{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RHVY7RI45PGPVFTWBOZCPVISBK","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":"9a7b42c362d55cb7fb79e2ae62a27706760da4e70729f150ead44511a727197b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-03-04T05:26:13Z","title_canon_sha256":"cf954fac60ba0ec6efc512f129cd94540e7e5bb90f9a6f39bd75fcbf2690f07a"},"schema_version":"1.0","source":{"id":"2603.03741","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.03741","created_at":"2026-06-02T02:04:15Z"},{"alias_kind":"arxiv_version","alias_value":"2603.03741v2","created_at":"2026-06-02T02:04:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03741","created_at":"2026-06-02T02:04:15Z"},{"alias_kind":"pith_short_12","alias_value":"RHVY7RI45PGP","created_at":"2026-06-02T02:04:15Z"},{"alias_kind":"pith_short_16","alias_value":"RHVY7RI45PGPVFTW","created_at":"2026-06-02T02:04:15Z"},{"alias_kind":"pith_short_8","alias_value":"RHVY7RI4","created_at":"2026-06-02T02:04:15Z"}],"graph_snapshots":[{"event_id":"sha256:f1ca155aec4129d5222a2f9fc566cc61d4cddec3986cb63681942d0cfb7f7f82","target":"graph","created_at":"2026-06-02T02:04:15Z","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/2603.03741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To improve generalization and resilience in human-robot collaboration (HRC), robots must contend with diverse combinations of human behaviors and contexts, motivating multi-agent reinforcement learning (MARL). However, inherent heterogeneity between robots and humans creates a rationality gap (RG), where decentralized policy updates deviate from cooperative joint optimization. The resulting learning problem is a general-sum differentiable game, so independent policy-gradient updates can oscillate or diverge without added structure. We propose heterogeneous-agent Lyapunov policy optimization (H","authors_text":"Ding Zhao, Hao Zhang, H. Eric Tseng, Yaru Niu, Yikai Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-03-04T05:26:13Z","title":"HALO: Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.03741","kind":"arxiv","version":2},"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:ab5779b9381f174a0adbc5eb9a316584acc102df10f9cdd9f9789d13402607de","target":"record","created_at":"2026-06-02T02:04:15Z","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":"9a7b42c362d55cb7fb79e2ae62a27706760da4e70729f150ead44511a727197b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-03-04T05:26:13Z","title_canon_sha256":"cf954fac60ba0ec6efc512f129cd94540e7e5bb90f9a6f39bd75fcbf2690f07a"},"schema_version":"1.0","source":{"id":"2603.03741","kind":"arxiv","version":2}},"canonical_sha256":"89eb8fc51cebccfa96760bb227d5120a9b075f7d8f59e109fecaf72fd5e2f95e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89eb8fc51cebccfa96760bb227d5120a9b075f7d8f59e109fecaf72fd5e2f95e","first_computed_at":"2026-06-02T02:04:15.585600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:15.585600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bEf1oEXlWZlqQmsHeiMluNCpOnnhxQ0FoducS7aoS2z51uKEMy+7y9gWsyMHNpYQGx7y8ulL8jZUTGOAm1jeBg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:15.586202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.03741","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab5779b9381f174a0adbc5eb9a316584acc102df10f9cdd9f9789d13402607de","sha256:f1ca155aec4129d5222a2f9fc566cc61d4cddec3986cb63681942d0cfb7f7f82"],"state_sha256":"3be3f569be042cf94c2ea4ad13c43713d4ac0de5f41e57ca782e4ca321057ab8"}