{"as_of":"2026-08-08T19:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5e88fd74ca316c7f6a4a7458f646abe61eba926d0f86daca14fd90dd08b89b1a","coverage":[{"denominator":196,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:00:53.750838Z","state":"measured"},{"denominator":103,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":103,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:54:57.931702Z","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":"2026-07-10T12:15:01.137692Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.06366","snapshot_observed_at":"2026-08-07T10:54:57.931702Z","title":"Ai agent behavioral science","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.04018","last_updated":"2026-06-22T12:47:48Z","snapshot_observed_at":"2026-08-07T10:46:59.056034Z","submitted_at":"2025-06-04T14:46:47Z","title":"AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T10:54:57.931702Z"},"links":{"cited_paper":"/paper/2506.06366","citing_paper":"/paper/2506.04018"},"observation_digest":"sha256:153dba031f4064d0a7cdc6db49e026961337d7cf9b810a55afb87a4f45b8b535","observation_id":"6f177dc1-6011-4264-afbd-f455507a6c56","resolution":{"observed_at":"2026-08-07T10:54:57.931702Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"cited_work":{"arxiv_id":"2506.06366","doi":"10.48550/arxiv.2506.06366","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.06366","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"doi:10.48550/arXiv.2506.06366 , abstract =","venue":null,"work_id":"d19bcc7f-0aca-4781-87f0-62fcc28c2f83","year":2025},"citing_paper":{"arxiv_id":"2605.09197","last_updated":"2026-05-09T22:33:51Z","snapshot_observed_at":"2026-07-06T23:21:21.560069Z","submitted_at":"2026-05-09T22:33:51Z","title":"An Experimental Method to Study Opinion Diffusion in Human-AI Hybrid Societies","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-05-12T03:47:54.451357Z"},"links":{"cited_paper":"/paper/2506.06366","citing_paper":"/paper/2605.09197"},"observation_digest":"sha256:7654ba04a8b98678a35ef8960df9335c5c6a8efaaf19acb6f0893f916ffc8d72","observation_id":"5c8dc11b-6984-4435-9ddd-842f235b5ce9","resolution":{"observed_at":"2026-05-12T03:51:19.945669Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"cited_work":{"arxiv_id":"2506.06366","doi":"10.48550/arxiv.2506.06366","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.06366","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"doi:10.48550/arXiv.2506.06366 , abstract =","venue":null,"work_id":"d19bcc7f-0aca-4781-87f0-62fcc28c2f83","year":2025},"citing_paper":{"arxiv_id":"2605.27960","last_updated":"2026-05-27T04:54:07Z","snapshot_observed_at":"2026-08-03T00:24:19.442122Z","submitted_at":"2026-05-27T04:54:07Z","title":"Mags-RL: Wearing Multimodal LLMs a Magnifying Glass via Agentic Reinforcement Learning For Complex Scene Reasoning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-29T13:38:01.819121Z"},"links":{"cited_paper":"/paper/2506.06366","citing_paper":"/paper/2605.27960"},"observation_digest":"sha256:fe55ad9f2854aace6814bc54d950930eff29ff59508d4de76ab519b4f46fa811","observation_id":"34851dfd-aacb-4783-a010-c871f88229b3","resolution":{"observed_at":"2026-06-29T13:43:29.021857Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.06366/citation-record","integrity":"/paper/2506.06366/integrity","json":"/paper/2506.06366/citation-record.json","paper":"/paper/2506.06366"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:00:53.262552Z","title":"Coopera- tion, competition, and maliciousness: Llm-stakeholders interactive negotiation.Advances in Neural Information Processing Systems, 37:83548–83599, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.262552Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:7117548b86311a95df0aec46aa1551b490263a908a3c28126fbc484aa8c07fdd","observation_id":"d9705055-00e1-4ab5-99b5-af0fc5d96764","resolution":{"observed_at":"2026-08-07T11:00:53.262552Z","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":"2026-08-07T11:00:53.269248Z","title":"Large language models show human-like content biases in transmission chain experiments.Proceedings of the National Academy of Sciences, 120(44):e2313790120, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.269248Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:43f100972ea02c6b7be86c42a4426c98397b820a1b3bcde87053c7af5ccbf069","observation_id":"4619b45a-8d8f-4ec3-87c1-7d630d125c07","resolution":{"observed_at":"2026-08-07T11:00:53.269248Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.16867","last_updated":"2025-05-07T12:44:45Z","snapshot_observed_at":"2026-07-30T23:00:07.898209Z","submitted_at":"2023-05-26T12:17:59Z","title":"Playing repeated games with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.16867","snapshot_observed_at":"2026-08-07T11:00:53.274854Z","title":"Playing repeated games with large language models.arXiv preprint arXiv:2305.16867, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.274854Z"},"links":{"cited_paper":"/paper/2305.16867","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:9beaae7c4e60fc836f5699aef722024df511d82f446a656082fb7acd752fd295","observation_id":"851ea83e-3feb-425c-ae29-da8661cf55e5","resolution":{"observed_at":"2026-08-07T11:00:53.274854Z","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":"2026-08-07T11:00:53.281400Z","title":"Flamingo: a visual language model for few-shot learning.Advances in neural information processing systems, 35:23716–23736, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.281400Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:d8f28c3f62fdec2f7a61468d18cd26cb5d9ee5e028794db99c29c0a85604ca5f","observation_id":"d6461f96-66ad-4f5b-974a-e63c11b9de1c","resolution":{"observed_at":"2026-08-07T11:00:53.281400Z","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":"2026-08-07T11:00:53.287229Z","title":"Characterizing the role of bots’ in polarized stance on social media.Social Network Analysis and Mining, 12(1):30, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.287229Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:0b0f33887603d750da6081d3b4f2b4f56b76de049706a2204b3d8bcc26564445","observation_id":"d83c74a7-3863-4eac-86a7-e2023a61a1a7","resolution":{"observed_at":"2026-08-07T11:00:53.287229Z","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":"2026-08-07T11:00:53.292375Z","title":"Investigating Cultural Alignment of Large Language Models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.292375Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:024a7c5e4620a2d88bb9b79014dd0fe639411b673f9e0421178dea47a16d1305","observation_id":"ec12c66b-50db-47dd-aa2f-f2d907b0bdac","resolution":{"observed_at":"2026-08-07T11:00:53.292375Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.10571","last_updated":"2024-06-06T12:02:37Z","snapshot_observed_at":"2026-07-06T17:31:04.675896Z","submitted_at":"2024-02-16T10:55:38Z","title":"Direct Preference Optimization with an Offset","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.10571","snapshot_observed_at":"2026-08-07T11:00:53.302553Z","title":"Direct preference optimization with an offset","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.302553Z"},"links":{"cited_paper":"/paper/2402.10571","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:03e71f823e75cbf4b7ef81e4e0503b255982eda0405783d514da6c670cdc08d4","observation_id":"e669799f-6b5e-4c36-a8fd-f7011e9720ec","resolution":{"observed_at":"2026-08-07T11:00:53.302553Z","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":"2026-08-07T11:00:53.308292Z","title":"Embodied cognition: A field guide.Artificial intelligence, 149(1):91– 130, 2003","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.308292Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:7b6fb55696bb8904557e65181dd0e2fbe3c6d9f0dac93b4a65f451455aa9785a","observation_id":"cf145b7f-e214-473a-8f35-9b7e3e6a6121","resolution":{"observed_at":"2026-08-07T11:00:53.308292Z","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":"2026-08-07T11:00:53.322256Z","title":"The moral machine experiment.Nature, 563(7729):59–64, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.322256Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:8e0d635ae176301270c776cf87378c9d7c2f20aee6a7bb65e9a30a2845da9acc","observation_id":"80969970-613f-4ae8-8042-06e304dba322","resolution":{"observed_at":"2026-08-07T11:00:53.322256Z","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":"2026-08-07T11:00:53.326884Z","title":"Explicitly un- biased large language models still form biased associations.Proceedings of the National Academy of Sciences, 122(8):e2416228122, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.326884Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:84acfcd686a006bc6df6e82a0f7ffc6f3236514f7642c21d3afb6f2928dad1be","observation_id":"216ec829-4573-4c7e-9e80-1bf76cc5db30","resolution":{"observed_at":"2026-08-07T11:00:53.326884Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.07528","last_updated":"2020-02-11T00:56:50Z","snapshot_observed_at":"2026-08-06T20:46:20.413566Z","submitted_at":"2019-09-17T00:17:02Z","title":"Emergent Tool Use From Multi-Agent Autocurricula","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.07528","snapshot_observed_at":"2026-08-07T11:00:53.331363Z","title":"Emergent tool use from multi-agent autocurricula.ArXiv, abs/1909.07528, 2019","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.331363Z"},"links":{"cited_paper":"/paper/1909.07528","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:a79a3589b8301637b5a649cf3074025c2d1d0fc801795a96805f7f94fbc7989a","observation_id":"ef48afea-5d0e-49c8-bbeb-4f874f625408","resolution":{"observed_at":"2026-08-07T11:00:53.331363Z","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":"2026-08-07T11:00:53.336431Z","title":"Miller, Sandra Mitts, Adithya Renduchintala, Stephen Roller, Dirk Rowe, Weiyan Shi, Joe Spisak, Alexander Wei, David J","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.336431Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:56bcbf9d72ffb45229dd3a61241c3ed357c5a0b9f7d586de54a559de042ef0ef","observation_id":"1cbe9cad-3a9b-401c-b824-c99d1a9c84de","resolution":{"observed_at":"2026-08-07T11:00:53.336431Z","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":"2026-08-07T11:00:53.340700Z","title":"Social cognitive theory: An agentic perspective.Annual review of psychol- ogy, 52(1):1–26, 2001","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.340700Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:230712a4076aceb4cf697165d585d3656c760ba9d304a707f0b2101a417a545a","observation_id":"ea037c8c-863e-4f66-ab9e-602a21c98962","resolution":{"observed_at":"2026-08-07T11:00:53.340700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.05986","last_updated":"2025-07-21T13:51:31Z","snapshot_observed_at":"2026-08-08T17:06:27.267561Z","submitted_at":"2025-02-09T18:35:08Z","title":"Preventing Rogue Agents Improves Multi-Agent Collaboration","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.05986","snapshot_observed_at":"2026-08-07T11:00:53.345027Z","title":"Preventing rogue agents improves multi-agent collab- oration.arXiv preprint arXiv:2502.05986, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.345027Z"},"links":{"cited_paper":"/paper/2502.05986","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:7084ddf39b0beb273d47685f7dfb38a4a8990d696b71e6b2e1e8743055fb4a53","observation_id":"86ae5dad-8856-4daf-b3e7-9af72ca9eb40","resolution":{"observed_at":"2026-08-07T11:00:53.345027Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.22932","last_updated":"2024-11-01T12:37:10Z","snapshot_observed_at":"2026-07-06T19:42:12.472869Z","submitted_at":"2024-10-30T11:38:13Z","title":"Multi-Agent Large Language Models for Conversational Task-Solving","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.22932","snapshot_observed_at":"2026-08-07T11:00:53.349580Z","title":"Multi-agent large language models for conversational task-solving.arXiv preprint arXiv:2410.22932, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.349580Z"},"links":{"cited_paper":"/paper/2410.22932","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:11ec15ce930b435254e99e175c9360d363a2c866975ca90424d8c0266d2b21b9","observation_id":"94d052a4-0642-4b3f-b7eb-b4c798304b92","resolution":{"observed_at":"2026-08-07T11:00:53.349580Z","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":"2026-08-07T11:00:53.354026Z","title":"Reflective multi-agent collaboration based on large language models.Advances in Neural Information Processing Systems, 37:138595–138631, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.354026Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:73a74d1347f155d95379e42024acf881a2cf2496016e5bd339b54af63c660d11","observation_id":"47f75d80-186a-4462-9d66-d2c179b03936","resolution":{"observed_at":"2026-08-07T11:00:53.354026Z","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":"2026-08-07T11:00:53.357996Z","title":"Machine culture.Nature Human Behaviour, 7(11):1855–1868, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.357996Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:def4c71b513ce824107eceb6e361c7a2ee746758411991fcb4b49bb7c35366c1","observation_id":"13da3b81-5645-431d-87d5-8c722a0bc565","resolution":{"observed_at":"2026-08-07T11:00:53.357996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.06817","last_updated":"2023-08-11T17:45:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-12-13T18:55:15Z","title":"RT-1: Robotics Transformer for Real-World Control at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.06817","snapshot_observed_at":"2026-08-07T11:00:53.362150Z","title":"Rt-1: Robotics transformer for real-world control at scale.arXiv preprint arXiv:2212.06817, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.362150Z"},"links":{"cited_paper":"/paper/2212.06817","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:f05a6d5d02880315d653f94279565bcdfb5be4ebd82a125ea79245950dd59305","observation_id":"f17127d3-1733-4ad3-b8e6-be7fc6cd8952","resolution":{"observed_at":"2026-08-07T11:00:53.362150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.14125","last_updated":"2023-11-23T17:46:30Z","snapshot_observed_at":"2026-08-04T09:52:50.528860Z","submitted_at":"2023-11-23T17:46:30Z","title":"Scalable AI Safety via Doubly-Efficient Debate","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.14125","snapshot_observed_at":"2026-08-07T11:00:53.366862Z","title":"Scalable ai safety via doubly- efficient debate.arXiv preprint arXiv:2311.14125, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.366862Z"},"links":{"cited_paper":"/paper/2311.14125","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:e403396583b866a355bf66946a585a1673baecb082e4fc026c6000c5ecfab8e7","observation_id":"9529d80f-f8b2-4791-b77d-8c247b33a912","resolution":{"observed_at":"2026-08-07T11:00:53.366862Z","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":"2026-08-07T11:00:53.371557Z","title":"Behavioural science is unlikely to change the world without a heterogeneity revolution.Nature human behaviour, 5(8):980– 989, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.371557Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:598521f778868bca7f6bf1cf211a1230c6bb5aa016dcb04ad5ed561fd05cc282","observation_id":"446cb640-4dde-45e8-afda-0735735f05b2","resolution":{"observed_at":"2026-08-07T11:00:53.371557Z","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":"2026-08-07T11:00:53.376067Z","title":"Motivat- ing voter turnout by invoking the self.Proceedings of the National Academy of Sciences, 108(31):12653–12656, 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.376067Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:55621339591200749e4bacdfdc1d47fc4abd68c8a7fd4696793984cc762773c9","observation_id":"5a3af2d9-9d05-489e-8077-a865ae9c9d9f","resolution":{"observed_at":"2026-08-07T11:00:53.376067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.03827","last_updated":"2024-03-02T21:33:53Z","snapshot_observed_at":"2026-08-03T01:53:33.505931Z","submitted_at":"2022-12-07T18:17:56Z","title":"Discovering Latent Knowledge in Language Models Without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.03827","snapshot_observed_at":"2026-08-07T11:00:53.380523Z","title":"Discovering latent knowledge in language models without supervision.arXiv preprint arXiv:2212.03827, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.380523Z"},"links":{"cited_paper":"/paper/2212.03827","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:5a99c977c429892d552c61faf17bc69f46dbd518390502177138fbfd4cbc6ced","observation_id":"1b16e75a-d08b-4aa7-9cc8-cb61e729f44b","resolution":{"observed_at":"2026-08-07T11:00:53.380523Z","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":"2026-08-07T11:00:53.384816Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.384816Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:8d2c8458b3a713a8a7061f22e9c7040cd3c5758e236b8774971655bca965786d","observation_id":"9e6051a6-69d4-415c-8ee3-61b71c07225d","resolution":{"observed_at":"2026-08-07T11:00:53.384816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.07201","last_updated":"2023-08-14T15:13:04Z","snapshot_observed_at":"2026-08-02T01:34:38.978920Z","submitted_at":"2023-08-14T15:13:04Z","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.07201","snapshot_observed_at":"2026-08-07T11:00:53.388957Z","title":"Chateval: Towards better llm-based evaluators through multi-agent debate","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.388957Z"},"links":{"cited_paper":"/paper/2308.07201","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:a4fd9c438c5d6d07245f6ee7e413c3fd8e958b7f82f92e35f2fd12b900044360","observation_id":"310f587a-d45e-4010-b332-9fe2584e583d","resolution":{"observed_at":"2026-08-07T11:00:53.388957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.17288","last_updated":"2024-04-29T18:38:26Z","snapshot_observed_at":"2026-07-06T16:25:34.527871Z","submitted_at":"2023-09-29T14:46:30Z","title":"AutoAgents: A Framework for Automatic Agent Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.17288","snapshot_observed_at":"2026-08-07T11:00:53.394086Z","title":"Autoagents: A framework for automatic agent generation.arXiv preprint arXiv:2309.17288, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.394086Z"},"links":{"cited_paper":"/paper/2309.17288","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:beaa8ca165324d93aadf184350c2792541b2dee15b7f3b3382572e5a9aa84a32","observation_id":"83c51626-b378-40b0-943d-6579909daa31","resolution":{"observed_at":"2026-08-07T11:00:53.394086Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10858","last_updated":"2024-09-27T08:03:07Z","snapshot_observed_at":"2026-07-06T18:31:40.910349Z","submitted_at":"2024-06-16T09:06:17Z","title":"Step-level Value Preference Optimization for Mathematical Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10858","snapshot_observed_at":"2026-08-07T11:00:53.398869Z","title":"Step-level value preference optimiza- tion for mathematical reasoning.arXiv preprint arXiv:2406.10858, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.398869Z"},"links":{"cited_paper":"/paper/2406.10858","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:3b4eb6e464660f71e9d19b04f0f76ecfc36c360360afbe4cdf74385cf78117b5","observation_id":"5d3c20b9-ec80-4818-b818-4671909126f3","resolution":{"observed_at":"2026-08-07T11:00:53.398869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.20151","last_updated":"2025-01-21T06:26:43Z","snapshot_observed_at":"2026-07-06T16:40:55.334347Z","submitted_at":"2023-10-31T03:37:11Z","title":"Multi-Agent Consensus Seeking via Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.20151","snapshot_observed_at":"2026-08-07T11:00:53.403135Z","title":"Multi-agent consensus seeking via large language models.arXiv preprint arXiv:2310.20151, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.403135Z"},"links":{"cited_paper":"/paper/2310.20151","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:9ab02ed38647c8369f27dcbd4f81fa8d82dc0e199fa6370030fc4a936f7b8973","observation_id":"20001372-fcd0-4556-aba5-5c91a86697c3","resolution":{"observed_at":"2026-08-07T11:00:53.403135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05746","last_updated":"2024-08-25T11:19:33Z","snapshot_observed_at":"2026-07-06T16:29:51.896529Z","submitted_at":"2023-10-09T14:22:09Z","title":"Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05746","snapshot_observed_at":"2026-08-07T11:00:53.407589Z","title":"Put your money where your mouth is: Evaluating strategic planning and execution of llm agents in an auction arena.arXiv preprint arXiv:2310.05746, 2023","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.407589Z"},"links":{"cited_paper":"/paper/2310.05746","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:f23a5bd6b1d873e924da754631e77c24dce53670b17977726598b32395565b8c","observation_id":"64a52dcc-ce77-4f14-bf38-74f768ca6152","resolution":{"observed_at":"2026-08-07T11:00:53.407589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04578","last_updated":"2024-09-13T19:40:12Z","snapshot_observed_at":"2026-08-04T09:15:41.949487Z","submitted_at":"2024-02-07T04:36:31Z","title":"S-Agents: Self-organizing Agents in Open-ended Environments","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04578","snapshot_observed_at":"2026-08-07T11:00:53.412532Z","title":"S-agents: Self-organizing agents in open-ended environments.arXiv preprint arXiv:2402.04578, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.412532Z"},"links":{"cited_paper":"/paper/2402.04578","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:94e9ebf7b865d0138250280e272c188e3bdf364c6c329763f02a3e66ff683b46","observation_id":"03faee50-4dd7-4a90-963e-6d82b0e6fea8","resolution":{"observed_at":"2026-08-07T11:00:53.412532Z","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":"2026-08-07T11:00:53.419620Z","title":"Decision transformer: Reinforcement learn- ing via sequence modeling.Advances in neural information processing systems, 34:15084– 15097, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.419620Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:42b4ff7e16cfb72ed202418cf04e6dd9c6ebf91f536d4179fa94222164875772","observation_id":"8a59047d-d378-4917-a402-e0d2e64f782d","resolution":{"observed_at":"2026-08-07T11:00:53.419620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.12292","last_updated":"2024-01-31T06:44:42Z","snapshot_observed_at":"2026-08-08T12:57:35.341622Z","submitted_at":"2024-01-22T19:00:08Z","title":"GRATH: Gradual Self-Truthifying for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.12292","snapshot_observed_at":"2026-08-07T11:00:53.424864Z","title":"Grath: Gradual self-truthifying for large language models.arXiv preprint arXiv:2401.12292, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.424864Z"},"links":{"cited_paper":"/paper/2401.12292","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:bb30dbabf57da42d8cf99fe1108175bd1461d14a85c85fd9bd7e0a7af5183bbc","observation_id":"d2f089a9-3cec-46a1-9576-06b4abdfcee6","resolution":{"observed_at":"2026-08-07T11:00:53.424864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.10848","last_updated":"2023-10-23T05:05:15Z","snapshot_observed_at":"2026-07-06T16:08:37.443746Z","submitted_at":"2023-08-21T16:47:11Z","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.10848","snapshot_observed_at":"2026-08-07T11:00:53.429632Z","title":"Agentverse: Facilitating multi-agent collabo- ration and exploring emergent behaviors in agents.arXiv preprint arXiv:2308.10848, 2(4):6, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.429632Z"},"links":{"cited_paper":"/paper/2308.10848","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:d18892358672281a4069ea43e45454ff8d436fc5c3a99d049fefbb0afdc2a536","observation_id":"640e3b71-7446-47c0-bac6-e910fc7d59d5","resolution":{"observed_at":"2026-08-07T11:00:53.429632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.13359","last_updated":"2024-09-20T09:44:51Z","snapshot_observed_at":"2026-07-06T19:18:41.002837Z","submitted_at":"2024-09-20T09:44:51Z","title":"EmotionQueen: A Benchmark for Evaluating Empathy of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.13359","snapshot_observed_at":"2026-08-07T11:00:53.434105Z","title":"Emotionqueen: A benchmark for evaluating empathy of large language models.arXiv preprint arXiv:2409.13359, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.434105Z"},"links":{"cited_paper":"/paper/2409.13359","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:f7fce0b3e9608edc35033fd2155967a3aa964958c3185944d5bb51719fb025b0","observation_id":"37ccd495-ac9c-4e45-8c2b-edf8c4943a18","resolution":{"observed_at":"2026-08-07T11:00:53.434105Z","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":"2026-08-07T11:00:53.439443Z","title":"Deep reinforcement learning from human preferences.Advances in neural information pro- cessing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.439443Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:be66d4ef8385d014353101a36a896942422b546b18be6efba18a9c0890c63608","observation_id":"fcddcda7-d4fd-40ed-9969-b6ceb0847ecf","resolution":{"observed_at":"2026-08-07T11:00:53.439443Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09618","last_updated":"2024-04-01T01:12:35Z","snapshot_observed_at":"2026-08-08T03:51:13.261550Z","submitted_at":"2023-11-16T07:01:48Z","title":"Simulating Opinion Dynamics with Networks of LLM-based Agents","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09618","snapshot_observed_at":"2026-08-07T11:00:53.444665Z","title":"Simulating opinion dynamics with networks of llm-based agents.arXiv preprint arXiv:2311.09618, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.444665Z"},"links":{"cited_paper":"/paper/2311.09618","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:18cc3d59e2fc46819040ff0b0d756bc5e82fccd2d274ae3adfe54c30aef5cb24","observation_id":"7f332a23-e52d-4dc4-92ee-df668df47813","resolution":{"observed_at":"2026-08-07T11:00:53.444665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09665","last_updated":"2024-02-16T16:43:53Z","snapshot_observed_at":"2026-07-06T16:48:25.188504Z","submitted_at":"2023-11-16T08:30:15Z","title":"The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09665","snapshot_observed_at":"2026-08-07T11:00:53.448944Z","title":"The wisdom of partisan crowds: Comparing collective intelligence in humans and llm-based agents.arXiv preprint arXiv:2311.09665, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.448944Z"},"links":{"cited_paper":"/paper/2311.09665","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:53254de255c7b663d11251920fb1d84a327989b534e7c1bbcb415cb6c30fc80a","observation_id":"a5af3d35-4222-45a9-a4bf-94e582a61d21","resolution":{"observed_at":"2026-08-07T11:00:53.448944Z","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":"2026-08-07T11:00:53.453558Z","title":"MIT press, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.453558Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:31daac26e69fc0a86e1d6a5aee917039224032446995a324fe187a4c884222c5","observation_id":"0147d112-524a-4da7-a91d-fbdeaa3b45a5","resolution":{"observed_at":"2026-08-07T11:00:53.453558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.04341","last_updated":"2019-06-11T01:31:41Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2019-06-11T01:31:41Z","title":"What Does BERT Look At? An Analysis of BERT's Attention","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.04341","snapshot_observed_at":"2026-08-07T11:00:53.458415Z","title":"What does bert look at? an analysis of bert’s attention.arXiv preprint arXiv:1906.04341, 2019","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.458415Z"},"links":{"cited_paper":"/paper/1906.04341","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:777c39e33ef0c39b23782e4fde9b9395290660ef39a96e950da70351455ca6dc","observation_id":"68a3dba3-bc8c-47d9-8123-271173328cf5","resolution":{"observed_at":"2026-08-07T11:00:53.458415Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18225","last_updated":"2024-02-28T10:43:54Z","snapshot_observed_at":"2026-07-06T17:36:45.056710Z","submitted_at":"2024-02-28T10:43:54Z","title":"CogBench: a large language model walks into a psychology lab","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18225","snapshot_observed_at":"2026-08-07T11:00:53.463434Z","title":"Cogbench: a large language model walks into a psychology lab.arXiv preprint arXiv:2402.18225, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.463434Z"},"links":{"cited_paper":"/paper/2402.18225","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:e9f7d2d30d14ef45b6e13d92d0cb482e67bef10426296f26bda232245148582c","observation_id":"bda32900-7291-46cc-9e6b-05664bda5087","resolution":{"observed_at":"2026-08-07T11:00:53.463434Z","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":"2026-08-07T11:00:53.469013Z","title":"Durably reducing conspiracy beliefs through dialogues with ai.Science, 385(6714):eadq1814, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.469013Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:bf9917607e50103c4321b183f19623febac2719ac4d12799b7c8fbe9e914e197","observation_id":"bcc55527-23d6-4421-a91d-103be5df966c","resolution":{"observed_at":"2026-08-07T11:00:53.469013Z","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":"2026-08-07T11:00:53.473420Z","title":"Ultrafeedback: Boosting language models with high-quality feedback","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.473420Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:50f3bd41276c681df48d072bbf7e6e5ba64afc9bd8007877e09aa428ea15204e","observation_id":"967b0ec1-29e4-4caf-8250-87475c7d8b15","resolution":{"observed_at":"2026-08-07T11:00:53.473420Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14373","last_updated":"2024-07-01T22:06:13Z","snapshot_observed_at":"2026-07-06T18:34:15.291938Z","submitted_at":"2024-06-20T14:42:58Z","title":"Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14373","snapshot_observed_at":"2026-08-07T11:00:53.478059Z","title":"Artificial leviathan: Exploring social evolution of llm agents through the lens of hobbe- sian social contract theory.arXiv preprint arXiv:2406.14373, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.478059Z"},"links":{"cited_paper":"/paper/2406.14373","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:76fecb96f650e7f50070c907d69e6c4f1dcb553547410509097a11fb1bef6990","observation_id":"1b0a22dd-9cfb-4cda-8803-af37ef68b8b0","resolution":{"observed_at":"2026-08-07T11:00:53.478059Z","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":"2026-08-07T11:00:53.482355Z","title":"Behavioural nudges increase covid-19 vaccinations.Nature, 597(7876):404–409, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.482355Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:237c6ac5fd6ccc18b39b0d9e017c0a2f4742d0797ffe3c964f9c352a484c28a8","observation_id":"e62db63e-697b-40aa-91c2-182d05077382","resolution":{"observed_at":"2026-08-07T11:00:53.482355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.04203","last_updated":"2025-02-17T08:40:51Z","snapshot_observed_at":"2026-07-31T22:13:16.778044Z","submitted_at":"2024-08-08T03:57:20Z","title":"MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.04203","snapshot_observed_at":"2026-08-07T11:00:53.486440Z","title":"Mmrole: A com- prehensive framework for developing and evaluating multimodal role-playing agents.arXiv preprint arXiv:2408.04203, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.486440Z"},"links":{"cited_paper":"/paper/2408.04203","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:4b687fc7f03ce7ea2156e59fc148df09bc362f170570168b4350b04c6cc0f180","observation_id":"fea46a8e-1d74-47f1-80aa-2efd4af74803","resolution":{"observed_at":"2026-08-07T11:00:53.486440Z","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":"2026-08-07T11:00:53.491854Z","title":"Springer Science & Business Media, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.491854Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:04992d9757faed48e3734abb17d3aa846f29f8a2ab20e3d6baa9b5e423db2d36","observation_id":"cf8b26b1-c617-41fb-8402-69cd75043951","resolution":{"observed_at":"2026-08-07T11:00:53.491854Z","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":"2026-08-07T11:00:53.496242Z","title":"Shared mental models: Ideologies and institutions","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.496242Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:20ae83a6ae5c3a3581c36c625d0fc5bca684b7690898bf83fab708cc99a39c46","observation_id":"6731264b-e8ca-42ce-940d-a0163bc016ad","resolution":{"observed_at":"2026-08-07T11:00:53.496242Z","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":"2026-08-07T11:00:53.500482Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.500482Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:5e42f7b421868f6208514a95c2026355b8cfc9b802364c558cc95c840a2fc65e","observation_id":"37a2c130-730f-4b4e-934c-e80db71905f9","resolution":{"observed_at":"2026-08-07T11:00:53.500482Z","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":"2026-08-07T11:00:53.505150Z","title":"Springer, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.505150Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:5c79db380557d2127682216f59ed652048055fa5b2325d845b282957b747cfb3","observation_id":"7e02b46f-2185-4bdb-8769-6939d0d300d0","resolution":{"observed_at":"2026-08-07T11:00:53.505150Z","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":"2026-08-07T11:00:53.509332Z","title":"Humaine: human multi-agent immersive negotiation competition","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.509332Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:b844e961ceabd3cf0c527b1bee45f4ed10f8d1cfd5d2a42aaba893381ab83da1","observation_id":"38e0616d-10cc-40de-b8a5-57bda2e087d4","resolution":{"observed_at":"2026-08-07T11:00:53.509332Z","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":"2026-08-07T11:00:53.513986Z","title":"Towards a rigorous science of interpretable machine learning, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.513986Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:cfecb036fdb0e2491630c8de33b098410ac0df76c1c57f6a2e97ba22ac9d14ab","observation_id":"52b3cfbb-932f-4145-8fd3-909a7c9cd47f","resolution":{"observed_at":"2026-08-07T11:00:53.513986Z","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":"2026-08-07T11:00:53.518559Z","title":"Algorithmic agents in the hybrid media system: Social bots, selective amplifica- tion, and partisan news about covid-19.Human Communication Research, 48(3):516–542, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.518559Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:a74b095ce9e54515bde59485f9990c170b74b6daf2e399cc5c0c54ac12f2ceb8","observation_id":"6973fe7c-5c22-4f9c-9287-546da7a46ff2","resolution":{"observed_at":"2026-08-07T11:00:53.518559Z","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":"2026-08-07T11:00:53.522520Z","title":"EtiCor: Corpus for Analyzing LLMs for Etiquettes","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.522520Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:bfe2bcac1e1ecf437506638febe9164e3911671cc03a1e73a2a5e199330be96b","observation_id":"302fcce4-03e5-4b25-81a5-a0393fc1744b","resolution":{"observed_at":"2026-08-07T11:00:53.522520Z","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":"2026-08-07T11:00:53.527046Z","title":"Chatgpt outperforms humans in emotional awareness evaluations.Frontiers in psychology, 14:1199058, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.527046Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:d50dbbf3c924a39408d18403d5b891ea4f4b21f9c75b327728a053261d8787ea","observation_id":"c4ff2955-3424-48be-8d20-2a0f7ac631ff","resolution":{"observed_at":"2026-08-07T11:00:53.527046Z","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":"2026-08-07T11:00:53.532067Z","title":"Brookings Institution Press, 1996","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.532067Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:9bdc630b3e6874f7e74d916747cc4b0a572fbc03639cd866a6077a39c99b1169","observation_id":"0e2a777d-3e0c-49b5-a4c8-583b99977b6a","resolution":{"observed_at":"2026-08-07T11:00:53.532067Z","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":"2026-08-07T11:00:53.539387Z","title":"Why does unsuper- vised pre-training help deep learning? InProceedings of the thirteenth international confer- ence on artificial intelligence and statistics, pages 201–208","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.539387Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:424088112f25354eaaef06fd12dde8dc14ad2a6a1f376dde5a1b1c7af2042641","observation_id":"4424d991-1402-4adb-93bd-b41012099676","resolution":{"observed_at":"2026-08-07T11:00:53.539387Z","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":"2026-08-07T11:00:53.551101Z","title":"Can large language models serve as ra- tional players in game theory? a systematic analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.551101Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:66ad377e070cb9a96ecf3604e258c6452ff455c7e16739d39f2207c1ef9fd798","observation_id":"b6de590c-78e8-4e2d-a62b-f5c036fc4674","resolution":{"observed_at":"2026-08-07T11:00:53.551101Z","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":"2026-08-07T11:00:53.555300Z","title":"A behavior model for persuasive design","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.555300Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:c341d8fcaff943259ea20d65dd126fdbf3f1bf520e8b0e89e0c60b5970fc71eb","observation_id":"738ec1d7-419c-4eb8-b399-dd72f314a1e0","resolution":{"observed_at":"2026-08-07T11:00:53.555300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.13605","last_updated":"2024-09-19T15:19:58Z","snapshot_observed_at":"2026-08-04T22:21:01.792613Z","submitted_at":"2024-06-19T14:51:14Z","title":"Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.13605","snapshot_observed_at":"2026-08-07T11:00:53.560262Z","title":"Nicer than humans: How do large language models behave in the prisoner’s dilemma?arXiv preprint arXiv:2406.13605, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.560262Z"},"links":{"cited_paper":"/paper/2406.13605","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:82b10c4e56020e89728152ccc731aff2c32951fadbcc2d4b1bc5cea1a902aa7e","observation_id":"10108a32-8531-4830-ad83-6421022d3719","resolution":{"observed_at":"2026-08-07T11:00:53.560262Z","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":"2026-08-07T11:00:53.565136Z","title":"Bias and fairness in large language models: A survey.Computational Linguistics, 50(3):1097–1179, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.565136Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:3304fafd70ea2c697a17d62c18b5abc2456791e1b4c32e9ec87e841d7dbc0973","observation_id":"c7ffc13a-6a23-4ed6-a2a1-f1367ae1779f","resolution":{"observed_at":"2026-08-07T11:00:53.565136Z","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":"2026-08-07T11:00:53.569600Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.569600Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:4c505f7bd6d3d5502ff50aab806220b6a699b83a1414a186a00b04e370c2815e","observation_id":"c0045b91-560c-4499-a0e5-a819b7c88d06","resolution":{"observed_at":"2026-08-07T11:00:53.569600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.14984","last_updated":"2025-06-03T23:11:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-07-27T16:24:56Z","title":"S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.14984","snapshot_observed_at":"2026-08-07T11:00:53.574042Z","title":"S3: Social-network simulation system with large language model- empowered agents.arXiv preprint arXiv:2307.14984, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.574042Z"},"links":{"cited_paper":"/paper/2307.14984","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:2ccc418b711a12fa190d92fe6a38b716a0609f59fe769d4ba5250d492d956963","observation_id":"7580147b-d25c-4c33-80cf-69a7c0fa555c","resolution":{"observed_at":"2026-08-07T11:00:53.574042Z","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":"2026-08-07T11:00:53.580009Z","title":"How human–ai feedback loops alter human perceptual, emotional and social judgements.Nature Human Behaviour, pages 1–15, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.580009Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:13b68eb0bde57f004d495f5e24f64c6c0d581b82c9c6baf4a37a6e9e46008b3c","observation_id":"8b9d9137-f639-424b-9588-0d50ee3a1f4b","resolution":{"observed_at":"2026-08-07T11:00:53.580009Z","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":"2026-08-07T11:00:53.584482Z","title":"Deception abilities emerged in large language models.Proceedings of the National Academy of Sciences, 121(24):e2317967121, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.584482Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:e1b7fc3540473cde2959cae4355f384d9edb05ce1839231c75f4339c75051db1","observation_id":"8951716d-a854-4535-a269-5df387763520","resolution":{"observed_at":"2026-08-07T11:00:53.584482Z","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":"2026-08-07T11:00:53.588512Z","title":"Human-like intuitive behavior and rea- soning biases emerged in large language models but disappeared in chatgpt.Nature Compu- tational Science, 3(10):833–838, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.588512Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:c85232317d281dc388cd93a50ddccb87c5686ef4a6f26d2799a982b23419ecd6","observation_id":"9ed94c98-a0af-49c0-bd85-ef949e5fa2af","resolution":{"observed_at":"2026-08-07T11:00:53.588512Z","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":"2026-08-07T11:00:53.592691Z","title":"A survey on vision transformer.IEEE transactions on pattern analysis and machine intelligence, 45(1):87–110, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.592691Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:c9aa7a0bd47b84f29786831cfbd7211e8c0667f32b4b0319b92ee7be134a033e","observation_id":"34dd7d9a-d905-4b43-8109-3b30ed149d01","resolution":{"observed_at":"2026-08-07T11:00:53.592691Z","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":"2026-08-07T11:00:53.596987Z","title":"Large language models are bad game theoretic reasoners: Evaluating performance and bias in two- player non-zero-sum games","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.596987Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:f33f8c840155d86dfc4978be029f91df98bcf65f5034169df7e66fcc301b58b4","observation_id":"8d829d3f-4707-4bbf-980a-bc7a1b772542","resolution":{"observed_at":"2026-08-07T11:00:53.596987Z","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":"2026-08-07T11:00:53.601742Z","title":"Ai generates covertly racist decisions about people based on their dialect.Nature, 633(8028):147–154, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.601742Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:fce4fda90600242541eb38d58ebb0f4765a7f0717547aaccf0799ea0c64f8d7f","observation_id":"32e4e515-30b2-4355-8bba-5dcadb586978","resolution":{"observed_at":"2026-08-07T11:00:53.601742Z","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":"2026-08-07T11:00:53.605928Z","title":"Wang, Chenhui Zhang, Zhangheng LI, Bo Li, and Zhangyang Wang","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.605928Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:9782150896191bb5a3e2fab373766917a85b2cc21cc4465baa5a956c5667012b","observation_id":"940e043d-a436-458e-bacc-461970c86ebb","resolution":{"observed_at":"2026-08-07T11:00:53.605928Z","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":"2026-08-07T11:00:53.609923Z","title":"Generative Language Models Exhibit Social Identity Biases, June 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.609923Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:cf99ed01b9ead54ae3fdd761d13473157f074cdc6f0ed94cdb6f625836bf9f3d","observation_id":"8d36eb49-0732-42bd-8c41-c066cb1e4eee","resolution":{"observed_at":"2026-08-07T11:00:53.609923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.17227","last_updated":"2024-01-30T18:53:30Z","snapshot_observed_at":"2026-08-05T22:06:16.866709Z","submitted_at":"2023-11-28T20:59:49Z","title":"War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.17227","snapshot_observed_at":"2026-08-07T11:00:53.614973Z","title":"War and peace (waragent): Large language model-based multi-agent simulation of world wars.arXiv preprint arXiv:2311.17227, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.614973Z"},"links":{"cited_paper":"/paper/2311.17227","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:881035f0b93e0cc8ea178e257f2d5dbe5912e043599eda3b684dc05a568dac3c","observation_id":"f4f28718-4d9a-4ac6-a9d4-680a507534d1","resolution":{"observed_at":"2026-08-07T11:00:53.614973Z","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":"2026-08-07T11:00:53.620200Z","title":"Competing large language models in multi-agent gaming environments","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.620200Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:576c86ee41bde1c463c319bf32fe0d0ca90a1535120c79f51137d5eb82adf240","observation_id":"2869919f-991f-40d7-be36-cb9a0982251f","resolution":{"observed_at":"2026-08-07T11:00:53.620200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.20276","last_updated":"2024-08-11T13:56:58Z","snapshot_observed_at":"2026-07-06T18:53:31.241776Z","submitted_at":"2024-07-25T13:44:22Z","title":"Assessing AI Utility: The Random Guesser Test for Sequential Decision-Making Systems","version":2},"cited_work":{"arxiv_id":"2407.20276","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.20276","snapshot_observed_at":"2026-08-07T11:00:55.131808Z","title":"Assessing AI Utility: The Random Guesser Test for Sequential Decision-Making Systems","venue":"cs.CY","work_id":"8d6fc2a4-fadd-4697-89d1-c8d88d0217c2","year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.624618Z"},"links":{"cited_paper":"/paper/2407.20276","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:35b28e3eaec1415eb3935838fbaaae673449cb83bfe6ff40fe0908b3c65e3774","observation_id":"efffb5c6-3a7f-4b6e-8f88-49e4dc8cd26a","resolution":{"observed_at":"2026-08-07T11:00:55.137054Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11564","last_updated":"2023-10-17T20:22:13Z","snapshot_observed_at":"2026-07-06T16:34:42.650324Z","submitted_at":"2023-10-17T20:22:13Z","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11564","snapshot_observed_at":"2026-08-07T11:00:53.630371Z","title":"Personalized soups: Per- sonalized large language model alignment via post-hoc parameter merging.arXiv preprint arXiv:2310.11564, 2023","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.630371Z"},"links":{"cited_paper":"/paper/2310.11564","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:92476406056c1091f9881cd1a0d7a3ac4a87f8bcf378ae149b4cc3e68f6cf6e9","observation_id":"5c044a57-8491-44ee-b65a-07a953415983","resolution":{"observed_at":"2026-08-07T11:00:53.630371Z","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":"2026-08-07T11:00:53.635125Z","title":"Hwang, Chandra Bhagavatula, Ronan Le Bras, Jenny T","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.635125Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:fcef8ea8289cf9ce8a958ef89bc3dba993a05f3ccad7ef9e97b90bc40a7133d4","observation_id":"c06692f9-c2a0-42e9-9f60-a1ba8a3bd909","resolution":{"observed_at":"2026-08-07T11:00:53.635125Z","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":"2026-08-07T11:00:53.639774Z","title":"The global landscape of ai ethics guidelines","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.639774Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:1f905f601b2a41fc281c950f35b933e44b0803e37caf2f6b39af0295d7037c86","observation_id":"7c9f4a13-f27d-4d55-bc88-70764be5e847","resolution":{"observed_at":"2026-08-07T11:00:53.639774Z","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":"2026-08-07T11:00:53.644034Z","title":"Hachette UK, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.644034Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:9401a242c29885a754831b27ca74b239b9949be964d45dbaa35e2fe0e70f2af0","observation_id":"c66534b2-005f-4517-a613-6d22fc2ff4e3","resolution":{"observed_at":"2026-08-07T11:00:53.644034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12999","last_updated":"2025-06-16T05:47:36Z","snapshot_observed_at":"2026-07-06T19:34:55.594468Z","submitted_at":"2024-10-16T19:56:22Z","title":"POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12999","snapshot_observed_at":"2026-08-07T11:00:53.648319Z","title":"Porover: Improving safety and reducing overrefusal in large language models with overgeneration and preference optimization.arXiv preprint arXiv:2410.12999, 2024","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.648319Z"},"links":{"cited_paper":"/paper/2410.12999","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:41b79a64ae4506c293e2449bad3db328722d08503feacab804efd96da6538a95","observation_id":"b1a01a2b-57b2-40ae-9c79-94c5165b817b","resolution":{"observed_at":"2026-08-07T11:00:53.648319Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11441","last_updated":"2022-01-27T10:56:33Z","snapshot_observed_at":"2026-08-07T18:12:31.721863Z","submitted_at":"2022-01-27T10:56:33Z","title":"Human-centered mechanism design with Democratic AI","version":1},"cited_work":{"arxiv_id":"2201.11441","doi":null,"metadata_source":"pith","pith_arxiv_id":"2201.11441","snapshot_observed_at":"2026-08-07T11:00:55.067012Z","title":"Human-centered mechanism design with Democratic AI","venue":"cs.AI","work_id":"9fe3ec8e-5ec3-415d-99b9-99f3c46f6f72","year":2022},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.653125Z"},"links":{"cited_paper":"/paper/2201.11441","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:8d68f8c9cc4edcd024ecab66ba12f044ac5fbb36c3e18c06ee196afc63151975","observation_id":"33c3e096-7239-4367-bba9-5060062900a0","resolution":{"observed_at":"2026-08-07T11:00:55.072150Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T11:00:53.658191Z","title":"Socially situated artificial intelligence enables learning from human interaction.Proceedings of the National Academy of Sciences, 119(39):e2115730119, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.658191Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:8f11fd107e4475db377e290747fb7b8e9a7ddb629300473099f25ff413ed6222","observation_id":"60f6b22c-477d-497c-a562-16fedd968a5f","resolution":{"observed_at":"2026-08-07T11:00:53.658191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06625","last_updated":"2024-02-09T18:57:08Z","snapshot_observed_at":"2026-07-06T17:28:06.332906Z","submitted_at":"2024-02-09T18:57:08Z","title":"Understanding the Effects of Iterative Prompting on Truthfulness","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06625","snapshot_observed_at":"2026-08-07T11:00:53.662278Z","title":"Understanding the effects of iterative prompting on truthfulness.arXiv preprint arXiv:2402.06625, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.662278Z"},"links":{"cited_paper":"/paper/2402.06625","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:59b53dc8b80f3c5a2bf5246094f881e60d63d253d801972937741a4067e1540f","observation_id":"112fb250-d4e5-4b53-a4f9-5f9e618f8f30","resolution":{"observed_at":"2026-08-07T11:00:53.662278Z","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":"2026-08-07T11:00:53.667221Z","title":"The first workshop on ai behavioral science","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.667221Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:ea89a556cf1b2ded1f937c65c77eb9041dfcf7c52525d8d083f38dc5d2282518","observation_id":"6ceda5bc-c695-4dc3-b045-40bf50c0f64d","resolution":{"observed_at":"2026-08-07T11:00:53.667221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14985","last_updated":"2024-10-13T22:09:00Z","snapshot_observed_at":"2026-08-05T09:54:40.110243Z","submitted_at":"2023-10-23T14:35:26Z","title":"LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.14985","snapshot_observed_at":"2026-08-07T11:00:53.671610Z","title":"Llm-based agent society investigation: Collaboration and confronta- tion in avalon gameplay.arXiv preprint arXiv:2310.14985, 2023","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.671610Z"},"links":{"cited_paper":"/paper/2310.14985","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:00cf1aab5468b184b3e834301d861414193371d7547e4dca6a391a15b334743c","observation_id":"059a56e7-689e-425e-8ad6-5155c14d84e8","resolution":{"observed_at":"2026-08-07T11:00:53.671610Z","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":"2026-08-07T11:00:53.677046Z","title":"Uncovering the semantics of concepts using gpt-4.Proceedings of the National Academy of Sciences, 120(49):e2309350120, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.677046Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:1cc2ea2a04c863a2958468d9b488a3dd5fc6e6f7a2382df8ca44dc22ef7f8078","observation_id":"4508cb11-d9ed-4f0c-81c9-00572a95a705","resolution":{"observed_at":"2026-08-07T11:00:53.677046Z","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":"2026-08-07T11:00:53.681017Z","title":"Oxford University Press Oxford, 164–182, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.681017Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:07cc5fc9f7a982f7facbadac85702f9aef3db1f701da1f559ca27d8b3d02579c","observation_id":"ccbaa325-c890-4e6d-a38b-ade2d79d18a2","resolution":{"observed_at":"2026-08-07T11:00:53.681017Z","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":"2026-08-07T11:00:53.685073Z","title":"Prompting fairness: Integrating causality to debias large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.685073Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:14a0083e279ad9f74fc8a483562617d054cc2cb001ac031be8061e6af6269449","observation_id":"9f786f60-0ee5-4725-b2f0-bb6e79b09ae3","resolution":{"observed_at":"2026-08-07T11:00:53.685073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10436","last_updated":"2024-05-24T02:53:59Z","snapshot_observed_at":"2026-07-06T16:33:47.711411Z","submitted_at":"2023-10-16T14:19:40Z","title":"EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10436","snapshot_observed_at":"2026-08-07T11:00:53.689607Z","title":"Econagent: large lan- guage model-empowered agents for simulating macroeconomic activities.arXiv preprint arXiv:2310.10436, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.689607Z"},"links":{"cited_paper":"/paper/2310.10436","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:6c7804c1932ba2979041f1d9645c4a41d29e370962b5f3dde54e8706639ed656","observation_id":"5687151e-2bb0-4ad0-ab1b-516580b3bd62","resolution":{"observed_at":"2026-08-07T11:00:53.689607Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06500","last_updated":"2025-08-15T14:18:48Z","snapshot_observed_at":"2026-07-06T16:30:25.358715Z","submitted_at":"2023-10-10T10:17:58Z","title":"MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06500","snapshot_observed_at":"2026-08-07T11:00:53.694128Z","title":"Metaagents: Simulating interactions of human behaviors for llm-based task-oriented coordination via collaborative generative agents.arXiv preprint arXiv:2310.06500, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.694128Z"},"links":{"cited_paper":"/paper/2310.06500","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:ef45ea84dfe30355e07dc598412f2a15128ca0b7d5c2bf5847215c422b083cb4","observation_id":"7615888a-f70e-4fcf-8700-4ef6b25d2fae","resolution":{"observed_at":"2026-08-07T11:00:53.694128Z","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":"2026-08-07T11:00:53.698194Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.698194Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:b0bb023069c4679817252342c1f36174fc1409ad6e458aa96c0e9ee8e3290196","observation_id":"8d70c9ec-c893-4d34-8d8d-df13155dec60","resolution":{"observed_at":"2026-08-07T11:00:53.698194Z","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":"2026-08-07T11:00:53.702204Z","title":"Strategy selection as rational metareasoning.Psycho- logical review, 124(6):762, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.702204Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:6a81a99743da74a21e0283eb6e0b9783fa26ca3af9b20032855d87fe1ee8342b","observation_id":"9978d921-17a5-4f28-b89f-914c23fc0dd9","resolution":{"observed_at":"2026-08-07T11:00:53.702204Z","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":"2026-08-07T11:00:53.706013Z","title":"Toward a better understanding of the emo- tional dynamics of negotiation with large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.706013Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:1e7e012d0e4374f1931842d951fc3e89dd43b6e1fe9cd7d846019071049b53ce","observation_id":"fb16a92a-dd27-429a-b4e7-a8c49c5b8cf3","resolution":{"observed_at":"2026-08-07T11:00:53.706013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.07958","last_updated":"2022-05-08T02:43:02Z","snapshot_observed_at":"2026-08-03T16:26:48.747700Z","submitted_at":"2021-09-08T17:15:27Z","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.07958","snapshot_observed_at":"2026-08-07T11:00:53.709773Z","title":"Truthfulqa: Measuring how models mimic human falsehoods.arXiv preprint arXiv:2109.07958, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.709773Z"},"links":{"cited_paper":"/paper/2109.07958","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:24fbfbd46ff074b0157cde782f30180fd4a398ea7bc7c199518758984264faca","observation_id":"2423138d-d9dc-4b6e-b98d-2577dbf4af48","resolution":{"observed_at":"2026-08-07T11:00:53.709773Z","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":"2026-08-07T11:00:53.714323Z","title":"Explainable ai: A review of machine learning interpretability methods.Entropy, 23(1):18, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.714323Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:e7e9813643fa21109b3c8b7f6091626729048199ab65bc5e4efb02b259ff0e34","observation_id":"450271a1-9933-4d46-a078-5ef58a5d1e3f","resolution":{"observed_at":"2026-08-07T11:00:53.714323Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.00548","last_updated":"2024-06-01T20:12:54Z","snapshot_observed_at":"2026-08-03T19:56:22.125001Z","submitted_at":"2024-06-01T20:12:54Z","title":"LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models","version":1},"cited_work":{"arxiv_id":"2406.00548","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.00548","snapshot_observed_at":"2026-08-07T11:00:54.925541Z","title":"LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models","venue":"cs.LG","work_id":"1e7161fd-624a-45b3-b1d0-193162032f92","year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.718432Z"},"links":{"cited_paper":"/paper/2406.00548","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:744674070d522d7ee241e0476c747a792ec2bcadce1abda29f0cdd02c704abed","observation_id":"0bd40fc6-7a4d-4959-add0-c74b23204634","resolution":{"observed_at":"2026-08-07T11:00:54.930327Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T11:00:53.723520Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.723520Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:b4002ed6a6c275af3aaf8b7b9bb2d0e2101ef11920c7184085b167153555c7ed","observation_id":"225c1f65-d127-445e-b75e-2d4a6713d02a","resolution":{"observed_at":"2026-08-07T11:00:53.723520Z","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":"2026-08-07T11:00:53.728920Z","title":"Strategic behavior of large language models and the role of game structure versus contextual framing.Scientific Reports, 14(1):18490, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.728920Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:61b315d0f0f14e7336b592f5e2d6d7df7323b27d24ae2c7c2547ab0874c2092d","observation_id":"8035392a-2194-4b02-bf36-a4211e114b90","resolution":{"observed_at":"2026-08-07T11:00:53.728920Z","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":"2026-08-07T11:00:53.733037Z","title":"Multi-agent actor-critic for mixed cooperative-competitive environments","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.733037Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:b1c6c37efa0efbcb12af59079096ea4d289286cc6b7b317ab8b5c730fcde289a","observation_id":"d3b9fbbb-4fa9-4258-b0bb-b5516d4e5a57","resolution":{"observed_at":"2026-08-07T11:00:53.733037Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.06373","last_updated":"2024-08-08T04:47:20Z","snapshot_observed_at":"2026-08-08T17:42:09.656490Z","submitted_at":"2024-05-10T10:19:14Z","title":"LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.06373","snapshot_observed_at":"2026-08-07T11:00:53.737737Z","title":"Llm discussion: Enhancing the creativity of large language models via discussion frame- work and role-play.arXiv preprint arXiv:2405.06373, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.737737Z"},"links":{"cited_paper":"/paper/2405.06373","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:5d6f4b0e07b1c301922a476fb520aed52db3a34d0019cb88a661992c8d3d60ae","observation_id":"024b735e-ab71-4cff-a7df-b8494aac1fbd","resolution":{"observed_at":"2026-08-07T11:00:53.737737Z","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":"2026-08-07T11:00:53.742164Z","title":"Down the bot hole: Actionable insights from a one-year analysis of bot activity on twitter.First Monday, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.742164Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:cfb62b66235ecf5553800b158eb3d99b029a30d4e76361a59299aaf762a70dfd","observation_id":"6f5d3e9c-c7a8-4e0c-b505-9ba4605c0837","resolution":{"observed_at":"2026-08-07T11:00:53.742164Z","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":"2026-08-07T11:00:53.746839Z","title":"Red bots do it better: Compar- ative analysis of social bot partisan behavior","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.746839Z"},"links":{"citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:aabfaea883cf8ebbd3b94fb198148b8f86ed2b076b1cac894419aa89a7247cc8","observation_id":"9039bf6c-1009-458d-9d64-3d7e48c0798c","resolution":{"observed_at":"2026-08-07T11:00:53.746839Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08967","last_updated":"2024-12-13T04:44:11Z","snapshot_observed_at":"2026-08-05T08:09:01.340423Z","submitted_at":"2024-01-17T04:43:21Z","title":"ReFT: Reasoning with Reinforced Fine-Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08967","snapshot_observed_at":"2026-08-07T11:00:53.750838Z","title":"Reft: Reasoning with reinforced fine-tuning.arXiv preprint arXiv:2401.08967, 3, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:53.750838Z"},"links":{"cited_paper":"/paper/2401.08967","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:e32fee7f2bd6d9be66c8892786e6bdcc348a052b26597fa1cdca0619a402cecd","observation_id":"3f1138a9-c49d-4495-b9d6-6c8355ea4e03","resolution":{"observed_at":"2026-08-07T11:00:53.750838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","latest_version":3,"primary_category":"q-bio.NC","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":97,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":196},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 100 of 196 outbound references and 3 inbound Pith citation observations for arXiv:2506.06366."}