{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LQQJDZVFEK26H6M6LDLR2HLUYL","short_pith_number":"pith:LQQJDZVF","schema_version":"1.0","canonical_sha256":"5c2091e6a522b5e3f99e58d71d1d74c2c950ae5d792aa73b3299381e35914d9c","source":{"kind":"arxiv","id":"2511.04500","version":3},"attestation_state":"computed","paper":{"title":"Large language models replicate and predict human cooperation across experiments in game theory","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.GT","cs.MA"],"primary_cat":"cs.AI","authors_text":"Ana S. Cardenal, Andrea Cera Palatsi, Max Pellert, Samuel Martin-Gutierrez","submitted_at":"2025-11-06T16:21:27Z","abstract_excerpt":"Large language models (LLMs) are increasingly deployed as decision-making agents in high-stakes domains and as imitators of human behavior in the social and behavioral sciences. Yet how closely LLMs mirror human decision-making remains poorly understood. This gap is critical: misalignment could produce harmful outcomes in practice, while failure to replicate human behavior renders LLMs ineffective as social simulators. Here, we address this gap by replicating large-scale game-theoretic experiments and by introducing a systematic prompting and probing framework for machine-behavioral evaluation"},"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":"2511.04500","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-11-06T16:21:27Z","cross_cats_sorted":["cs.CL","cs.GT","cs.MA"],"title_canon_sha256":"e5a50a090a246a2712cd1857bd556caecb4e6c4faeef67c80f1b11f822413310","abstract_canon_sha256":"41e0b4909724be839d56135b802b1acfa4966e47b1c4e9e21895dc4f910cf9c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:25.993609Z","signature_b64":"PQkYzfCTfPKKVWC5KD7Kt2ZA2Q7ZRl708YWKOuwOVTCdigvg8Ppjek3K6IU5YDofCguJN1aFqrb+SLHzZ3cDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c2091e6a522b5e3f99e58d71d1d74c2c950ae5d792aa73b3299381e35914d9c","last_reissued_at":"2026-07-02T00:18:25.993052Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:25.993052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large language models replicate and predict human cooperation across experiments in game theory","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.GT","cs.MA"],"primary_cat":"cs.AI","authors_text":"Ana S. Cardenal, Andrea Cera Palatsi, Max Pellert, Samuel Martin-Gutierrez","submitted_at":"2025-11-06T16:21:27Z","abstract_excerpt":"Large language models (LLMs) are increasingly deployed as decision-making agents in high-stakes domains and as imitators of human behavior in the social and behavioral sciences. Yet how closely LLMs mirror human decision-making remains poorly understood. This gap is critical: misalignment could produce harmful outcomes in practice, while failure to replicate human behavior renders LLMs ineffective as social simulators. Here, we address this gap by replicating large-scale game-theoretic experiments and by introducing a systematic prompting and probing framework for machine-behavioral evaluation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.04500","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/2511.04500/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":"2511.04500","created_at":"2026-07-02T00:18:25.993113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.04500v3","created_at":"2026-07-02T00:18:25.993113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.04500","created_at":"2026-07-02T00:18:25.993113+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQQJDZVFEK26","created_at":"2026-07-02T00:18:25.993113+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQQJDZVFEK26H6M6","created_at":"2026-07-02T00:18:25.993113+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQQJDZVF","created_at":"2026-07-02T00:18:25.993113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18596","citing_title":"Large language models converge on competitive rationality but diverge on cooperation across providers and generations","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQQJDZVFEK26H6M6LDLR2HLUYL","json":"https://pith.science/pith/LQQJDZVFEK26H6M6LDLR2HLUYL.json","graph_json":"https://pith.science/api/pith-number/LQQJDZVFEK26H6M6LDLR2HLUYL/graph.json","events_json":"https://pith.science/api/pith-number/LQQJDZVFEK26H6M6LDLR2HLUYL/events.json","paper":"https://pith.science/paper/LQQJDZVF"},"agent_actions":{"view_html":"https://pith.science/pith/LQQJDZVFEK26H6M6LDLR2HLUYL","download_json":"https://pith.science/pith/LQQJDZVFEK26H6M6LDLR2HLUYL.json","view_paper":"https://pith.science/paper/LQQJDZVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.04500&json=true","fetch_graph":"https://pith.science/api/pith-number/LQQJDZVFEK26H6M6LDLR2HLUYL/graph.json","fetch_events":"https://pith.science/api/pith-number/LQQJDZVFEK26H6M6LDLR2HLUYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQQJDZVFEK26H6M6LDLR2HLUYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQQJDZVFEK26H6M6LDLR2HLUYL/action/storage_attestation","attest_author":"https://pith.science/pith/LQQJDZVFEK26H6M6LDLR2HLUYL/action/author_attestation","sign_citation":"https://pith.science/pith/LQQJDZVFEK26H6M6LDLR2HLUYL/action/citation_signature","submit_replication":"https://pith.science/pith/LQQJDZVFEK26H6M6LDLR2HLUYL/action/replication_record"}},"created_at":"2026-07-02T00:18:25.993113+00:00","updated_at":"2026-07-02T00:18:25.993113+00:00"}