{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CZ7YSVUWWDLVBZOQHETDYM35NE","short_pith_number":"pith:CZ7YSVUW","canonical_record":{"source":{"id":"2409.05622","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T13:56:03Z","cross_cats_sorted":[],"title_canon_sha256":"a7b47b497a19b3f193b02147b2213480b35cb3e0a4350c664843f052ae6cba71","abstract_canon_sha256":"afc0fcf35ef514065be18ba6f2b202b2a7de6f466c96da6803e45a52d2aec5e6"},"schema_version":"1.0"},"canonical_sha256":"167f895696b0d750e5d039263c337d6903ebcf866592d46b6c50c2f95a7c9a6e","source":{"kind":"arxiv","id":"2409.05622","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05622","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05622v2","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05622","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"pith_short_12","alias_value":"CZ7YSVUWWDLV","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"pith_short_16","alias_value":"CZ7YSVUWWDLVBZOQ","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"pith_short_8","alias_value":"CZ7YSVUW","created_at":"2026-07-05T09:49:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CZ7YSVUWWDLVBZOQHETDYM35NE","target":"record","payload":{"canonical_record":{"source":{"id":"2409.05622","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T13:56:03Z","cross_cats_sorted":[],"title_canon_sha256":"a7b47b497a19b3f193b02147b2213480b35cb3e0a4350c664843f052ae6cba71","abstract_canon_sha256":"afc0fcf35ef514065be18ba6f2b202b2a7de6f466c96da6803e45a52d2aec5e6"},"schema_version":"1.0"},"canonical_sha256":"167f895696b0d750e5d039263c337d6903ebcf866592d46b6c50c2f95a7c9a6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:09.942833Z","signature_b64":"TKjUuxTDAulf90pEa0KY2MQdLIQQNz71i2H8HEXmSQVfTE7nPLyErQgTcNIXvzU24LvlBf9lUaVmdCo3r2BuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167f895696b0d750e5d039263c337d6903ebcf866592d46b6c50c2f95a7c9a6e","last_reissued_at":"2026-07-05T09:49:09.942346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:09.942346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.05622","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":"2026-07-05T09:49:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wd8YrW6a1A+l5li2WSi71CGD1FOaGwmLUgcTkomuROHUriMrvpy1HmMT5RwPRDTJHvB/vMZYjFyqfoq3jT7UBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:08:36.228644Z"},"content_sha256":"b18bfe4082e1d60b2639096658e2fb1d25fccc629ba7152fba166a0f54fb1b63","schema_version":"1.0","event_id":"sha256:b18bfe4082e1d60b2639096658e2fb1d25fccc629ba7152fba166a0f54fb1b63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CZ7YSVUWWDLVBZOQHETDYM35NE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Forward KL Regularized Preference Optimization for Aligning Diffusion Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Chenyou Fan, Jiyuan Shi, Shuang Qiu, Zhao Shan","submitted_at":"2024-09-09T13:56:03Z","abstract_excerpt":"Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with human intents in various tasks. To achieve this, previous methods conduct return-conditioned policy generation or Reinforcement Learning (RL)-based policy optimization, while they both rely on pre-defined reward functions. In this work, we propose a novel framework, Forward KL regularized Preference optimization for aligning Diffusion policies, to align the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05622","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/2409.05622/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":"2026-07-05T09:49:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5QYO9XdxZcv7tJPV3erLJUyB2MJsuJet3p1NCqpCnkWth9Zcul1sgg+bw/95Yp1xCNc9H0tiwXThHBxJF0RRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:08:36.230208Z"},"content_sha256":"1b0ef64d0e66e44df519124eb6088a0f847bca79019041c49cbea8e1b25470ec","schema_version":"1.0","event_id":"sha256:1b0ef64d0e66e44df519124eb6088a0f847bca79019041c49cbea8e1b25470ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZ7YSVUWWDLVBZOQHETDYM35NE/bundle.json","state_url":"https://pith.science/pith/CZ7YSVUWWDLVBZOQHETDYM35NE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZ7YSVUWWDLVBZOQHETDYM35NE/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":"2026-08-12T21:08:36Z","links":{"resolver":"https://pith.science/pith/CZ7YSVUWWDLVBZOQHETDYM35NE","bundle":"https://pith.science/pith/CZ7YSVUWWDLVBZOQHETDYM35NE/bundle.json","state":"https://pith.science/pith/CZ7YSVUWWDLVBZOQHETDYM35NE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZ7YSVUWWDLVBZOQHETDYM35NE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CZ7YSVUWWDLVBZOQHETDYM35NE","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":"afc0fcf35ef514065be18ba6f2b202b2a7de6f466c96da6803e45a52d2aec5e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T13:56:03Z","title_canon_sha256":"a7b47b497a19b3f193b02147b2213480b35cb3e0a4350c664843f052ae6cba71"},"schema_version":"1.0","source":{"id":"2409.05622","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05622","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05622v2","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05622","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"pith_short_12","alias_value":"CZ7YSVUWWDLV","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"pith_short_16","alias_value":"CZ7YSVUWWDLVBZOQ","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"pith_short_8","alias_value":"CZ7YSVUW","created_at":"2026-07-05T09:49:09Z"}],"graph_snapshots":[{"event_id":"sha256:1b0ef64d0e66e44df519124eb6088a0f847bca79019041c49cbea8e1b25470ec","target":"graph","created_at":"2026-07-05T09:49:09Z","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/2409.05622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with human intents in various tasks. To achieve this, previous methods conduct return-conditioned policy generation or Reinforcement Learning (RL)-based policy optimization, while they both rely on pre-defined reward functions. In this work, we propose a novel framework, Forward KL regularized Preference optimization for aligning Diffusion policies, to align the ","authors_text":"Chenjia Bai, Chenyou Fan, Jiyuan Shi, Shuang Qiu, Zhao Shan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T13:56:03Z","title":"Forward KL Regularized Preference Optimization for Aligning Diffusion Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05622","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:b18bfe4082e1d60b2639096658e2fb1d25fccc629ba7152fba166a0f54fb1b63","target":"record","created_at":"2026-07-05T09:49:09Z","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":"afc0fcf35ef514065be18ba6f2b202b2a7de6f466c96da6803e45a52d2aec5e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-09T13:56:03Z","title_canon_sha256":"a7b47b497a19b3f193b02147b2213480b35cb3e0a4350c664843f052ae6cba71"},"schema_version":"1.0","source":{"id":"2409.05622","kind":"arxiv","version":2}},"canonical_sha256":"167f895696b0d750e5d039263c337d6903ebcf866592d46b6c50c2f95a7c9a6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"167f895696b0d750e5d039263c337d6903ebcf866592d46b6c50c2f95a7c9a6e","first_computed_at":"2026-07-05T09:49:09.942346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:09.942346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TKjUuxTDAulf90pEa0KY2MQdLIQQNz71i2H8HEXmSQVfTE7nPLyErQgTcNIXvzU24LvlBf9lUaVmdCo3r2BuCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:09.942833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.05622","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b18bfe4082e1d60b2639096658e2fb1d25fccc629ba7152fba166a0f54fb1b63","sha256:1b0ef64d0e66e44df519124eb6088a0f847bca79019041c49cbea8e1b25470ec"],"state_sha256":"f2983fb9ae902513ab15868403054b0f07f8d407e9a8bea21ce50cc67cde4a8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SvL/uGrwlJX/Bg3+DZtVT9l/+6f9Zx4cDtFyJOR/0F0s6Tj4lw949vkHBLKVvP7Dii4jPwEOQXRrI1zx1IXEBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T21:08:36.243523Z","bundle_sha256":"95b69863edbde6da0ec7fb1de46815d582c3a4297f31c857a0727cdc305e1845"}}