{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GKWA7NECHNTYQ7IB63JRE4NAJG","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":"c419d2a1fd7a241a824e520f3dac473a4b295a6076a37dd7dbaf9952fdb667e4","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-10-11T03:46:12Z","title_canon_sha256":"d223fd25959356edad30ffffce3d8e514cfddd5b5b7327ab47de8b45872ab33f"},"schema_version":"1.0","source":{"id":"2210.05125","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05125","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05125v1","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05125","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"GKWA7NECHNTY","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"GKWA7NECHNTYQ7IB","created_at":"2026-07-05T05:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"GKWA7NEC","created_at":"2026-07-05T05:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:05df397f3f406a946f4ed8e01e1c70873871d6816495a611561fe0c0319bc438","target":"graph","created_at":"2026-07-05T05:05:13Z","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/2210.05125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of making AI agents that collaborate well with humans in partially observable fully cooperative environments given datasets of human behavior. Inspired by piKL, a human-data-regularized search method that improves upon a behavioral cloning policy without diverging far away from it, we develop a three-step algorithm that achieve strong performance in coordinating with real humans in the Hanabi benchmark. We first use a regularized search algorithm and behavioral cloning to produce a better human model that captures diverse skill levels. Then, we integrate the policy regu","authors_text":"Adam Lerer, David J Wu, Hengyuan Hu, Jakob Foerster, Noam Brown","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-10-11T03:46:12Z","title":"Human-AI Coordination via Human-Regularized Search and Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05125","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:bd3812c300f37d91cf8523c1a29ffd62a14b12bec7e42edcdecf3180e2b1e00a","target":"record","created_at":"2026-07-05T05:05:13Z","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":"c419d2a1fd7a241a824e520f3dac473a4b295a6076a37dd7dbaf9952fdb667e4","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-10-11T03:46:12Z","title_canon_sha256":"d223fd25959356edad30ffffce3d8e514cfddd5b5b7327ab47de8b45872ab33f"},"schema_version":"1.0","source":{"id":"2210.05125","kind":"arxiv","version":1}},"canonical_sha256":"32ac0fb4823b67887d01f6d31271a049adad84d166f989e50b179a8e00467f2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32ac0fb4823b67887d01f6d31271a049adad84d166f989e50b179a8e00467f2a","first_computed_at":"2026-07-05T05:05:13.152932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:13.152932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TwiLIjWBuCyGCUWt0dveeKk+sMhpiFDCo7unrKNcltsbCA7nzLVIZSRV39I9z1HZt/YCxOy2kDDr2R+2e6+nDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:13.153387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05125","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd3812c300f37d91cf8523c1a29ffd62a14b12bec7e42edcdecf3180e2b1e00a","sha256:05df397f3f406a946f4ed8e01e1c70873871d6816495a611561fe0c0319bc438"],"state_sha256":"cb3f455a0c8775dff95da54731e8ef160994f7cdb3dc13aa48cf25c310af7f6c"}