{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OYZ4V7KXCBA22QZE3WGPVOLCRN","short_pith_number":"pith:OYZ4V7KX","schema_version":"1.0","canonical_sha256":"7633cafd571041ad4324dd8cfab9628b65408a43f86af1739b7a393f6575ee23","source":{"kind":"arxiv","id":"2108.06038","version":2},"attestation_state":"computed","paper":{"title":"Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chen Wang, C. Karen Liu, Claudia P\\'erez-D'Arpino, Danfei Xu, Li Fei-Fei, Silvio Savarese","submitted_at":"2021-08-13T03:14:43Z","abstract_excerpt":"We present a method for learning a human-robot collaboration policy from human-human collaboration demonstrations. An effective robot assistant must learn to handle diverse human behaviors shown in the demonstrations and be robust when the humans adjust their strategies during online task execution. Our method co-optimizes a human policy and a robot policy in an interactive learning process: the human policy learns to generate diverse and plausible collaborative behaviors from demonstrations while the robot policy learns to assist by estimating the unobserved latent strategy of its human colla"},"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":"2108.06038","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-08-13T03:14:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9b942128e8754a7dd08dd4144e078a36cfe5196ed278fa3b88984f7e7d07ce6e","abstract_canon_sha256":"845808404bf7766b8a13b10f8c78875f6ada55ed7c81091347efa60819a9a371"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:18.787259Z","signature_b64":"k5D6UlXKiRTpArR37qXhuTmwtHZ0cqSnJ9Wh7I1ITzcfWOsSCMAEj+Ges+ui+brygCELgl52GQlACUpIOphUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7633cafd571041ad4324dd8cfab9628b65408a43f86af1739b7a393f6575ee23","last_reissued_at":"2026-07-05T06:52:18.786787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:18.786787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chen Wang, C. Karen Liu, Claudia P\\'erez-D'Arpino, Danfei Xu, Li Fei-Fei, Silvio Savarese","submitted_at":"2021-08-13T03:14:43Z","abstract_excerpt":"We present a method for learning a human-robot collaboration policy from human-human collaboration demonstrations. An effective robot assistant must learn to handle diverse human behaviors shown in the demonstrations and be robust when the humans adjust their strategies during online task execution. Our method co-optimizes a human policy and a robot policy in an interactive learning process: the human policy learns to generate diverse and plausible collaborative behaviors from demonstrations while the robot policy learns to assist by estimating the unobserved latent strategy of its human colla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.06038","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/2108.06038/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":"2108.06038","created_at":"2026-07-05T06:52:18.786844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.06038v2","created_at":"2026-07-05T06:52:18.786844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.06038","created_at":"2026-07-05T06:52:18.786844+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYZ4V7KXCBA2","created_at":"2026-07-05T06:52:18.786844+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYZ4V7KXCBA22QZE","created_at":"2026-07-05T06:52:18.786844+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYZ4V7KX","created_at":"2026-07-05T06:52:18.786844+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.28197","citing_title":"OmniRobotHome: A Multi-Camera Platform for Real-Time Multiadic Human-Robot Interaction","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYZ4V7KXCBA22QZE3WGPVOLCRN","json":"https://pith.science/pith/OYZ4V7KXCBA22QZE3WGPVOLCRN.json","graph_json":"https://pith.science/api/pith-number/OYZ4V7KXCBA22QZE3WGPVOLCRN/graph.json","events_json":"https://pith.science/api/pith-number/OYZ4V7KXCBA22QZE3WGPVOLCRN/events.json","paper":"https://pith.science/paper/OYZ4V7KX"},"agent_actions":{"view_html":"https://pith.science/pith/OYZ4V7KXCBA22QZE3WGPVOLCRN","download_json":"https://pith.science/pith/OYZ4V7KXCBA22QZE3WGPVOLCRN.json","view_paper":"https://pith.science/paper/OYZ4V7KX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.06038&json=true","fetch_graph":"https://pith.science/api/pith-number/OYZ4V7KXCBA22QZE3WGPVOLCRN/graph.json","fetch_events":"https://pith.science/api/pith-number/OYZ4V7KXCBA22QZE3WGPVOLCRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYZ4V7KXCBA22QZE3WGPVOLCRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYZ4V7KXCBA22QZE3WGPVOLCRN/action/storage_attestation","attest_author":"https://pith.science/pith/OYZ4V7KXCBA22QZE3WGPVOLCRN/action/author_attestation","sign_citation":"https://pith.science/pith/OYZ4V7KXCBA22QZE3WGPVOLCRN/action/citation_signature","submit_replication":"https://pith.science/pith/OYZ4V7KXCBA22QZE3WGPVOLCRN/action/replication_record"}},"created_at":"2026-07-05T06:52:18.786844+00:00","updated_at":"2026-07-05T06:52:18.786844+00:00"}