{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2FRC2KORZXIJI5OLMMWAZMUJWR","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":"584241d41eefe90aed6b0a7f4bf2362fe33582cdb3b4613506bc377b6862d9ca","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T08:22:20Z","title_canon_sha256":"d8e6b1604a0669b8c66eeed136d01c6b5e6949ff01b58d2c9f6663e22ce28fbe"},"schema_version":"1.0","source":{"id":"2502.12631","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12631","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12631v2","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12631","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"2FRC2KORZXIJ","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"2FRC2KORZXIJI5OL","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"2FRC2KOR","created_at":"2026-07-05T10:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:13fce907036a5cc1d6a2b6b11ab80eb2478d3b3538796051995cb52f693085c5","target":"graph","created_at":"2026-07-05T10:17:54Z","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/2502.12631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion policies have shown promise in learning complex behaviors from demonstrations, particularly for tasks requiring precise control and long-term planning. However, they face challenges in robustness when encountering distribution shifts. This paper explores improving diffusion-based imitation learning models through online interactions with the environment. We propose OTPR (Optimal Transport-guided score-based diffusion Policy for Reinforcement learning fine-tuning), a novel method that integrates diffusion policies with RL using optimal transport theory. OTPR leverages the Q-function a","authors_text":"Donglin Wang, Mingyang Sun, Pengxiang Ding, Weinan Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T08:22:20Z","title":"Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12631","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:af5d57e89b78b36920877ef4f69b374709376e486637636c5caa3d25a7771d3d","target":"record","created_at":"2026-07-05T10:17:54Z","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":"584241d41eefe90aed6b0a7f4bf2362fe33582cdb3b4613506bc377b6862d9ca","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T08:22:20Z","title_canon_sha256":"d8e6b1604a0669b8c66eeed136d01c6b5e6949ff01b58d2c9f6663e22ce28fbe"},"schema_version":"1.0","source":{"id":"2502.12631","kind":"arxiv","version":2}},"canonical_sha256":"d1622d29d1cdd09475cb632c0cb289b454a5c42ca20fa1d96b3226c4c135c78a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1622d29d1cdd09475cb632c0cb289b454a5c42ca20fa1d96b3226c4c135c78a","first_computed_at":"2026-07-05T10:17:54.614493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:54.614493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R5nCiWRWe6/VjF21BvZdhQmF7Tvcvr3JSM9YOH1Wa224VaBXryvK4UZaK+WvIw+XHfOSuG8LG4b2n3PLENprDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:54.614939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12631","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af5d57e89b78b36920877ef4f69b374709376e486637636c5caa3d25a7771d3d","sha256:13fce907036a5cc1d6a2b6b11ab80eb2478d3b3538796051995cb52f693085c5"],"state_sha256":"a79295dbe7a064ad81a86723dc6ff11a215d0ac0065e890095a9d7763db924fc"}