{"id":"98ace081e7e78a26f1324f3f8286cb3fdeb6f17d7f4087d39c9bf8d874ee078d","title":"Costello, Pennycook and Rand: Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs","argument":"Thomas H. Costello, Gordon Pennycook and David G. Rand argue in their paper that personalized AI dialogues reduce conspiracy beliefs mainly through relevant, well-reasoned counterevidence—not rapport, storytelling or appeals to empathy. They report two experiments with 2,193 U.S. adults recruited online, testing possible explanations for the effect. The reported reduction remained when the researchers changed how the exchange was framed, shortened the AI’s responses, changed how beliefs were measured, and replaced dialogue with one tailored message. It was substantially reduced only when the AI was instructed to persuade without factual evidence and arguments. The authors’ account makes the proposed mechanism important: the findings point to the substance of the evidence, rather than a conversational style alone, as central to these participants’ changed beliefs. They suggest that people might be similarly effective if they could supply comparable evidence. The abstract reports these experiments with online-recruited U.S. adults; it does not establish whether the same results hold in other populations or settings.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The abstract describes two experiments with U.S. adults recruited online; it does not establish whether the findings generalize to other populations or settings. The supplied evidence is the paper’s abstract, so it does not provide the experiments’ detailed methods or results.","speaker":{"name":"Costello, Thomas H., Pennycook, Gordon, Rand, David G.","roleAtSource":"Article author"},"source":{"title":"Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.05572","publishedAt":"2026-11-03","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors report that two experiments with U.S. adults recruited online found that personalized AI dialogues substantially reduced conspiracy beliefs.","excerpt":"we conducted two experiments with U.S. adults recruited online (total N = 2,193)","url":"https://arxiv.org/abs/2611.05572","relationship":"Source-stated"},{"text":"The authors report that the debunking effect was robust to several changes in framing, response length, belief measurement and format, but was substantially reduced when the AI was instructed to persuade without factual evidence and arguments.","excerpt":"Only instructing the AI to persuade without factual evidence and arguments substantially reduced the debunking effect.","url":"https://arxiv.org/abs/2611.05572","relationship":"Source-stated"},{"text":"The authors attribute larger reductions in conspiracy beliefs primarily to factual argumentation and suggest that humans might be similarly effective if they could provide comparable evidence.","excerpt":"Our results suggest that humans might be similarly effective if they could supply comparable evidence.","url":"https://arxiv.org/abs/2611.05572","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05572","checkedAt":"2026-11-09T08:42:08.375Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Would people be similarly effective at reducing conspiracy beliefs if they could supply evidence comparable to the AI’s?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Costello, Pennycook and Rand: Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs","summary":"Thomas H. Costello, Gordon Pennycook and David G. Rand argue in their paper that personalized AI dialogues reduce conspiracy beliefs mainly through relevant, well-reasoned counterevidence—not rapport, storytelling or appeals to empathy. They report two experiments with 2,193 U.S. adults recruited online, testing possible explanations for the effect. The reported reduction remained when the researchers changed how the exchange was framed, shortened the AI’s responses, changed how beliefs were measured, and replaced dialogue with one tailored message. It was substantially reduced only when the AI was instructed to persuade without factual evidence and arguments. The authors’ account makes the proposed mechanism important: the findings point to the substance of the evidence, rather than a conversational style alone, as central to these participants’ changed beliefs. They suggest that people might be similarly effective if they could supply comparable evidence. The abstract reports these experiments with online-recruited U.S. adults; it does not establish whether the same results hold in other populations or settings.","question":"Would people be similarly effective at reducing conspiracy beliefs if they could supply evidence comparable to the AI’s?","claims":[{"text":"The authors report that two experiments with U.S. adults recruited online found that personalized AI dialogues substantially reduced conspiracy beliefs.","excerpt":"we conducted two experiments with U.S. adults recruited online (total N = 2,193)","support":"source-stated"},{"text":"The authors report that the debunking effect was robust to several changes in framing, response length, belief measurement and format, but was substantially reduced when the AI was instructed to persuade without factual evidence and arguments.","excerpt":"Only instructing the AI to persuade without factual evidence and arguments substantially reduced the debunking effect.","support":"source-stated"},{"text":"The authors attribute larger reductions in conspiracy beliefs primarily to factual argumentation and suggest that humans might be similarly effective if they could provide comparable evidence.","excerpt":"Our results suggest that humans might be similarly effective if they could supply comparable evidence.","support":"source-stated"}],"limitations":["The abstract describes two experiments with U.S. adults recruited online; it does not establish whether the findings generalize to other populations or settings.","The supplied evidence is the paper’s abstract, so it does not provide the experiments’ detailed methods or results."],"mediaId":"618186ac2db4c16c7854a7091816089d7a1d4a34952d9ef00ef30b72feb1c272","correctionReason":null,"id":"98ace081e7e78a26f1324f3f8286cb3fdeb6f17d7f4087d39c9bf8d874ee078d","publicationId":"2fea85f3-388b-40d7-8837-ac1ff97e2e2f","version":1,"sourceUrl":"https://arxiv.org/abs/2611.05572","sourceTitle":"Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-03","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:06:24.938Z","createdAt":"2026-11-09T08:10:02.242Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"618186ac2db4c16c7854a7091816089d7a1d4a34952d9ef00ef30b72feb1c272","kind":"article","url":"https://arxiv.org/abs/2611.05572","sourceUrl":"https://arxiv.org/abs/2611.05572","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T08:09:19.785Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05572","checkedAt":"2026-11-09T08:42:08.375Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"618186ac2db4c16c7854a7091816089d7a1d4a34952d9ef00ef30b72feb1c272","confidence":0.7100000000000001,"provider":"typesafe","model":"jev-1.13.0","inputHash":"8f8853bd23593bc453c7b6d62dee651edd55da1eb1b3bf0e7ac818e0a3b19357","decidedAt":"2026-11-09T08:09:20.316Z"},"provenance":{"textHash":"e0f61655d04249e18d1338824ed32ab802fd9a77406b2fad68d69bebbcfaacb5","observationId":"72c5610af42ae6df951ee1523cb99a4a0fd03934da06938e84d757208b1b3583","retrievedAt":"2026-11-09T08:09:19.704Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"77f691b8-7b14-4a5e-8912-c18bcc9ce9ab"},"reviewer":{"model":"gpt-6-luna","runId":"e23faeaf-5735-46b7-8827-cb7d1855d71e"}},"audit":{"status":"passed","reviewedAt":"2026-11-09T08:10:02.242Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Costello, Thomas H.","url":null,"kind":"unknown"},{"name":"Pennycook, Gordon","url":null,"kind":"unknown"},{"name":"Rand, David G.","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Costello, Thomas H.","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Costello, Thomas H.","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05572","locator":"head/meta[name=author|citation_author]"},"assertionId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T08:42:08.375Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9","sourceUrl":"https://arxiv.org/abs/2611.05572","contentSha256":"2d94b7d53bcd326c8c049c87fbea0c3c14050321ff737b8042803fcc88226097","textHash":"e0f61655d04249e18d1338824ed32ab802fd9a77406b2fad68d69bebbcfaacb5","observedAt":"2026-11-09T08:42:08.375Z"}},{"actor":{"name":"Pennycook, Gordon","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Pennycook, Gordon","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05572","locator":"head/meta[name=author|citation_author]"},"assertionId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T08:42:08.375Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9","sourceUrl":"https://arxiv.org/abs/2611.05572","contentSha256":"2d94b7d53bcd326c8c049c87fbea0c3c14050321ff737b8042803fcc88226097","textHash":"e0f61655d04249e18d1338824ed32ab802fd9a77406b2fad68d69bebbcfaacb5","observedAt":"2026-11-09T08:42:08.375Z"}},{"actor":{"name":"Rand, David G.","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Rand, David G.","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05572","locator":"head/meta[name=author|citation_author]"},"assertionId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T08:42:08.375Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9","sourceUrl":"https://arxiv.org/abs/2611.05572","contentSha256":"2d94b7d53bcd326c8c049c87fbea0c3c14050321ff737b8042803fcc88226097","textHash":"e0f61655d04249e18d1338824ed32ab802fd9a77406b2fad68d69bebbcfaacb5","observedAt":"2026-11-09T08:42:08.375Z"}}],"participationCoverage":{"total":3,"returned":3,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.05572","snapshotId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9","contentSha256":"2d94b7d53bcd326c8c049c87fbea0c3c14050321ff737b8042803fcc88226097","textHash":"e0f61655d04249e18d1338824ed32ab802fd9a77406b2fad68d69bebbcfaacb5","observedAt":"2026-11-09T08:42:08.375Z","basis":"publisher-page-metadata","sourceLinks":39,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/98ace081e7e78a26f1324f3f8286cb3fdeb6f17d7f4087d39c9bf8d874ee078d/source"}},"canonicalUrl":"https://escapemeridian.com/readings/costello-pennycook-and-rand-just-the-facts-how-dialogues-with-98ace081","formats":{"html":"/readings/costello-pennycook-and-rand-just-the-facts-how-dialogues-with-98ace081","markdown":"/readings/costello-pennycook-and-rand-just-the-facts-how-dialogues-with-98ace081.md","json":"/readings/costello-pennycook-and-rand-just-the-facts-how-dialogues-with-98ace081.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[],"entities":[{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"98ace081e7e78a26f1324f3f8286cb3fdeb6f17d7f4087d39c9bf8d874ee078d","revision":"2fea85f3-388b-40d7-8837-ac1ff97e2e2f","revisionKind":"publication-id","title":"Costello, Pennycook and Rand: Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs","url":"https://escapemeridian.com/readings/costello-pennycook-and-rand-just-the-facts-how-dialogues-with-98ace081"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.05572","revision":"e0f61655d04249e18d1338824ed32ab802fd9a77406b2fad68d69bebbcfaacb5","revisionKind":"sha256-source-text","title":"Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs","url":"https://arxiv.org/abs/2611.05572"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"98ace081e7e78a26f1324f3f8286cb3fdeb6f17d7f4087d39c9bf8d874ee078d","title":"Costello, Pennycook and Rand: Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs","argument":"Thomas H. Costello, Gordon Pennycook and David G. Rand argue in their paper that personalized AI dialogues reduce conspiracy beliefs mainly through relevant, well-reasoned counterevidence—not rapport, storytelling or appeals to empathy. They report two experiments with 2,193 U.S. adults recruited online, testing possible explanations for the effect. The reported reduction remained when the researchers changed how the exchange was framed, shortened the AI’s responses, changed how beliefs were measured, and replaced dialogue with one tailored message. It was substantially reduced only when the AI was instructed to persuade without factual evidence and arguments. The authors’ account makes the proposed mechanism important: the findings point to the substance of the evidence, rather than a conversational style alone, as central to these participants’ changed beliefs. They suggest that people might be similarly effective if they could supply comparable evidence. The abstract reports these experiments with online-recruited U.S. adults; it does not establish whether the same results hold in other populations or settings.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The abstract describes two experiments with U.S. adults recruited online; it does not establish whether the findings generalize to other populations or settings. The supplied evidence is the paper’s abstract, so it does not provide the experiments’ detailed methods or results.","speaker":{"name":"Costello, Thomas H., Pennycook, Gordon, Rand, David G.","roleAtSource":"Article author"},"source":{"title":"Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.05572","publishedAt":"2026-11-03","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors report that two experiments with U.S. adults recruited online found that personalized AI dialogues substantially reduced conspiracy beliefs.","excerpt":"we conducted two experiments with U.S. adults recruited online (total N = 2,193)","url":"https://arxiv.org/abs/2611.05572","relationship":"Source-stated"},{"text":"The authors report that the debunking effect was robust to several changes in framing, response length, belief measurement and format, but was substantially reduced when the AI was instructed to persuade without factual evidence and arguments.","excerpt":"Only instructing the AI to persuade without factual evidence and arguments substantially reduced the debunking effect.","url":"https://arxiv.org/abs/2611.05572","relationship":"Source-stated"},{"text":"The authors attribute larger reductions in conspiracy beliefs primarily to factual argumentation and suggest that humans might be similarly effective if they could provide comparable evidence.","excerpt":"Our results suggest that humans might be similarly effective if they could supply comparable evidence.","url":"https://arxiv.org/abs/2611.05572","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05572","checkedAt":"2026-11-09T08:42:08.375Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Would people be similarly effective at reducing conspiracy beliefs if they could supply evidence comparable to the AI’s?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Costello, Pennycook and Rand: Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs","summary":"Thomas H. Costello, Gordon Pennycook and David G. Rand argue in their paper that personalized AI dialogues reduce conspiracy beliefs mainly through relevant, well-reasoned counterevidence—not rapport, storytelling or appeals to empathy. They report two experiments with 2,193 U.S. adults recruited online, testing possible explanations for the effect. The reported reduction remained when the researchers changed how the exchange was framed, shortened the AI’s responses, changed how beliefs were measured, and replaced dialogue with one tailored message. It was substantially reduced only when the AI was instructed to persuade without factual evidence and arguments. The authors’ account makes the proposed mechanism important: the findings point to the substance of the evidence, rather than a conversational style alone, as central to these participants’ changed beliefs. They suggest that people might be similarly effective if they could supply comparable evidence. The abstract reports these experiments with online-recruited U.S. adults; it does not establish whether the same results hold in other populations or settings.","question":"Would people be similarly effective at reducing conspiracy beliefs if they could supply evidence comparable to the AI’s?","claims":[{"text":"The authors report that two experiments with U.S. adults recruited online found that personalized AI dialogues substantially reduced conspiracy beliefs.","excerpt":"we conducted two experiments with U.S. adults recruited online (total N = 2,193)","support":"source-stated"},{"text":"The authors report that the debunking effect was robust to several changes in framing, response length, belief measurement and format, but was substantially reduced when the AI was instructed to persuade without factual evidence and arguments.","excerpt":"Only instructing the AI to persuade without factual evidence and arguments substantially reduced the debunking effect.","support":"source-stated"},{"text":"The authors attribute larger reductions in conspiracy beliefs primarily to factual argumentation and suggest that humans might be similarly effective if they could provide comparable evidence.","excerpt":"Our results suggest that humans might be similarly effective if they could supply comparable evidence.","support":"source-stated"}],"limitations":["The abstract describes two experiments with U.S. adults recruited online; it does not establish whether the findings generalize to other populations or settings.","The supplied evidence is the paper’s abstract, so it does not provide the experiments’ detailed methods or results."],"mediaId":"618186ac2db4c16c7854a7091816089d7a1d4a34952d9ef00ef30b72feb1c272","correctionReason":null,"id":"98ace081e7e78a26f1324f3f8286cb3fdeb6f17d7f4087d39c9bf8d874ee078d","publicationId":"2fea85f3-388b-40d7-8837-ac1ff97e2e2f","version":1,"sourceUrl":"https://arxiv.org/abs/2611.05572","sourceTitle":"Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-03","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:06:24.938Z","createdAt":"2026-11-09T08:10:02.242Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"618186ac2db4c16c7854a7091816089d7a1d4a34952d9ef00ef30b72feb1c272","kind":"article","url":"https://arxiv.org/abs/2611.05572","sourceUrl":"https://arxiv.org/abs/2611.05572","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T08:09:19.785Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05572","checkedAt":"2026-11-09T08:42:08.375Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"618186ac2db4c16c7854a7091816089d7a1d4a34952d9ef00ef30b72feb1c272","confidence":0.7100000000000001,"provider":"typesafe","model":"jev-1.13.0","inputHash":"8f8853bd23593bc453c7b6d62dee651edd55da1eb1b3bf0e7ac818e0a3b19357","decidedAt":"2026-11-09T08:09:20.316Z"},"provenance":{"textHash":"e0f61655d04249e18d1338824ed32ab802fd9a77406b2fad68d69bebbcfaacb5","observationId":"72c5610af42ae6df951ee1523cb99a4a0fd03934da06938e84d757208b1b3583","retrievedAt":"2026-11-09T08:09:19.704Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"77f691b8-7b14-4a5e-8912-c18bcc9ce9ab"},"reviewer":{"model":"gpt-6-luna","runId":"e23faeaf-5735-46b7-8827-cb7d1855d71e"}},"audit":{"status":"passed","reviewedAt":"2026-11-09T08:10:02.242Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Costello, Thomas H.","url":null,"kind":"unknown"},{"name":"Pennycook, Gordon","url":null,"kind":"unknown"},{"name":"Rand, David G.","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Costello, Thomas H.","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Costello, Thomas H.","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05572","locator":"head/meta[name=author|citation_author]"},"assertionId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T08:42:08.375Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9","sourceUrl":"https://arxiv.org/abs/2611.05572","contentSha256":"2d94b7d53bcd326c8c049c87fbea0c3c14050321ff737b8042803fcc88226097","textHash":"e0f61655d04249e18d1338824ed32ab802fd9a77406b2fad68d69bebbcfaacb5","observedAt":"2026-11-09T08:42:08.375Z"}},{"actor":{"name":"Pennycook, Gordon","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Pennycook, Gordon","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05572","locator":"head/meta[name=author|citation_author]"},"assertionId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T08:42:08.375Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9","sourceUrl":"https://arxiv.org/abs/2611.05572","contentSha256":"2d94b7d53bcd326c8c049c87fbea0c3c14050321ff737b8042803fcc88226097","textHash":"e0f61655d04249e18d1338824ed32ab802fd9a77406b2fad68d69bebbcfaacb5","observedAt":"2026-11-09T08:42:08.375Z"}},{"actor":{"name":"Rand, David G.","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Rand, David G.","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05572","locator":"head/meta[name=author|citation_author]"},"assertionId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T08:42:08.375Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9","sourceUrl":"https://arxiv.org/abs/2611.05572","contentSha256":"2d94b7d53bcd326c8c049c87fbea0c3c14050321ff737b8042803fcc88226097","textHash":"e0f61655d04249e18d1338824ed32ab802fd9a77406b2fad68d69bebbcfaacb5","observedAt":"2026-11-09T08:42:08.375Z"}}],"participationCoverage":{"total":3,"returned":3,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.05572","snapshotId":"e1399dc1355789e5c1e95eef25d6fc2d9e2cab453bfdca43b38737b7164b27c9","contentSha256":"2d94b7d53bcd326c8c049c87fbea0c3c14050321ff737b8042803fcc88226097","textHash":"e0f61655d04249e18d1338824ed32ab802fd9a77406b2fad68d69bebbcfaacb5","observedAt":"2026-11-09T08:42:08.375Z","basis":"publisher-page-metadata","sourceLinks":39,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/98ace081e7e78a26f1324f3f8286cb3fdeb6f17d7f4087d39c9bf8d874ee078d/source"}}}],"audits":[{"publicationId":"2fea85f3-388b-40d7-8837-ac1ff97e2e2f","verdict":"passed","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading correctly attributes the paper and its claims to Thomas H. Costello, Gordon Pennycook and David G. Rand. It keeps the mechanism claim and the suggestion about humans framed as the authors' argument rather than established fact.","excerpt":"Authors:Thomas H. Costello, Gordon Pennycook, David G. Rand"},{"dimension":"summary","status":"pass","explanation":"The summary accurately conveys the study design, the robustness tests, the one condition that substantially reduced the effect, and the proposed mechanism. 'Changed how the exchange was framed' compresses the disclosure, debate-framing and inform-not-persuade conditions, but it does not distort them. The language is accessible, and the question follows from the authors' own suggestion. The abstract's hedge ('appear') is softened slightly to 'argue', but attribution is preserved. Minor optional repair: list the disclosure and inform-not-persuade conditions explicitly.","excerpt":"AI dialogues appear to reduce conspiracy beliefs primarily by supplying relevant, well-reasoned counterevidence."},{"dimension":"date","status":"pass","explanation":"The originalPublished value of 2026-11-03 matches the arXiv v1 submission date. The feed date of 2026-11-05 is correctly not used.","excerpt":"[Submitted on 3 Nov 2026]"},{"dimension":"support","status":"pass","explanation":"Each claim is source-stated and supported by the abstract. The limitations correctly note the sample scope and that only the abstract was available. The question restates the authors' own conditional suggestion as an open issue without adding unsupported benefits or costs.","excerpt":"Only instructing the AI to persuade without factual evidence and arguments substantially reduced the debunking effect."},{"dimension":"media","status":"pass","explanation":"The selected media is the verified arXiv abstract page for this paper. It is the direct original source and the most relevant link.","excerpt":null}],"createdAt":"2026-11-09T08:10:02.242Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}