{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2FRC2KORZXIJI5OLMMWAZMUJWR","short_pith_number":"pith:2FRC2KOR","canonical_record":{"source":{"id":"2502.12631","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T08:22:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8e6b1604a0669b8c66eeed136d01c6b5e6949ff01b58d2c9f6663e22ce28fbe","abstract_canon_sha256":"584241d41eefe90aed6b0a7f4bf2362fe33582cdb3b4613506bc377b6862d9ca"},"schema_version":"1.0"},"canonical_sha256":"d1622d29d1cdd09475cb632c0cb289b454a5c42ca20fa1d96b3226c4c135c78a","source":{"kind":"arxiv","id":"2502.12631","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2FRC2KORZXIJI5OLMMWAZMUJWR","target":"record","payload":{"canonical_record":{"source":{"id":"2502.12631","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T08:22:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8e6b1604a0669b8c66eeed136d01c6b5e6949ff01b58d2c9f6663e22ce28fbe","abstract_canon_sha256":"584241d41eefe90aed6b0a7f4bf2362fe33582cdb3b4613506bc377b6862d9ca"},"schema_version":"1.0"},"canonical_sha256":"d1622d29d1cdd09475cb632c0cb289b454a5c42ca20fa1d96b3226c4c135c78a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:54.614939Z","signature_b64":"R5nCiWRWe6/VjF21BvZdhQmF7Tvcvr3JSM9YOH1Wa224VaBXryvK4UZaK+WvIw+XHfOSuG8LG4b2n3PLENprDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1622d29d1cdd09475cb632c0cb289b454a5c42ca20fa1d96b3226c4c135c78a","last_reissued_at":"2026-07-05T10:17:54.614493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:54.614493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.12631","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOc1jQNdpOWWkVFqQVG3hstfTyPxO5yMy0gl68J5KRDv5c4SilSk+1DZsJXSL++EH5uHkRWDdR9+ylSnDkmjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T06:01:49.934817Z"},"content_sha256":"af5d57e89b78b36920877ef4f69b374709376e486637636c5caa3d25a7771d3d","schema_version":"1.0","event_id":"sha256:af5d57e89b78b36920877ef4f69b374709376e486637636c5caa3d25a7771d3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2FRC2KORZXIJI5OLMMWAZMUJWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Mingyang Sun, Pengxiang Ding, Weinan Zhang","submitted_at":"2025-02-18T08:22:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12631","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/2502.12631/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V0xT2NXC/qE9e20RT9uqiCbqFikFEh+deni7ye1gnU7cxmhC8A82/GgF3IyIgQdvNJi2qA1Pe0NGfpUynx41DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T06:01:49.935222Z"},"content_sha256":"13fce907036a5cc1d6a2b6b11ab80eb2478d3b3538796051995cb52f693085c5","schema_version":"1.0","event_id":"sha256:13fce907036a5cc1d6a2b6b11ab80eb2478d3b3538796051995cb52f693085c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2FRC2KORZXIJI5OLMMWAZMUJWR/bundle.json","state_url":"https://pith.science/pith/2FRC2KORZXIJI5OLMMWAZMUJWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2FRC2KORZXIJI5OLMMWAZMUJWR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-10T06:01:49Z","links":{"resolver":"https://pith.science/pith/2FRC2KORZXIJI5OLMMWAZMUJWR","bundle":"https://pith.science/pith/2FRC2KORZXIJI5OLMMWAZMUJWR/bundle.json","state":"https://pith.science/pith/2FRC2KORZXIJI5OLMMWAZMUJWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2FRC2KORZXIJI5OLMMWAZMUJWR/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FKVwe/HGPpoPOB94Np3qM2L2E0HgppBsZVH10tIwl+Rs+HEZs8/4+icQrBC5j/f3SVD2corRUh+Itkze2/ocDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T06:01:49.937263Z","bundle_sha256":"e068e3e4b434afd1d0952d12beedc499e8f253d02f69ac8c2ddb45d68564371d"}}