{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RPS5YBUFZXPKXBM7Z5OZU45EBV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e96adaf3e7afc47224b03e408c61785e19bd066ff52d1704c14351ce77f80e12","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T08:36:17Z","title_canon_sha256":"8a76023455d8820832e47475ee37591f00c4401f5bc2fff09ed225d4d68ee12d"},"schema_version":"1.0","source":{"id":"2411.13934","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13934","created_at":"2026-07-05T09:38:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13934v1","created_at":"2026-07-05T09:38:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13934","created_at":"2026-07-05T09:38:39Z"},{"alias_kind":"pith_short_12","alias_value":"RPS5YBUFZXPK","created_at":"2026-07-05T09:38:39Z"},{"alias_kind":"pith_short_16","alias_value":"RPS5YBUFZXPKXBM7","created_at":"2026-07-05T09:38:39Z"},{"alias_kind":"pith_short_8","alias_value":"RPS5YBUF","created_at":"2026-07-05T09:38:39Z"}],"graph_snapshots":[{"event_id":"sha256:62f2300c6935699df4968dc9254525ea9780ec357e4e88ef3199bae8aaf7f063","target":"graph","created_at":"2026-07-05T09:38:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.13934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abhishek Gupta, Daphne Chen, Natasha Jaques, Simon S. Du, Yancheng Liang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T08:36:17Z","title":"Learning to Cooperate with Humans using Generative Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13934","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:42a6641ceb91c617292ff925129116745d3aad3909856c42370f3b20f416caba","target":"record","created_at":"2026-07-05T09:38:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e96adaf3e7afc47224b03e408c61785e19bd066ff52d1704c14351ce77f80e12","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T08:36:17Z","title_canon_sha256":"8a76023455d8820832e47475ee37591f00c4401f5bc2fff09ed225d4d68ee12d"},"schema_version":"1.0","source":{"id":"2411.13934","kind":"arxiv","version":1}},"canonical_sha256":"8be5dc0685cddeab859fcf5d9a73a40d4b36e3662edcf9096a2a3c692fe74b8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8be5dc0685cddeab859fcf5d9a73a40d4b36e3662edcf9096a2a3c692fe74b8a","first_computed_at":"2026-07-05T09:38:39.128569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:39.128569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8kl1trhy0qOuO9CACFGIIzPtvcksjqMTHcy+OqxwUEJ5POGj80GKuGzvTzGgULxjXoOhehiJjrrArnNEl8WcCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:39.128993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13934","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42a6641ceb91c617292ff925129116745d3aad3909856c42370f3b20f416caba","sha256:62f2300c6935699df4968dc9254525ea9780ec357e4e88ef3199bae8aaf7f063"],"state_sha256":"83a1f0a759e76c17479937ca53fb731048bada3829835225d99d81f33b9e6c27"}