{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RRY34ZER6BVF3UOYRXW57NTUR6","short_pith_number":"pith:RRY34ZER","canonical_record":{"source":{"id":"2407.13734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T17:35:32Z","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"title_canon_sha256":"462271bd8cf495b4cf4ddf2a1c40de7efa10125cd09344de93db5cd6b6469857","abstract_canon_sha256":"15b8bfdb8dad70170b43f5393f0dc071ce2e4d6075e849e3de48325e5675410f"},"schema_version":"1.0"},"canonical_sha256":"8c71be6491f06a5dd1d88deddfb6748f9b33defb6bffd3ffaa2923354e61ca7e","source":{"kind":"arxiv","id":"2407.13734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13734","created_at":"2026-07-05T08:45:43Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13734v1","created_at":"2026-07-05T08:45:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13734","created_at":"2026-07-05T08:45:43Z"},{"alias_kind":"pith_short_12","alias_value":"RRY34ZER6BVF","created_at":"2026-07-05T08:45:43Z"},{"alias_kind":"pith_short_16","alias_value":"RRY34ZER6BVF3UOY","created_at":"2026-07-05T08:45:43Z"},{"alias_kind":"pith_short_8","alias_value":"RRY34ZER","created_at":"2026-07-05T08:45:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RRY34ZER6BVF3UOYRXW57NTUR6","target":"record","payload":{"canonical_record":{"source":{"id":"2407.13734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T17:35:32Z","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"title_canon_sha256":"462271bd8cf495b4cf4ddf2a1c40de7efa10125cd09344de93db5cd6b6469857","abstract_canon_sha256":"15b8bfdb8dad70170b43f5393f0dc071ce2e4d6075e849e3de48325e5675410f"},"schema_version":"1.0"},"canonical_sha256":"8c71be6491f06a5dd1d88deddfb6748f9b33defb6bffd3ffaa2923354e61ca7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:43.057978Z","signature_b64":"jqRthDBf0jH69Hhiortp6wwOXNeyfh32FjeipJAujmJEdsw7DIg0fLFAr+Oahr2rNP7czkT+UX1sYADJIze2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c71be6491f06a5dd1d88deddfb6748f9b33defb6bffd3ffaa2923354e61ca7e","last_reissued_at":"2026-07-05T08:45:43.057559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:43.057559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.13734","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qONskK9w3FFzXPAz2QQQQiehTL1KI+taElcnKy8o2ZKyANbR4acCyC6fUUnzlcUC7uDFBFDVNECAoNwMgsk8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:47:17.440730Z"},"content_sha256":"e6c3896a2fb7141b11f60ca969dc8d0848ddeec24e2bcbfa7ebbcecea4d9427a","schema_version":"1.0","event_id":"sha256:e6c3896a2fb7141b11f60ca969dc8d0848ddeec24e2bcbfa7ebbcecea4d9427a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RRY34ZER6BVF3UOYRXW57NTUR6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Masatoshi Uehara, Sergey Levine, Tommaso Biancalani, Yulai Zhao","submitted_at":"2024-07-18T17:35:32Z","abstract_excerpt":"This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. While diffusion models are widely known to provide excellent generative modeling capability, practical applications in domains such as biology require generating samples that maximize some desired metric (e.g., translation efficiency in RNA, docking score in molecules, stability in protein). In these cases, the diffusion model can be optimized not only to generate realistic samples but also to explicitly maximize the measure of interest. Such methods are based on c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13734","kind":"arxiv","version":1},"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/2407.13734/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":"2026-07-05T08:45:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TiOITFaevAYB5AtTSgDCnTKaACjLwOa+pu4vRIbq4GVMXYt2Bvg6hJ6Os9o4Abqf2Jik1J03mp9937GFcOLZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:47:17.441274Z"},"content_sha256":"36d6d43498e828ea0a5b20d0cbd0cdda5e13f3ed81ec0b48ea3bd16413f01d28","schema_version":"1.0","event_id":"sha256:36d6d43498e828ea0a5b20d0cbd0cdda5e13f3ed81ec0b48ea3bd16413f01d28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRY34ZER6BVF3UOYRXW57NTUR6/bundle.json","state_url":"https://pith.science/pith/RRY34ZER6BVF3UOYRXW57NTUR6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRY34ZER6BVF3UOYRXW57NTUR6/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":"2026-07-31T20:47:17Z","links":{"resolver":"https://pith.science/pith/RRY34ZER6BVF3UOYRXW57NTUR6","bundle":"https://pith.science/pith/RRY34ZER6BVF3UOYRXW57NTUR6/bundle.json","state":"https://pith.science/pith/RRY34ZER6BVF3UOYRXW57NTUR6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRY34ZER6BVF3UOYRXW57NTUR6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RRY34ZER6BVF3UOYRXW57NTUR6","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":"15b8bfdb8dad70170b43f5393f0dc071ce2e4d6075e849e3de48325e5675410f","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T17:35:32Z","title_canon_sha256":"462271bd8cf495b4cf4ddf2a1c40de7efa10125cd09344de93db5cd6b6469857"},"schema_version":"1.0","source":{"id":"2407.13734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13734","created_at":"2026-07-05T08:45:43Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13734v1","created_at":"2026-07-05T08:45:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13734","created_at":"2026-07-05T08:45:43Z"},{"alias_kind":"pith_short_12","alias_value":"RRY34ZER6BVF","created_at":"2026-07-05T08:45:43Z"},{"alias_kind":"pith_short_16","alias_value":"RRY34ZER6BVF3UOY","created_at":"2026-07-05T08:45:43Z"},{"alias_kind":"pith_short_8","alias_value":"RRY34ZER","created_at":"2026-07-05T08:45:43Z"}],"graph_snapshots":[{"event_id":"sha256:36d6d43498e828ea0a5b20d0cbd0cdda5e13f3ed81ec0b48ea3bd16413f01d28","target":"graph","created_at":"2026-07-05T08:45:43Z","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/2407.13734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. While diffusion models are widely known to provide excellent generative modeling capability, practical applications in domains such as biology require generating samples that maximize some desired metric (e.g., translation efficiency in RNA, docking score in molecules, stability in protein). In these cases, the diffusion model can be optimized not only to generate realistic samples but also to explicitly maximize the measure of interest. Such methods are based on c","authors_text":"Masatoshi Uehara, Sergey Levine, Tommaso Biancalani, Yulai Zhao","cross_cats":["cs.AI","q-bio.QM","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T17:35:32Z","title":"Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13734","kind":"arxiv","version":1},"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:e6c3896a2fb7141b11f60ca969dc8d0848ddeec24e2bcbfa7ebbcecea4d9427a","target":"record","created_at":"2026-07-05T08:45:43Z","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":"15b8bfdb8dad70170b43f5393f0dc071ce2e4d6075e849e3de48325e5675410f","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T17:35:32Z","title_canon_sha256":"462271bd8cf495b4cf4ddf2a1c40de7efa10125cd09344de93db5cd6b6469857"},"schema_version":"1.0","source":{"id":"2407.13734","kind":"arxiv","version":1}},"canonical_sha256":"8c71be6491f06a5dd1d88deddfb6748f9b33defb6bffd3ffaa2923354e61ca7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c71be6491f06a5dd1d88deddfb6748f9b33defb6bffd3ffaa2923354e61ca7e","first_computed_at":"2026-07-05T08:45:43.057559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:43.057559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jqRthDBf0jH69Hhiortp6wwOXNeyfh32FjeipJAujmJEdsw7DIg0fLFAr+Oahr2rNP7czkT+UX1sYADJIze2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:43.057978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6c3896a2fb7141b11f60ca969dc8d0848ddeec24e2bcbfa7ebbcecea4d9427a","sha256:36d6d43498e828ea0a5b20d0cbd0cdda5e13f3ed81ec0b48ea3bd16413f01d28"],"state_sha256":"63ddfaf69858acc1dff54aafef71b26f95c209924856b68c4d2f398744bca882"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kDJ/lj0U6PI8XSnLgZSCFBvordw08pMe6sW/h1kgFv5Dk312Q6aXw3IFwc6L77XMkfGfP+7i8E1aUCt6+1i0CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T20:47:17.445304Z","bundle_sha256":"2f7d819be2c3abc31d856e5ed60aac90e782d2f4712ab530f905100239c483b4"}}