{"as_of":"2026-08-10T20:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ff4ea57815f29c9fa97dec7543ac2dad046f58280d5b37ef67e0599469cce32d","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T04:45:43.198440Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T11:35:39.906365Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T08:16:47.516630Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.17273","snapshot_observed_at":"2026-08-03T11:35:39.906365Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.05751","last_updated":"2026-06-05T07:06:47Z","snapshot_observed_at":"2026-08-04T17:00:12.286204Z","submitted_at":"2026-01-09T12:07:38Z","title":"Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-03T11:35:39.906365Z"},"links":{"cited_paper":"/paper/2501.17273","citing_paper":"/paper/2601.05751"},"observation_digest":"sha256:871be9d494fc0203186d591a8ce3e927f549900e009e6e8b8d896e77ee959528","observation_id":"ea849a78-7c5f-4c14-ba64-57a5ba25e935","resolution":{"observed_at":"2026-08-03T11:35:39.906365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"cited_work":{"arxiv_id":"2501.17273","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.17273","snapshot_observed_at":"2026-07-02T08:16:47.516630Z","title":"Tailored truths: Optimizing llm persuasion with personalization and fabricated statistics.arXiv preprint arXiv:2501.17273","venue":null,"work_id":"3d9d7221-b33f-4a55-a6a5-38569d79a460","year":2025},"citing_paper":{"arxiv_id":"2604.06552","last_updated":"2026-04-08T01:02:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-08T01:02:54Z","title":"To Lie or Not to Lie? Investigating The Biased Spread of Global Lies by LLMs","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-05-10T18:41:54.081628Z"},"links":{"cited_paper":"/paper/2501.17273","citing_paper":"/paper/2604.06552"},"observation_digest":"sha256:80d129b5c86882c92143b482beae5c21200a7ba8be0055ebe25126dd78db618f","observation_id":"32f7f3a6-d48a-4447-9ae0-b6f08d5398de","resolution":{"observed_at":"2026-05-11T00:05:50.875144Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"cited_work":{"arxiv_id":"2501.17273","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.17273","snapshot_observed_at":"2026-07-02T08:16:47.516630Z","title":"Tailored truths: Optimizing llm persuasion with personalization and fabricated statistics.arXiv preprint arXiv:2501.17273","venue":null,"work_id":"3d9d7221-b33f-4a55-a6a5-38569d79a460","year":2025},"citing_paper":{"arxiv_id":"2604.22109","last_updated":"2026-04-27T04:41:35Z","snapshot_observed_at":"2026-07-06T23:08:33.204647Z","submitted_at":"2026-04-23T23:01:38Z","title":"Spontaneous Persuasion: An Audit of Model Persuasiveness in Everyday Conversations","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-09T20:25:35.562690Z"},"links":{"cited_paper":"/paper/2501.17273","citing_paper":"/paper/2604.22109"},"observation_digest":"sha256:9fb122bed28d1a0b1d512261ab037126e032eedd952ff81258dc71b834c1507b","observation_id":"8ceb28bd-1991-4a48-8583-d541c9e04c22","resolution":{"observed_at":"2026-05-11T15:16:07.877820Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"cited_work":{"arxiv_id":"2501.17273","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.17273","snapshot_observed_at":"2026-07-02T08:16:47.516630Z","title":"Tailored truths: Optimizing llm persuasion with personalization and fabricated statistics.arXiv preprint arXiv:2501.17273","venue":null,"work_id":"3d9d7221-b33f-4a55-a6a5-38569d79a460","year":2025},"citing_paper":{"arxiv_id":"2606.05330","last_updated":"2026-06-03T18:17:20Z","snapshot_observed_at":"2026-08-03T19:00:51.745221Z","submitted_at":"2026-06-03T18:17:20Z","title":"A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing","version":1},"reference_index":125,"source":"pdf_text","source_observed_at":"2026-06-28T06:17:01.173495Z"},"links":{"cited_paper":"/paper/2501.17273","citing_paper":"/paper/2606.05330"},"observation_digest":"sha256:710c84eeae7d1ca9dbc4d786e6c1cd6aeb87b15a1deb915d7d6d21ccc215528f","observation_id":"99c10b7d-c1ef-48f9-a905-0596d0f40dea","resolution":{"observed_at":"2026-07-02T08:16:47.518225Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.17273/citation-record","integrity":"/paper/2501.17273/integrity","json":"/paper/2501.17273/citation-record.json","paper":"/paper/2501.17273"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.774135Z","title":"What is israeli firm stoic and how it tried to disrupt lok sabha polls 2024","venue":null,"work_id":"929a8d12-3c69-4fc7-a740-b78f470ad97b","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.022933Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:504b23f738e28efc3b104575fb6fec59e8d11942ca7ba2b7c8cb01e281999a2b","observation_id":"784f8a8c-415f-40a9-8d6b-ee80ab5c326e","resolution":{"observed_at":"2026-08-10T04:45:43.777647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.763845Z","title":"Challenges in Red Teaming AI Systems, June","venue":null,"work_id":"4a71ef68-aa0d-4ef5-981a-c98ab9e0acd1","year":null},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.026856Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:ebd8eaa1ccfe7ba87e94da899ff62d25f38fb18fba8d49df0470a7ff28456781","observation_id":"80ffd939-4a0a-463c-a143-bdffd2a5ad31","resolution":{"observed_at":"2026-08-10T04:45:43.767613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.745065Z","title":"C., Elson, M., and Schneider, I","venue":null,"work_id":"5bf28587-1726-45fe-ac8c-a0cab5bf49cb","year":2023},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.034305Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:a33bcadcb9eab01a0374ddb7f55db6f10fde5d8cc5f75572b4fa4be3566f2888","observation_id":"8413ea01-4705-4131-8e62-1fcb89891377","resolution":{"observed_at":"2026-08-10T04:45:43.748362Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.038033Z","title":"The dark side of language models: Exploring the potential of llms in multimedia disinformation generation and dissemination","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.038033Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:a9014b3880e8726dab524f801ca5da5b689e2336a65afb1116a9a05ab59029aa","observation_id":"3cfe5918-b33f-419e-b145-c238180c115c","resolution":{"observed_at":"2026-08-10T04:45:43.038033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.735878Z","title":null,"venue":null,"work_id":"cebc09fa-b88d-4b8f-9934-8086b06c1df2","year":2020},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.041651Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:7c7f62e9e0aaa5fec26d26b0a14366335d5b9898c25c4ea85a25358f51b2631c","observation_id":"4a890595-aee9-4878-89f2-57eb1bb8a773","resolution":{"observed_at":"2026-08-10T04:45:43.739112Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.15523","last_updated":"2023-12-24T16:21:11Z","snapshot_observed_at":"2026-07-06T17:07:44.254476Z","submitted_at":"2023-12-24T16:21:11Z","title":"The Persuasive Power of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.15523","snapshot_observed_at":"2026-08-10T04:45:43.048757Z","title":"M., Egdal, D","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.048757Z"},"links":{"cited_paper":"/paper/2312.15523","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:faffd55a3b01630f3de85156446d9502b4e5a21e3f98649dc7b46926e7096b65","observation_id":"d49b9959-13c8-49b3-9578-87b1c42ed328","resolution":{"observed_at":"2026-08-10T04:45:43.048757Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.716390Z","title":"Truth, Lies, and Automation How Language Models Could Change Disinformation","venue":null,"work_id":"9d310cd5-9ebf-4e2f-9a97-cc21609b165e","year":2021},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.052852Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:0d7abd22e3c50956637dbc19a2634a34402e578ff07ec39eb8777533cf7a0999","observation_id":"93498b3b-318d-491d-9fe0-960595097dc1","resolution":{"observed_at":"2026-08-10T04:45:43.719997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.706740Z","title":"Debate format: Three rounds of structured debate, 2020","venue":null,"work_id":"702e2e44-7ff8-4767-9d15-b0d136f56a09","year":2020},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.056699Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:8fff534d2aad44bd9165c0cda1a6bdfd198180c3c7bbc0ae36c0ce95b21b5002","observation_id":"ca893402-59d3-4018-8842-a91a19fb33fe","resolution":{"observed_at":"2026-08-10T04:45:43.710243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.697430Z","title":"Non-determinism in gpt-4, 2023","venue":null,"work_id":"f012a925-2fb2-4813-aa29-faf369d0e57c","year":2023},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.059986Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:1d80da484e5b0e9922112333db0c2bde1796631209fd115dbf2a797ee1de481e","observation_id":"1c45580d-692c-4277-8d4d-74b9c580f1eb","resolution":{"observed_at":"2026-08-10T04:45:43.700663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.688099Z","title":"Committee on national security systems (cnss) glos- sary","venue":null,"work_id":"c75ae8c8-8983-4616-a958-94fb763c2dfd","year":2022},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.063684Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:a812d410cbf3dd5d81bfd8828a22377fdcef14d20d9475ce9ed5fdb9d7baa307","observation_id":"c93c9f76-8563-4075-a9cc-e48c3a9a4633","resolution":{"observed_at":"2026-08-10T04:45:43.691562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.678739Z","title":"Durably reducing conspiracy beliefs through dialogues with ai","venue":null,"work_id":"4525d962-fb08-461d-959b-11606e9cb3c6","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.066897Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:e26fceef96b6f4f4d17193f7860f01493d1c0ad40b737e64e153db796ce7171f","observation_id":"18189b4c-015c-4446-8cbb-45d1ecbc3cc1","resolution":{"observed_at":"2026-08-10T04:45:43.682280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.669219Z","title":"A Guide to Min- imum Wage in India, September 2024","venue":null,"work_id":"7b83ff66-ad80-403b-b732-77dca91d1789","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.070124Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:bcf3968e3ec3c77b12128e4c71c35f463315b4eba2db5bfc924ecf69259c212d","observation_id":"2f445417-41b1-4429-837e-eebf836bac1b","resolution":{"observed_at":"2026-08-10T04:45:43.672549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-10T16:40:37.411115Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-10T04:45:43.073586Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.073586Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:539b3f3701cd339a2744482c8372623ed32acb0fa22bcd7776c5f75751d7af81","observation_id":"f1987654-7516-463d-990e-29c73d31adbf","resolution":{"observed_at":"2026-08-10T04:45:43.073586Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.660176Z","title":"Measuring the persuasiveness of language models","venue":null,"work_id":"a7651ff1-2969-4395-b361-d9c879e12778","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.077585Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:25a1db54162f29886ec56e0826d4e8bf6e185b02002e184cc51fa120f8d0023c","observation_id":"e8f9ef3e-a4af-4693-935c-b3ba2f16d06c","resolution":{"observed_at":"2026-08-10T04:45:43.663445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.650111Z","title":"A day in the life of a Shwe Kokko scammer, June","venue":null,"work_id":"e9fbba87-90a2-4171-8fdd-992eea66bf73","year":null},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.080720Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:0fef11ca814435efa75c06e81b4800fadf29621122394d3a4ac9dcb5df299b0c","observation_id":"c76a5cc4-e690-4221-b86c-87c032d45396","resolution":{"observed_at":"2026-08-10T04:45:43.654248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.03566","last_updated":"2024-09-26T17:36:22Z","snapshot_observed_at":"2026-08-06T02:02:57.797902Z","submitted_at":"2024-09-26T17:36:22Z","title":"A Survey on Offensive AI Within Cybersecurity","version":1},"cited_work":{"arxiv_id":"2410.03566","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.03566","snapshot_observed_at":"2026-08-10T04:45:43.368282Z","title":"A Survey on Offensive AI Within Cybersecurity","venue":"cs.CR","work_id":"49f913ac-7277-4d57-893f-247be120e664","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.087590Z"},"links":{"cited_paper":"/paper/2410.03566","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:0ae1fe5ec95e3d2a92e417c187b235fb49dcab8f2a212db042ef7e90980c1b4a","observation_id":"ea8ca0e6-7b35-4ecf-8379-34bc471baa63","resolution":{"observed_at":"2026-08-10T04:45:43.372259Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.630154Z","title":"Predicting personality with social media","venue":null,"work_id":"d9671bcd-703d-4c4f-8cc5-7cc566ee9133","year":2011},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.091748Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:0b535a51ecd9d435869136fac5ac59aa912e55ec74aaedcfb382b1c1e541642f","observation_id":"eccf3b9b-abce-4a39-be34-dfa5a410dc8b","resolution":{"observed_at":"2026-08-10T04:45:43.633457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.04246","last_updated":"2023-01-10T23:42:30Z","snapshot_observed_at":"2026-08-10T16:10:21.882538Z","submitted_at":"2023-01-10T23:42:30Z","title":"Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.04246","snapshot_observed_at":"2026-08-10T04:45:43.094856Z","title":"A., Sastry, G., Musser, M., DiResta, R., Gentzel, M., and Sedova, K","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.094856Z"},"links":{"cited_paper":"/paper/2301.04246","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:93cc0e2aecea9a0308d6d327c271ff0b38efd3ca3c3af22839913e03fe4d7829","observation_id":"bc2226c4-fe33-46e4-a538-e92e3fe94a47","resolution":{"observed_at":"2026-08-10T04:45:43.094856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.098462Z","title":"D., Rentfrow, P","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.098462Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:17e08359dd962333803ce87919feb5b7053972b4bc4a5cf73f28635934147ce2","observation_id":"a68a0532-71d6-4b2a-a69a-9807340349bb","resolution":{"observed_at":"2026-08-10T04:45:43.098462Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.620322Z","title":"Why report estimated marginal means?, aug 2021","venue":null,"work_id":"e710709d-efbb-4aca-8a6b-a24c923c4c4c","year":2021},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.101779Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:0a539a95c17ad45b120cb91eb90a7f51a98375577532e64cbde017a41b7525f3","observation_id":"b2d607b5-8c1e-4b47-b67e-18289fc2e00d","resolution":{"observed_at":"2026-08-10T04:45:43.623855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.611175Z","title":"and Margetts, H","venue":null,"work_id":"e0c66b97-a674-451f-a05e-e6ed10696927","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.105424Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:266e89ba79854f311882704a125357c08bfae6c99ddb4b75ee5d984dd1e7f3fe","observation_id":"a9060b28-1d27-49db-81c0-85387ceb5550","resolution":{"observed_at":"2026-08-10T04:45:43.614399Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.601662Z","title":"A russian bot farm used ai to lie to americans","venue":null,"work_id":"1388ee4a-8337-4384-b7c7-1645ccc635b4","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.108708Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:b72b8a07838e7a2e63a1efa82f83b1f681b3bca92da715c04e207438fb7f5733","observation_id":"07a23861-e465-40e9-8ab2-b0d3f214f91a","resolution":{"observed_at":"2026-08-10T04:45:43.605265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.592144Z","title":"Bots and misinformation spread on social media: Implications for covid-19","venue":null,"work_id":"c469ffa6-5c10-42d7-85ab-17a870b0db3e","year":2021},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.112049Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:f5490a2f18f6f8a1d2f560eefdc1193b3b0b2d281f18ab8c80a868b61c75367b","observation_id":"500c7bf3-73b0-45d8-b4e4-41ccb590b906","resolution":{"observed_at":"2026-08-10T04:45:43.595496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.583144Z","title":"Of 2 minds: How fast and slow thinking shape perception and choice [excerpt]","venue":null,"work_id":"58cd81fd-9c7d-44a9-bb44-e3cf33a5ffba","year":2012},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.115166Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:724ebab533b7f9ae33f9beed46062bdf29907362cfe1188abdc20ef07c6d85e5","observation_id":"a4427ca8-58af-4234-a287-2293d4b1c9bd","resolution":{"observed_at":"2026-08-10T04:45:43.586458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.573707Z","title":"Private traits and attributes are predictable from digital records of human behavior","venue":null,"work_id":"e258eac2-87e6-4194-bf17-0782e222fcc7","year":2013},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.118531Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:cefb6815d16cb38af7cb93e3c970852d9f494b5cd88506eccc0bb08295cfcd23","observation_id":"48aaf1e3-ff7f-4227-9194-db75142171e5","resolution":{"observed_at":"2026-08-10T04:45:43.577257Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17382","last_updated":"2024-11-07T08:34:27Z","snapshot_observed_at":"2026-07-06T18:20:44.070255Z","submitted_at":"2024-05-27T17:38:33Z","title":"ReMoDetect: Reward Models Recognize Aligned LLM's Generations","version":2},"cited_work":{"arxiv_id":"2405.17382","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.17382","snapshot_observed_at":"2026-08-10T04:45:43.344273Z","title":"ReMoDetect: Reward Models Recognize Aligned LLM's Generations","venue":"cs.LG","work_id":"f390cd1d-27cc-42c4-a8dd-641d9f1ed225","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.121623Z"},"links":{"cited_paper":"/paper/2405.17382","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:13b21d70ada1070169289b4e4b2145d47838b12ae1be72df68f35677c1178da1","observation_id":"a17dfcfd-9dbf-4a8d-b0ef-f1f196f9c2ac","resolution":{"observed_at":"2026-08-10T04:45:43.348739Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.564453Z","title":"and Warren, P","venue":null,"work_id":"a046e588-61a5-4d04-a51e-144ec1466f1a","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.125118Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:1d9dfee373087803964fc0ac59850b65443be064c0394cab271591e801b73d1f","observation_id":"3bd833d6-adc1-46f8-afed-c59510984976","resolution":{"observed_at":"2026-08-10T04:45:43.567821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03172","last_updated":"2023-11-20T23:09:34Z","snapshot_observed_at":"2026-07-06T15:51:12.179086Z","submitted_at":"2023-07-06T17:54:11Z","title":"Lost in the Middle: How Language Models Use Long Contexts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03172","snapshot_observed_at":"2026-08-10T04:45:43.128218Z","title":"F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., and Liang, P","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.128218Z"},"links":{"cited_paper":"/paper/2307.03172","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:9afcf1ad2449871f3f9c7b8dc460bc242a771c5fde7e98a2786e300fbd07dc1e","observation_id":"6d18eda5-8f48-4c9c-8c53-c3bb3c3fc671","resolution":{"observed_at":"2026-08-10T04:45:43.128218Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.555121Z","title":"ConspEmoLLM: Conspiracy Theory Detection Using an Emotion-Based Large Language Model","venue":null,"work_id":"8db01df7-91fa-4184-904d-f28afc462670","year":null},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.131686Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:de4e64401a771d9e03e02476f905050c4365cfaeac998f133dd1f6f4718fb11b","observation_id":"8a23357a-7f8f-4356-b7b0-034b2f8bd2e8","resolution":{"observed_at":"2026-08-10T04:45:43.558621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1301.6870","last_updated":"2013-01-29T09:29:54Z","snapshot_observed_at":"2026-07-06T03:05:08.361224Z","submitted_at":"2013-01-29T09:29:54Z","title":"Studying User Footprints in Different Online Social Networks","version":1},"cited_work":{"arxiv_id":"1301.6870","doi":null,"metadata_source":"pith","pith_arxiv_id":"1301.6870","snapshot_observed_at":"2026-08-10T04:45:43.320098Z","title":"Studying User Footprints in Different Online Social Networks","venue":"cs.SI","work_id":"69814139-2ac2-4a23-ac3c-2e5aab5cc3e3","year":2013},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.138521Z"},"links":{"cited_paper":"/paper/1301.6870","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:e317e41096336c9be378ce9343c15395462a896d4caad17c79f6bda8094672c4","observation_id":"d8b9a0be-56f9-4ec3-8131-0b0bf25445f6","resolution":{"observed_at":"2026-08-10T04:45:43.324115Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.142052Z","title":"C., Teeny, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.142052Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:b505f63b88a2630ed2efbb732b2bf3c2d32e039e00c97efc4fa65484c662d1a8","observation_id":"cad2ba4a-1ed7-4475-9ea5-ae07397b2655","resolution":{"observed_at":"2026-08-10T04:45:43.142052Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.06008","last_updated":"2024-11-12T14:30:28Z","snapshot_observed_at":"2026-08-07T04:06:26.044745Z","submitted_at":"2024-11-08T23:02:59Z","title":"The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.06008","snapshot_observed_at":"2026-08-10T04:45:43.145525Z","title":"The dark patterns of personalized persuasion in large language models: Exposing persuasive linguistic features for big five personality traits in llms responses, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.145525Z"},"links":{"cited_paper":"/paper/2411.06008","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:da2997425c78d66442fc201bde844b8f34512cabfdf61a100df463f59d86322e","observation_id":"80a79ba7-0644-4c03-bfe6-adbc6be684bb","resolution":{"observed_at":"2026-08-10T04:45:43.145525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.3233/faia241060","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":"doi: 10.3233/faia241060","venue":"Frontiers in artificial intelligence and applications","work_id":"e9ede0dd-4f59-4d7d-a050-a26707219e07","year":null},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.135138Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:9045abd4d8d7d1c982ca2893963590aeed4e558e7daea2872680dcd03184dcb2","observation_id":"10bded5a-4c40-40f9-9679-034f26702924","resolution":{"observed_at":"2026-08-10T04:45:43.255348Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.545073Z","title":"Reality Check Commentary: Krem- lin’s World-Class Dashboard Maximizes Disinfor- mation, at 26 Cents Per Lie, February 2024","venue":null,"work_id":"dea78062-4243-4dc8-adaa-855853bf0bf1","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.152122Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:74324fd1ea627e5ac497773d3d82f7ae249309ca73bc02228bf9b3676e0331c3","observation_id":"b9a8c3ee-8164-41fd-904f-0d40bc46362b","resolution":{"observed_at":"2026-08-10T04:45:43.548656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.00114","last_updated":"2021-11-30T21:32:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-11-30T21:32:46Z","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.00114","snapshot_observed_at":"2026-08-10T04:45:43.155310Z","title":"J., Gur-Ari, G., Michalewski, H., Austin, J., Bieber, D., Dohan, D., Lewkowycz, A., Bosma, M., Luan, D., Sutton, C., and Odena, A","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.155310Z"},"links":{"cited_paper":"/paper/2112.00114","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:ee65a8916f1606d7dbe01abd29b905778b776dbd16b8117736e6ab90fc7cab80","observation_id":"e6137d09-19cd-4905-8a49-f2b5bfe86ea7","resolution":{"observed_at":"2026-08-10T04:45:43.155310Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.535327Z","title":"OpenAI Red Teaming Network, September 2023","venue":null,"work_id":"2a6f8e67-c423-443b-abd2-a524d43c53f4","year":2023},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.158651Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:676f8011f54decefa21ea67de12677555054dd9b50e0f04d71c01ff15cba654f","observation_id":"956c4c8f-7e0d-4800-8758-d5c556735298","resolution":{"observed_at":"2026-08-10T04:45:43.538715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.148892Z","title":"M., De Francisci Morales, G., and Bonchi, F","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.148892Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:ee7aedf1be995ccd35b8b3b1b43106f3d26b9272e9eb4d6f1d61fc67da6f6c5e","observation_id":"503dd392-ac22-4451-afa6-b130e4015f61","resolution":{"observed_at":"2026-08-10T04:45:43.148892Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.516089Z","title":"Disrupting deceptive uses of ai by covert influence operations, May 2024","venue":null,"work_id":"dde84e5e-4f88-4aeb-aa09-5c40f864c96a","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.164943Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:1d15a0687b096adea43cd5d072aaf948538c40511d34ff6b41537773ab03cc5a","observation_id":"0a45a723-3fa7-47a9-9266-9a6a71e2f253","resolution":{"observed_at":"2026-08-10T04:45:43.519552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.506436Z","title":null,"venue":null,"work_id":"cb11f9ed-ceb5-4d49-90bf-72d2f3a50d8d","year":2017},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.168080Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:45164019f8de8461d16bb5d89a2ed56a7f5cd97f65aef138b747595fdacf806b","observation_id":"6d91b929-446b-4f3b-bf06-5537e5776061","resolution":{"observed_at":"2026-08-10T04:45:43.509922Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.496278Z","title":null,"venue":null,"work_id":"f524bddd-a5e4-4e4c-868a-d7f7c0b5367d","year":2015},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.171571Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:33acf3723de9b0794626ba61d5349856736bb8162a1519ee0a1271a13fa0d6ae","observation_id":"92bca78e-d3f5-49f3-b6be-a8fd3a5c7f65","resolution":{"observed_at":"2026-08-10T04:45:43.499912Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.525799Z","title":"Api pricing for openai models, 2024","venue":null,"work_id":"e9dea8e5-9f98-4c04-ab82-9b7c793d1086","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.161768Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:76bf39f510285405cb86851a003b3190fcd82a0c9ea1c2b006a474e146bff78e","observation_id":"4b93edae-62aa-4b22-8330-c471d76b3251","resolution":{"observed_at":"2026-08-10T04:45:43.529116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14380","last_updated":"2024-03-21T13:14:40Z","snapshot_observed_at":"2026-07-06T17:48:19.344410Z","submitted_at":"2024-03-21T13:14:40Z","title":"On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14380","snapshot_observed_at":"2026-08-10T04:45:43.178229Z","title":"H., Gallotti, R., and West, R","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.178229Z"},"links":{"cited_paper":"/paper/2403.14380","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:e1d5bf87ed1aa1d0ebf4d3262072474a9e39d0bb41cf398a12c6da8f0f952466","observation_id":"a70ed6c3-1c81-466c-bbae-c4488dfb5d3f","resolution":{"observed_at":"2026-08-10T04:45:43.178229Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1073/pnas.2216261120","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":"Quantifying the potential persuasive returns to political microtargeting","venue":"Proceedings of the National Academy of Sciences","work_id":"fd839ebb-0024-4cf4-96a5-8d406f5adb03","year":2023},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.181742Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:6d4b839fbbcc27e5f052cb1e76ae82d41b254d5fb694cc9d306e682b9f47d488","observation_id":"12f7c558-b3a3-43f3-bd52-059c2c6767b2","resolution":{"observed_at":"2026-08-10T04:45:43.231699Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.476796Z","title":"Government Accountability Office","venue":null,"work_id":"0885baed-b746-484a-90a6-fbdbe6cdf74d","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.185056Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:db2ad22c3a41a30d2e8bb94769b03003cedf8fc09f7274cec380e3153d2e6a89","observation_id":"393d88e2-133c-4ca1-97d5-140fc1bcbffb","resolution":{"observed_at":"2026-08-10T04:45:43.480201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.486668Z","title":null,"venue":null,"work_id":"aee34a26-0964-4f46-8650-acb562bc0083","year":2007},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.174732Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:cb61053d222282f818dcfda72bb49949b5441a192dff863ee0a1a2568737582b","observation_id":"b8301849-03ce-4001-b4f0-bb6fbbc6cf15","resolution":{"observed_at":"2026-08-10T04:45:43.490069Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13160","last_updated":"2023-10-10T17:34:15Z","snapshot_observed_at":"2026-07-06T15:30:45.921201Z","submitted_at":"2023-05-22T15:47:31Z","title":"Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13160","snapshot_observed_at":"2026-08-10T04:45:43.191396Z","title":"Can chatgpt defend its belief in truth? evaluating llm reasoning via debate, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.191396Z"},"links":{"cited_paper":"/paper/2305.13160","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:ec7d512ed06009025d13726b5aa562c4844e9dee2637a2a43cfaf2d60250bb55","observation_id":"faaaa970-02ec-44d4-be60-9ddfed7302c0","resolution":{"observed_at":"2026-08-10T04:45:43.191396Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04692","last_updated":"2024-06-07T07:04:10Z","snapshot_observed_at":"2026-08-10T13:08:49.587751Z","submitted_at":"2024-06-07T07:04:10Z","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04692","snapshot_observed_at":"2026-08-10T04:45:43.194750Z","title":"Mixture-of-agents enhances large language model capabilities, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.194750Z"},"links":{"cited_paper":"/paper/2406.04692","citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:28e1d8bf4483514e52d705a2dc12dafa19a614be2ea43a613b7bd2f58bb10e0a","observation_id":"5a1df823-8c51-4bb7-8de4-1904e9e6c2d4","resolution":{"observed_at":"2026-08-10T04:45:43.194750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.456210Z","title":"workers at Russian troll farms earn 660 USD equivalent per month for writing 100 comments per day on social media","venue":null,"work_id":"c855c570-614e-46ca-b752-8e7eb19390d6","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.198440Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:e4ab25ee2cbe353da5f60c29e26f6db8cdcaea4ca74fbcac49773dce4aa4512c","observation_id":"317fe21b-d3ae-44fe-a6ce-2dbe9488351a","resolution":{"observed_at":"2026-08-10T04:45:43.459888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.466450Z","title":"Who does(n’t) target you? mapping the worldwide usage of online political microtar- geting","venue":null,"work_id":"882d74fc-7825-4b94-b55c-dce8003f61ef","year":2024},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.188140Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:8f603ccd39b93961c23efef584c4664af67429f4e840d75d7baefcf61f7b7873","observation_id":"c9e5c442-2555-4510-9daf-7e7346286b38","resolution":{"observed_at":"2026-08-10T04:45:43.470006Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.725962Z","title":"This work is licensed under a Creative Commons Attribution - Non Commercial - Share Alike 4.0 International License","venue":null,"work_id":"468b9fca-6633-4c26-a8b7-596a7b50bded","year":null},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.045128Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:e22ae5517881eb2003a321bddbe8485cefaa6be73da72966297da1c574fb9019","observation_id":"e6e56cd5-04fb-44c5-b621-7a97944a49c5","resolution":{"observed_at":"2026-08-10T04:45:43.729937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.639724Z","title":null,"venue":null,"work_id":"b48fa40f-049f-4e9f-ac02-53216e9d8e2e","year":null},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.083974Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:d7f305c6669f3891b0a065ff1ad527f64c2e9c5d30a18b181e52476a79ed4290","observation_id":"7105e199-34c3-4f5c-82c6-b046a16c2c31","resolution":{"observed_at":"2026-08-10T04:45:43.643966Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:45:43.754350Z","title":null,"venue":null,"work_id":"07f43a68-4946-47ef-8d81-ca6de2f41058","year":null},"citing_paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-10T04:45:43.030356Z"},"links":{"citing_paper":"/paper/2501.17273"},"observation_digest":"sha256:6054e25920fddcb9775b029e3a601009fc0e39f1bd1e6d45608f76bc19dd8e7d","observation_id":"564d86df-e706-4db3-bcb9-40c3a7c65cd7","resolution":{"observed_at":"2026-08-10T04:45:43.757737Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.17273","last_updated":"2025-01-28T20:06:09Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-10T16:10:45.324066Z","submitted_at":"2025-01-28T20:06:09Z","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":3,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":5,"verified_fuzzy":26},"total_outbound_references":52},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 4 inbound Pith citation observations for arXiv:2501.17273."}