{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7HC6Q5BGGK4HIB7A6FOG6SC5EK","short_pith_number":"pith:7HC6Q5BG","schema_version":"1.0","canonical_sha256":"f9c5e8742632b87407e0f15c6f485d22974cf4b26a7ad37b809f12f38ac863c0","source":{"kind":"arxiv","id":"1910.05789","version":2},"attestation_state":"computed","paper":{"title":"On the Utility of Learning about Humans for Human-AI Coordination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anca Dragan, Mark K. Ho, Micah Carroll, Pieter Abbeel, Rohin Shah, Sanjit A. Seshia, Thomas L. Griffiths","submitted_at":"2019-10-13T17:17:52Z","abstract_excerpt":"While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to them can converge to coordination protocols that fail to understand and be understood by humans. To demonstrate this, we introduce a simple environment that requires challenging coordination, based on the popular game Overcooked, and learn a simple model that mimics human play. We evaluate the performance of agents trained via self-play and population-based t"},"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":"1910.05789","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-13T17:17:52Z","cross_cats_sorted":["cs.AI","cs.HC","stat.ML"],"title_canon_sha256":"7424e222641bf20135dfe1f337225172f0640262629270e22bcae3e5da4f7d28","abstract_canon_sha256":"5e52a7d1f58442a9a505afed1bed52d49f206a6a88f3f01cc3af65f0f4546301"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:32:22.312457Z","signature_b64":"XnJtTkBILRy5ruY1towIBYwBqE8rYAI5R2nM6vdTqr85E0B6Zv+FNy5X/rK+JXy0fvIB5gQtGixE5Ct+/DqIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9c5e8742632b87407e0f15c6f485d22974cf4b26a7ad37b809f12f38ac863c0","last_reissued_at":"2026-07-05T00:32:22.311986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:32:22.311986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Utility of Learning about Humans for Human-AI Coordination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anca Dragan, Mark K. Ho, Micah Carroll, Pieter Abbeel, Rohin Shah, Sanjit A. Seshia, Thomas L. Griffiths","submitted_at":"2019-10-13T17:17:52Z","abstract_excerpt":"While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to them can converge to coordination protocols that fail to understand and be understood by humans. To demonstrate this, we introduce a simple environment that requires challenging coordination, based on the popular game Overcooked, and learn a simple model that mimics human play. We evaluate the performance of agents trained via self-play and population-based t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05789","kind":"arxiv","version":2},"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/1910.05789/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":"1910.05789","created_at":"2026-07-05T00:32:22.312045+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.05789v2","created_at":"2026-07-05T00:32:22.312045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05789","created_at":"2026-07-05T00:32:22.312045+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HC6Q5BGGK4H","created_at":"2026-07-05T00:32:22.312045+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HC6Q5BGGK4HIB7A","created_at":"2026-07-05T00:32:22.312045+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HC6Q5BG","created_at":"2026-07-05T00:32:22.312045+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09826","citing_title":"EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09826","citing_title":"EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18123","citing_title":"ConventionPlay: Capability-Limited Training for Robust Ad-Hoc Collaboration","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7HC6Q5BGGK4HIB7A6FOG6SC5EK","json":"https://pith.science/pith/7HC6Q5BGGK4HIB7A6FOG6SC5EK.json","graph_json":"https://pith.science/api/pith-number/7HC6Q5BGGK4HIB7A6FOG6SC5EK/graph.json","events_json":"https://pith.science/api/pith-number/7HC6Q5BGGK4HIB7A6FOG6SC5EK/events.json","paper":"https://pith.science/paper/7HC6Q5BG"},"agent_actions":{"view_html":"https://pith.science/pith/7HC6Q5BGGK4HIB7A6FOG6SC5EK","download_json":"https://pith.science/pith/7HC6Q5BGGK4HIB7A6FOG6SC5EK.json","view_paper":"https://pith.science/paper/7HC6Q5BG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.05789&json=true","fetch_graph":"https://pith.science/api/pith-number/7HC6Q5BGGK4HIB7A6FOG6SC5EK/graph.json","fetch_events":"https://pith.science/api/pith-number/7HC6Q5BGGK4HIB7A6FOG6SC5EK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HC6Q5BGGK4HIB7A6FOG6SC5EK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HC6Q5BGGK4HIB7A6FOG6SC5EK/action/storage_attestation","attest_author":"https://pith.science/pith/7HC6Q5BGGK4HIB7A6FOG6SC5EK/action/author_attestation","sign_citation":"https://pith.science/pith/7HC6Q5BGGK4HIB7A6FOG6SC5EK/action/citation_signature","submit_replication":"https://pith.science/pith/7HC6Q5BGGK4HIB7A6FOG6SC5EK/action/replication_record"}},"created_at":"2026-07-05T00:32:22.312045+00:00","updated_at":"2026-07-05T00:32:22.312045+00:00"}