{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RPS5YBUFZXPKXBM7Z5OZU45EBV","short_pith_number":"pith:RPS5YBUF","schema_version":"1.0","canonical_sha256":"8be5dc0685cddeab859fcf5d9a73a40d4b36e3662edcf9096a2a3c692fe74b8a","source":{"kind":"arxiv","id":"2411.13934","version":1},"attestation_state":"computed","paper":{"title":"Learning to Cooperate with Humans using Generative Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Daphne Chen, Natasha Jaques, Simon S. Du, Yancheng Liang","submitted_at":"2024-11-21T08:36:17Z","abstract_excerpt":"Training agents that can coordinate zero-shot with humans is a key mission in multi-agent reinforcement learning (MARL). Current algorithms focus on training simulated human partner policies which are then used to train a Cooperator agent. The simulated human is produced either through behavior cloning over a dataset of human cooperation behavior, or by using MARL to create a population of simulated agents. However, these approaches often struggle to produce a Cooperator that can coordinate well with real humans, since the simulated humans fail to cover the diverse strategies and styles employ"},"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":"2411.13934","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T08:36:17Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"8a76023455d8820832e47475ee37591f00c4401f5bc2fff09ed225d4d68ee12d","abstract_canon_sha256":"e96adaf3e7afc47224b03e408c61785e19bd066ff52d1704c14351ce77f80e12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:39.128993Z","signature_b64":"8kl1trhy0qOuO9CACFGIIzPtvcksjqMTHcy+OqxwUEJ5POGj80GKuGzvTzGgULxjXoOhehiJjrrArnNEl8WcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8be5dc0685cddeab859fcf5d9a73a40d4b36e3662edcf9096a2a3c692fe74b8a","last_reissued_at":"2026-07-05T09:38:39.128569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:39.128569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Cooperate with Humans using Generative Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Daphne Chen, Natasha Jaques, Simon S. Du, Yancheng Liang","submitted_at":"2024-11-21T08:36:17Z","abstract_excerpt":"Training agents that can coordinate zero-shot with humans is a key mission in multi-agent reinforcement learning (MARL). Current algorithms focus on training simulated human partner policies which are then used to train a Cooperator agent. The simulated human is produced either through behavior cloning over a dataset of human cooperation behavior, or by using MARL to create a population of simulated agents. However, these approaches often struggle to produce a Cooperator that can coordinate well with real humans, since the simulated humans fail to cover the diverse strategies and styles employ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13934","kind":"arxiv","version":1},"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/2411.13934/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":"2411.13934","created_at":"2026-07-05T09:38:39.128626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13934v1","created_at":"2026-07-05T09:38:39.128626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13934","created_at":"2026-07-05T09:38:39.128626+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPS5YBUFZXPK","created_at":"2026-07-05T09:38:39.128626+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPS5YBUFZXPKXBM7","created_at":"2026-07-05T09:38:39.128626+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPS5YBUF","created_at":"2026-07-05T09:38:39.128626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.17323","citing_title":"Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPS5YBUFZXPKXBM7Z5OZU45EBV","json":"https://pith.science/pith/RPS5YBUFZXPKXBM7Z5OZU45EBV.json","graph_json":"https://pith.science/api/pith-number/RPS5YBUFZXPKXBM7Z5OZU45EBV/graph.json","events_json":"https://pith.science/api/pith-number/RPS5YBUFZXPKXBM7Z5OZU45EBV/events.json","paper":"https://pith.science/paper/RPS5YBUF"},"agent_actions":{"view_html":"https://pith.science/pith/RPS5YBUFZXPKXBM7Z5OZU45EBV","download_json":"https://pith.science/pith/RPS5YBUFZXPKXBM7Z5OZU45EBV.json","view_paper":"https://pith.science/paper/RPS5YBUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13934&json=true","fetch_graph":"https://pith.science/api/pith-number/RPS5YBUFZXPKXBM7Z5OZU45EBV/graph.json","fetch_events":"https://pith.science/api/pith-number/RPS5YBUFZXPKXBM7Z5OZU45EBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPS5YBUFZXPKXBM7Z5OZU45EBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPS5YBUFZXPKXBM7Z5OZU45EBV/action/storage_attestation","attest_author":"https://pith.science/pith/RPS5YBUFZXPKXBM7Z5OZU45EBV/action/author_attestation","sign_citation":"https://pith.science/pith/RPS5YBUFZXPKXBM7Z5OZU45EBV/action/citation_signature","submit_replication":"https://pith.science/pith/RPS5YBUFZXPKXBM7Z5OZU45EBV/action/replication_record"}},"created_at":"2026-07-05T09:38:39.128626+00:00","updated_at":"2026-07-05T09:38:39.128626+00:00"}