{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WMG3QMJZBHSJPBCDGDEBYYBXLR","short_pith_number":"pith:WMG3QMJZ","schema_version":"1.0","canonical_sha256":"b30db8313909e497844330c81c60375c4e459ffbcf0bfcf8bc3b07b2822601a7","source":{"kind":"arxiv","id":"2410.10398","version":3},"attestation_state":"computed","paper":{"title":"Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CE","authors_text":"Canyu Chen, Chengxing Xie, Guohao Li, Hao Liu, Philip Torr, Songjia Liu, Yu Lei, Zhen Wu, Zhiyu Yin","submitted_at":"2024-10-14T11:39:05Z","abstract_excerpt":"As large language models (LLMs) increasingly engage in complex social interactions, ensuring that their behaviors align with human ethical principles and intentions, known as value alignment, has become a critical scientific challenge. Existing benchmarks often rely on static assessments and fail to capture the longitudinal dynamics of decision-making or the latent cognitive processes driving agent behavior. In this work, we propose FairMindSim, a realistic simulation benchmark rooted in social psychology that evaluates alignment through continuous economic games. To move beyond black-box obse"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.10398","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-10-14T11:39:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f07dcd373a95b369d9c836a99ed63077dfd10e9875b0b054848770628305a7e0","abstract_canon_sha256":"cbcb7b9cf0d93393328ef3262cd79b120dd6075fff21f931d7ae07c8dc8045ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:12.216471Z","signature_b64":"KCIjnpyQ6+qA7hX/bAUOHspuMGaf+RkQOkoD41/cnc+3W5MWkVCdjc4vtx7jKYGs3aNal/D94WYY2uupnACaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b30db8313909e497844330c81c60375c4e459ffbcf0bfcf8bc3b07b2822601a7","last_reissued_at":"2026-05-29T00:04:12.215573Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:12.215573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CE","authors_text":"Canyu Chen, Chengxing Xie, Guohao Li, Hao Liu, Philip Torr, Songjia Liu, Yu Lei, Zhen Wu, Zhiyu Yin","submitted_at":"2024-10-14T11:39:05Z","abstract_excerpt":"As large language models (LLMs) increasingly engage in complex social interactions, ensuring that their behaviors align with human ethical principles and intentions, known as value alignment, has become a critical scientific challenge. Existing benchmarks often rely on static assessments and fail to capture the longitudinal dynamics of decision-making or the latent cognitive processes driving agent behavior. In this work, we propose FairMindSim, a realistic simulation benchmark rooted in social psychology that evaluates alignment through continuous economic games. To move beyond black-box obse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10398","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.10398/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.10398","created_at":"2026-05-29T00:04:12.215703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10398v3","created_at":"2026-05-29T00:04:12.215703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10398","created_at":"2026-05-29T00:04:12.215703+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMG3QMJZBHSJ","created_at":"2026-05-29T00:04:12.215703+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMG3QMJZBHSJPBCD","created_at":"2026-05-29T00:04:12.215703+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMG3QMJZ","created_at":"2026-05-29T00:04:12.215703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMG3QMJZBHSJPBCDGDEBYYBXLR","json":"https://pith.science/pith/WMG3QMJZBHSJPBCDGDEBYYBXLR.json","graph_json":"https://pith.science/api/pith-number/WMG3QMJZBHSJPBCDGDEBYYBXLR/graph.json","events_json":"https://pith.science/api/pith-number/WMG3QMJZBHSJPBCDGDEBYYBXLR/events.json","paper":"https://pith.science/paper/WMG3QMJZ"},"agent_actions":{"view_html":"https://pith.science/pith/WMG3QMJZBHSJPBCDGDEBYYBXLR","download_json":"https://pith.science/pith/WMG3QMJZBHSJPBCDGDEBYYBXLR.json","view_paper":"https://pith.science/paper/WMG3QMJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10398&json=true","fetch_graph":"https://pith.science/api/pith-number/WMG3QMJZBHSJPBCDGDEBYYBXLR/graph.json","fetch_events":"https://pith.science/api/pith-number/WMG3QMJZBHSJPBCDGDEBYYBXLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMG3QMJZBHSJPBCDGDEBYYBXLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMG3QMJZBHSJPBCDGDEBYYBXLR/action/storage_attestation","attest_author":"https://pith.science/pith/WMG3QMJZBHSJPBCDGDEBYYBXLR/action/author_attestation","sign_citation":"https://pith.science/pith/WMG3QMJZBHSJPBCDGDEBYYBXLR/action/citation_signature","submit_replication":"https://pith.science/pith/WMG3QMJZBHSJPBCDGDEBYYBXLR/action/replication_record"}},"created_at":"2026-05-29T00:04:12.215703+00:00","updated_at":"2026-05-29T00:04:12.215703+00:00"}