{"as_of":"2026-08-10T16:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2bc409e6840fd722ee9351a72148fda06e06f50e29aecfe29e0359b1a8e4a008","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":27,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:22:55.726899Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":8,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2406.10162","last_updated":"2024-06-29T00:28:47Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-14T16:26:20Z","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","version":3},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-05-17T14:43:29.496457Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2406.10162"},"observation_digest":"sha256:3bf2606987fb70e09fb33ec80381a8cedc9f6fc4a6a463e12d271a3eb80f9e92","observation_id":"258c51e0-0cde-410c-856d-fbd2bea53538","resolution":{"observed_at":"2026-05-17T14:43:30.125082Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-07T14:22:55.726899Z","title":"Scheurer, M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.19212","last_updated":"2026-07-24T14:18:32Z","snapshot_observed_at":"2026-08-10T00:32:01.048016Z","submitted_at":"2025-05-25T16:19:24Z","title":"When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T14:22:55.726899Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2505.19212"},"observation_digest":"sha256:8f9559b07808878a1da3ccebae3c3cc3d6240b3c4fc1176c799277e9775c06b9","observation_id":"c7e9aa0c-8330-4303-b9b0-0b707b82d616","resolution":{"observed_at":"2026-08-07T14:22:55.726899Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-06T20:57:42.045271Z","title":"Large language models can strategically deceive their users when put under pressure, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01413","last_updated":"2025-07-02T07:06:49Z","snapshot_observed_at":"2026-08-09T16:11:02.776047Z","submitted_at":"2025-07-02T07:06:49Z","title":"Evaluating LLM Agent Collusion in Double Auctions","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-06T20:57:42.045271Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2507.01413"},"observation_digest":"sha256:a700979e2165a2fb5513f9108e5e7fc6b7534b14139aff43767090e90c60932a","observation_id":"153780e5-c91b-40b6-b0eb-ced2a4c85ef3","resolution":{"observed_at":"2026-08-06T20:57:42.045271Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-06T20:18:15.488840Z","title":"Scheurer, M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.03409","last_updated":"2025-07-04T09:16:11Z","snapshot_observed_at":"2026-08-08T10:46:44.107781Z","submitted_at":"2025-07-04T09:16:11Z","title":"Lessons from a Chimp: AI \"Scheming\" and the Quest for Ape Language","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T20:18:15.488840Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2507.03409"},"observation_digest":"sha256:2ce5a690841e9cd405cf9f990ee06efba6fb1cc190dc43a2e0834f534a61b4f2","observation_id":"e5f00efd-22de-45db-ba5d-f6f9a788f17e","resolution":{"observed_at":"2026-08-06T20:18:15.488840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-06T17:11:24.169940Z","title":"Last retrieved from https://arxiv.org/abs/2311.07590 on May 30,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.11597","last_updated":"2025-07-15T17:59:06Z","snapshot_observed_at":"2026-08-10T05:59:25.447021Z","submitted_at":"2025-07-15T17:59:06Z","title":"AI, Humans, and Data Science: Optimizing Roles Across Workflows and the Workforce","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T17:11:24.169940Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2507.11597"},"observation_digest":"sha256:6e16bb200130a249c38602f8ebabba6c1d2bf53e3abb1b32004fa88d74362aae","observation_id":"c4c3e8fe-ec3d-453a-92ae-ebb4f5b34a26","resolution":{"observed_at":"2026-08-06T17:11:24.169940Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-06T16:39:37.499516Z","title":"arXiv:2311.07590","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.12872","last_updated":"2025-07-17T07:45:53Z","snapshot_observed_at":"2026-08-10T05:33:39.298538Z","submitted_at":"2025-07-17T07:45:53Z","title":"Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T16:39:37.499516Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2507.12872"},"observation_digest":"sha256:4be83d283a14feac40ea8e2e39071a8c5e7cae63f85e72b70bd0b141b2c44986","observation_id":"cbe3c3ce-fde7-47b6-9ef2-b51c5f46b7d1","resolution":{"observed_at":"2026-08-06T16:39:37.499516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T15:52:45.025680Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.19432","last_updated":"2025-08-26T21:01:45Z","snapshot_observed_at":"2026-08-09T00:35:46.151432Z","submitted_at":"2025-08-26T21:01:45Z","title":"Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-05T15:52:45.025680Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2508.19432"},"observation_digest":"sha256:77f3d6d5c2a8c7efc34589adffc65673746e24ac51b3f07b8e3bd4d2269d3376","observation_id":"e28914da-2d68-4a56-becc-d012126e74f7","resolution":{"observed_at":"2026-08-05T15:52:45.025680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T10:55:31.286599Z","title":"Scheurer, M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03518","last_updated":"2025-09-03T17:59:45Z","snapshot_observed_at":"2026-08-08T06:59:31.324367Z","submitted_at":"2025-09-03T17:59:45Z","title":"Can LLMs Lie? Investigation beyond Hallucination","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T10:55:31.286599Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2509.03518"},"observation_digest":"sha256:09a0c9cedf0740fd8fafc5d8dc3c9441e4302cb50cdabad5f8167e98eeac8f0b","observation_id":"dd7965ac-4315-4b08-84be-145157e74a6a","resolution":{"observed_at":"2026-08-05T10:55:31.286599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2509.06701","last_updated":"2026-05-12T03:07:08Z","snapshot_observed_at":"2026-07-06T22:25:53.156731Z","submitted_at":"2025-09-08T13:55:01Z","title":"Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-18T18:25:25.751119Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2509.06701"},"observation_digest":"sha256:77916047e671db683503280c8e3a966fa3c2550ce30cc9ce52bfb414b2c1e240","observation_id":"ce7e60ef-3588-4e16-81d4-b2ab0d3efca8","resolution":{"observed_at":"2026-05-18T18:26:43.661233Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2511.17408","last_updated":"2026-04-19T21:58:15Z","snapshot_observed_at":"2026-08-06T11:23:25.216358Z","submitted_at":"2025-11-21T17:08:48Z","title":"The Impact of Off-Policy Training Data on Probe Generalisation","version":4},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-05-17T20:26:37.914522Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2511.17408"},"observation_digest":"sha256:8821d16f35de38c5b038b9337023120856db206a519e6457229d7669b9acb1a8","observation_id":"7ae73266-38ec-4e72-9fd0-ace740a1501b","resolution":{"observed_at":"2026-05-17T20:30:11.706210Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-03T10:15:19.202543Z","title":"12 Annika M","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.10896","last_updated":"2026-06-04T19:23:12Z","snapshot_observed_at":"2026-08-06T23:37:32.882301Z","submitted_at":"2026-01-15T22:50:46Z","title":"DialDefer: A Framework for Detecting and Mitigating LLM Dialogic Deference","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-03T10:15:19.202543Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2601.10896"},"observation_digest":"sha256:f2c03a71bd22855c3b2e8be4e9f54a3f60a322440fa5353b0e28decb989c3d64","observation_id":"28c302aa-d4c1-448d-96b4-4910c111bfb7","resolution":{"observed_at":"2026-08-03T10:15:19.202543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2604.01151","last_updated":"2026-05-09T19:42:28Z","snapshot_observed_at":"2026-07-06T22:51:31.209896Z","submitted_at":"2026-04-01T17:08:05Z","title":"Detecting Multi-Agent Collusion Through Multi-Agent Interpretability","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-13T22:46:39.337887Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2604.01151"},"observation_digest":"sha256:5574e31dd1348897508f37ba7902b590693995c3e9772945ad9390bdda1cb442","observation_id":"da29a004-c0db-4bbc-8fe5-4ad871a8cb80","resolution":{"observed_at":"2026-05-13T22:48:22.923160Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2604.03121","last_updated":"2026-04-03T15:45:35Z","snapshot_observed_at":"2026-07-06T22:52:20.577677Z","submitted_at":"2026-04-03T15:45:35Z","title":"An Independent Safety Evaluation of Kimi K2.5","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-13T19:38:18.674355Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2604.03121"},"observation_digest":"sha256:0993e2589582a23f80e4e1da35ec9929d74c1578973fd62422dff7f998fed440","observation_id":"9504b5f2-4019-46e3-aa0e-6cff7f628a8f","resolution":{"observed_at":"2026-05-13T19:43:11.545844Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2604.04157","last_updated":"2026-04-05T15:54:43Z","snapshot_observed_at":"2026-08-02T05:47:41.026585Z","submitted_at":"2026-04-05T15:54:43Z","title":"Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-13T16:53:57.769734Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2604.04157"},"observation_digest":"sha256:762dd28274082f099fe17b65c83051d95d7eeb407418facb805565e26e95d5bc","observation_id":"42ed6504-6f5a-41d3-8012-cad0cc0bd15c","resolution":{"observed_at":"2026-05-13T17:08:01.905040Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2604.04561","last_updated":"2026-04-06T09:44:34Z","snapshot_observed_at":"2026-07-06T22:53:29.118925Z","submitted_at":"2026-04-06T09:44:34Z","title":"Mapping the Exploitation Surface: A 10,000-Trial Taxonomy of What Makes LLM Agents Exploit Vulnerabilities","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T20:17:28.084494Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2604.04561"},"observation_digest":"sha256:9824894f8f91be3bbca30527aa082e6d3d042fa6644e86606c762d1637eb060e","observation_id":"6db92c01-edd2-48e4-8ae6-29d96df40e56","resolution":{"observed_at":"2026-05-10T22:05:47.801352Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2604.09104","last_updated":"2026-04-10T08:37:18Z","snapshot_observed_at":"2026-08-09T07:14:44.837796Z","submitted_at":"2026-04-10T08:37:18Z","title":"Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T17:14:11.957795Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2604.09104"},"observation_digest":"sha256:8cb1a09a83d48417d31163e6e9f43c92a0385382199c0d2195aed11989cd2b0f","observation_id":"98b70601-dad7-4443-90a5-3be5b660bf8d","resolution":{"observed_at":"2026-05-11T07:16:09.645858Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2604.24966","last_updated":"2026-04-27T20:07:09Z","snapshot_observed_at":"2026-07-06T23:10:52.763251Z","submitted_at":"2026-04-27T20:07:09Z","title":"Risk Reporting for Developers' Internal AI Model Use","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-07T17:47:21.321820Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2604.24966"},"observation_digest":"sha256:0f53312b2c400fbe19759aca675c079b75502e8f416121be9731e2fe01d07abd","observation_id":"d6da676d-4dd3-415f-8dea-1e9ba3957274","resolution":{"observed_at":"2026-05-11T23:16:16.631606Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2605.06327","last_updated":"2026-05-07T14:23:31Z","snapshot_observed_at":"2026-07-06T23:18:51.157048Z","submitted_at":"2026-05-07T14:23:31Z","title":"Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-05-08T10:23:02.697982Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2605.06327"},"observation_digest":"sha256:c6db4fa7ac88fec8805dcffd0873a5195c34b83a7b1609548bde240b2f5de8a9","observation_id":"a9a36954-ebe9-4876-8f07-0a031d411a9c","resolution":{"observed_at":"2026-05-08T22:04:17.852934Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2605.06490","last_updated":"2026-05-07T16:12:36Z","snapshot_observed_at":"2026-08-06T16:49:31.340266Z","submitted_at":"2026-05-07T16:12:36Z","title":"Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-08T09:44:44.131088Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2605.06490"},"observation_digest":"sha256:dc4323cffe9f149c3ba40bcd7a909ec41be11de3dc441f33858620fb7f1f7745","observation_id":"3905201c-caa6-4fed-ad53-eba735590580","resolution":{"observed_at":"2026-05-11T20:16:10.885117Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2605.09391","last_updated":"2026-05-15T12:37:57Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T07:38:34Z","title":"Do Linear Probes Generalize Better in Persona Coordinates?","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-05-12T04:47:47.214726Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2605.09391"},"observation_digest":"sha256:401671d1e6ba5b28f463f329e5ffd54decec1ea7a5af8baffbb7fee2b4847c66","observation_id":"2c946e05-992e-465e-b2a5-7258d81a3a64","resolution":{"observed_at":"2026-05-12T04:51:23.059966Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2605.09391","last_updated":"2026-05-15T12:37:57Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T07:38:34Z","title":"Do Linear Probes Generalize Better in Persona Coordinates?","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-05-19T17:06:22.481341Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2605.09391"},"observation_digest":"sha256:08650a850ad8a1ac044149fdc5c7eadd8b4b5de4db7a1c1ffd0ce540741a55f7","observation_id":"9b5841b1-1c38-4ba5-b0b5-052682188b90","resolution":{"observed_at":"2026-05-19T17:07:40.543789Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2605.11448","last_updated":"2026-05-12T02:59:44Z","snapshot_observed_at":"2026-07-06T23:23:16.461539Z","submitted_at":"2026-05-12T02:59:44Z","title":"Deep Minds and Shallow Probes","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-13T02:19:42.346071Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2605.11448"},"observation_digest":"sha256:c13bf1c0d49f524e7e62dd6935a481496555a4a4e72900ddc9c8b664f2da0267","observation_id":"706f1617-1c0b-47db-af6d-e769d5f17089","resolution":{"observed_at":"2026-05-13T02:22:06.405151Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2605.13329","last_updated":"2026-05-13T10:44:23Z","snapshot_observed_at":"2026-07-06T23:24:57.051440Z","submitted_at":"2026-05-13T10:44:23Z","title":"Tracing Persona Vectors Through LLM Pretraining","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-14T20:28:17.086117Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2605.13329"},"observation_digest":"sha256:595d02a0c0b92e9f1059c3b0f5de2641ab0613beb6b05dd068210e2addf6b78a","observation_id":"177d67b0-812c-4397-b1c1-bc3569c1bdd4","resolution":{"observed_at":"2026-05-14T20:29:27.886698Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2605.28114","last_updated":"2026-08-04T02:19:52Z","snapshot_observed_at":"2026-08-10T11:03:31.040109Z","submitted_at":"2026-05-27T08:06:50Z","title":"Language model agents show in-group trust bias invisible to standard behavioural audits","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T12:16:09.760516Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2605.28114"},"observation_digest":"sha256:03962014cdc6bc3d404f82bf8212b8327a4f951cc84ab8e3f2de15040f08ff1b","observation_id":"91f4be7f-c7c6-435e-8358-2a3435f36478","resolution":{"observed_at":"2026-06-29T12:23:24.485868Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2606.25899","last_updated":"2026-06-24T14:47:47Z","snapshot_observed_at":"2026-07-07T00:00:17.090702Z","submitted_at":"2026-06-24T14:47:47Z","title":"Manipulation Is Task-Dependent: A Multi-Axis, Multi-Environment Evaluation of Frontier LLMs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-25T19:07:05.406391Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2606.25899"},"observation_digest":"sha256:ea23d5383b35618e43c3609d5e23cb060c35504e9bc4a53895f567bee481e0dd","observation_id":"61a01cfa-fab8-4958-b964-a607b7eabfb6","resolution":{"observed_at":"2026-07-04T21:00:10.018341Z","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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":"2311.07590","doi":"10.48550/arxiv.2311.07590","metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure , url =","venue":"arXiv (Cornell University)","work_id":"3e028505-9578-4597-baf3-0a871f478f3a","year":2024},"citing_paper":{"arxiv_id":"2606.31916","last_updated":"2026-06-30T16:22:12Z","snapshot_observed_at":"2026-08-02T10:24:05.379334Z","submitted_at":"2026-06-30T16:22:12Z","title":"Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-07-01T05:40:54.002702Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2606.31916"},"observation_digest":"sha256:914a570a3a7560839a20023479cca2faeb5050a1806c7953c58b562c00f4eafa","observation_id":"884097bd-11be-4b0a-a74e-e6133246748f","resolution":{"observed_at":"2026-07-01T10:15:44.683595Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2311.07590","last_updated":"2024-07-15T08:51:52Z","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07590","snapshot_observed_at":"2026-08-01T12:54:36.127746Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19292","last_updated":"2026-07-21T17:02:37Z","snapshot_observed_at":"2026-08-09T18:07:49.749835Z","submitted_at":"2026-07-21T17:02:37Z","title":"The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T12:54:36.127746Z"},"links":{"cited_paper":"/paper/2311.07590","citing_paper":"/paper/2607.19292"},"observation_digest":"sha256:b33a01057b79a20cbb249943b30aa92cd4d9b29a6e26ebbd9782d1dfa9d9140a","observation_id":"1a57f4aa-f5e2-4147-a80c-66f953f08357","resolution":{"observed_at":"2026-08-01T12:54:36.127746Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2311.07590/citation-record","integrity":"/paper/2311.07590/integrity","json":"/paper/2311.07590/citation-record.json","paper":"/paper/2311.07590"},"outbound":[],"paper":{"arxiv_id":"2311.07590","last_updated":"2024-07-15T08:51:52Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-04T14:42:36.955119Z","submitted_at":"2023-11-09T17:12:44Z","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 0 of 0 outbound references and 27 inbound Pith citation observations for arXiv:2311.07590."}