{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T4R735ZMZIVWNXGW5FM3USCXR5","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":"698bf3bfa2e7f7c6c00b4b460361a2bd52fe4efaadae84fcb00ebc205fa39400","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T19:44:48Z","title_canon_sha256":"6782ed248ca8cedcc82aeea21890a60d0794c8cac237159ac18e8fff700ba337"},"schema_version":"1.0","source":{"id":"2506.09202","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09202","created_at":"2026-07-05T11:20:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09202v2","created_at":"2026-07-05T11:20:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09202","created_at":"2026-07-05T11:20:14Z"},{"alias_kind":"pith_short_12","alias_value":"T4R735ZMZIVW","created_at":"2026-07-05T11:20:14Z"},{"alias_kind":"pith_short_16","alias_value":"T4R735ZMZIVWNXGW","created_at":"2026-07-05T11:20:14Z"},{"alias_kind":"pith_short_8","alias_value":"T4R735ZM","created_at":"2026-07-05T11:20:14Z"}],"graph_snapshots":[{"event_id":"sha256:f566ff83f2102aa5563e2981fceed6d1d966f3191266876c0b649d6e5a65deec","target":"graph","created_at":"2026-07-05T11:20:14Z","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/2506.09202/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel task of clustering trajectories from offline reinforcement learning (RL) datasets, where each cluster center represents the policy that generated its trajectories. By leveraging the connection between the KL-divergence of offline trajectory distributions and a mixture of policy-induced distributions, we formulate a natural clustering objective. To solve this, we propose Policy-Guided K-means (PG-Kmeans) and Centroid-Attracted Autoencoder (CAAE). PG-Kmeans iteratively trains behavior cloning (BC) policies and assigns trajectories based on policy generation probabilities, wh","authors_text":"Hao Hu, Simon Shaolei Du, Xinqi Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T19:44:48Z","title":"Policy-Based Trajectory Clustering in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09202","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":"sha256:7d7a89a178405ee9574e64c3d4e3adea674623b55cdaba4614ccaa80d0e6eb06","target":"record","created_at":"2026-07-05T11:20:14Z","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":"698bf3bfa2e7f7c6c00b4b460361a2bd52fe4efaadae84fcb00ebc205fa39400","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T19:44:48Z","title_canon_sha256":"6782ed248ca8cedcc82aeea21890a60d0794c8cac237159ac18e8fff700ba337"},"schema_version":"1.0","source":{"id":"2506.09202","kind":"arxiv","version":2}},"canonical_sha256":"9f23fdf72cca2b66dcd6e959ba48578f57ce50fd9fe354ab79bf52c4288a8af2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f23fdf72cca2b66dcd6e959ba48578f57ce50fd9fe354ab79bf52c4288a8af2","first_computed_at":"2026-07-05T11:20:14.531286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:14.531286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6aWBUWenEOeUopzv3RDIYF36SVlvfArUmwTDsui9tMOygeA/s+nQUlq8kiu5hrIL4vyi+1jZKE2wu3xiHP3/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:14.531835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09202","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d7a89a178405ee9574e64c3d4e3adea674623b55cdaba4614ccaa80d0e6eb06","sha256:f566ff83f2102aa5563e2981fceed6d1d966f3191266876c0b649d6e5a65deec"],"state_sha256":"341871054957dc18c11d3542c056ebef5dc9ee2d9787140fe98b1b06f9dd93e2"}