", "source": "_sources/089.pdf", "final_url": "https://cdn.vanderbilt.edu/vu-URL/wp-content/uploads/sites/412/2026/01/28222934/AI-Neutrality-.pdf", "result": "epub", "pages": 24, "conversion": "PDF text with embedded original pages", "epub": "12 - Remedies and interventions/89 - AI Neutrality.epub", "note": "Reflowable text extracted from PDF. Each page links to an embedded original page image for diagrams, equations, and layout. Text extraction may affect reading order or mathematical symbols.", "epub_bytes": 3984741, "citation": "AI Neutrality — Ramzanali and Rajan, Vanderbilt Policy Accelerator, 2026", "attribution": "Ramzanali and Rajan, Vanderbilt Policy Accelerator, 2026", "combined_figures": 6 } ]