{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5QM3NCXFY75ATPYWMPEGWG536S","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":"1249a59b3c7d577e3f9af3c63ccdffd8361da26f8983c5df0cb188c948db040e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-10T03:28:18Z","title_canon_sha256":"7a2dab8510d88c9ebb900cd9dfcc323212e3a74f4e6bca953c17f57bd574a79f"},"schema_version":"1.0","source":{"id":"2509.08257","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08257","created_at":"2026-07-05T12:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08257v2","created_at":"2026-07-05T12:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08257","created_at":"2026-07-05T12:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"5QM3NCXFY75A","created_at":"2026-07-05T12:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"5QM3NCXFY75ATPYW","created_at":"2026-07-05T12:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"5QM3NCXF","created_at":"2026-07-05T12:09:24Z"}],"graph_snapshots":[{"event_id":"sha256:e5f28591083fe99d823663f7997baface9757c27f113fe538374a2955bbbc347","target":"graph","created_at":"2026-07-05T12:09:24Z","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/2509.08257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In robotic systems, the performance of reinforcement learning depends on the rationality of predefined reward functions. However, manually designed reward functions often lead to policy failures due to inaccuracies. Inverse Reinforcement Learning (IRL) addresses this problem by inferring implicit reward functions from expert demonstrations. Nevertheless, existing methods rely heavily on large amounts of expert demonstrations to accurately recover the reward function. The high cost of collecting expert demonstrations in robotic applications, particularly in multi-robot systems, severely hinders","authors_text":"Jie Luo, Wenjun Wu, Xin Yu, Yirong Qi, Yongkai Tian","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-10T03:28:18Z","title":"Symmetry-Guided Multi-Agent Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08257","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":"sha256:6e98e9278c82b8376e4da399cb46e5d4844ecc327f065880573f37382e8dc7bd","target":"record","created_at":"2026-07-05T12:09:24Z","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":"1249a59b3c7d577e3f9af3c63ccdffd8361da26f8983c5df0cb188c948db040e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-10T03:28:18Z","title_canon_sha256":"7a2dab8510d88c9ebb900cd9dfcc323212e3a74f4e6bca953c17f57bd574a79f"},"schema_version":"1.0","source":{"id":"2509.08257","kind":"arxiv","version":2}},"canonical_sha256":"ec19b68ae5c7fa09bf1663c86b1bbbf4a18dddd6f5899c90c3b0533c0fb99302","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec19b68ae5c7fa09bf1663c86b1bbbf4a18dddd6f5899c90c3b0533c0fb99302","first_computed_at":"2026-07-05T12:09:24.922845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:24.922845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GEmP5N5wkdxoLuLfQLR+PgFypMRTZzVpu+GIgfyyMT9+Ou3zXPXvPNISe+yA0ghv9fGbWAhkpJDOcoNaf4jVAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:24.923499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.08257","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e98e9278c82b8376e4da399cb46e5d4844ecc327f065880573f37382e8dc7bd","sha256:e5f28591083fe99d823663f7997baface9757c27f113fe538374a2955bbbc347"],"state_sha256":"1c9078cbf544d51e1f6b9b41c79daac5f657f749b72cd7c397af2aa293b21f8d"}