{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:36AYBKONZTR6PLT4IK37BZVXXK","short_pith_number":"pith:36AYBKON","canonical_record":{"source":{"id":"2402.16359","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T07:24:32Z","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"title_canon_sha256":"e71b82e6c73650ab0e691e5e0c3e01a9d6bd7832dce75e8d93d83055d7136127","abstract_canon_sha256":"8472ca3b161a296fa62cbe14695a481ca36d02d40fb531eeeba8d87527eabb9b"},"schema_version":"1.0"},"canonical_sha256":"df8180a9cdcce3e7ae7c42b7f0e6b7baa1eddafd903e617a4b9253075904a865","source":{"kind":"arxiv","id":"2402.16359","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16359","created_at":"2026-07-05T08:45:25Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16359v3","created_at":"2026-07-05T08:45:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16359","created_at":"2026-07-05T08:45:25Z"},{"alias_kind":"pith_short_12","alias_value":"36AYBKONZTR6","created_at":"2026-07-05T08:45:25Z"},{"alias_kind":"pith_short_16","alias_value":"36AYBKONZTR6PLT4","created_at":"2026-07-05T08:45:25Z"},{"alias_kind":"pith_short_8","alias_value":"36AYBKON","created_at":"2026-07-05T08:45:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:36AYBKONZTR6PLT4IK37BZVXXK","target":"record","payload":{"canonical_record":{"source":{"id":"2402.16359","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T07:24:32Z","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"title_canon_sha256":"e71b82e6c73650ab0e691e5e0c3e01a9d6bd7832dce75e8d93d83055d7136127","abstract_canon_sha256":"8472ca3b161a296fa62cbe14695a481ca36d02d40fb531eeeba8d87527eabb9b"},"schema_version":"1.0"},"canonical_sha256":"df8180a9cdcce3e7ae7c42b7f0e6b7baa1eddafd903e617a4b9253075904a865","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:25.503395Z","signature_b64":"PKA/v8GmhXrfNxjb3s0LYtngdtixdKYMX5TqhUEyXGod0vaShVDyGvb9evpr4N0YnefrtJRnIlhTSbaO3KN/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df8180a9cdcce3e7ae7c42b7f0e6b7baa1eddafd903e617a4b9253075904a865","last_reissued_at":"2026-07-05T08:45:25.502901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:25.502901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.16359","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Pk5+0o1e2nXocD8kMn3DMEBQ6WN9xocnQ//EWvZ+6pWfM5W2ymaEFMD9yrQXB9dYWTqhq0vPZGCKyG25lBcDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:08:20.766297Z"},"content_sha256":"effeeb43d8745331c42b314e6fb1dfdf1ebe2f8f2e541e402d28390bce8d23eb","schema_version":"1.0","event_id":"sha256:effeeb43d8745331c42b314e6fb1dfdf1ebe2f8f2e541e402d28390bce8d23eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:36AYBKONZTR6PLT4IK37BZVXXK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Feedback Efficient Online Fine-Tuning of Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex M Tseng, Ehsan Hajiramezanali, Gabriele Scalia, Kevin Black, Masatoshi Uehara, Nathaniel Lee Diamant, Sergey Levine, Tommaso Biancalani, Yulai Zhao","submitted_at":"2024-02-26T07:24:32Z","abstract_excerpt":"Diffusion models excel at modeling complex data distributions, including those of images, proteins, and small molecules. However, in many cases, our goal is to model parts of the distribution that maximize certain properties: for example, we may want to generate images with high aesthetic quality, or molecules with high bioactivity. It is natural to frame this as a reinforcement learning (RL) problem, in which the objective is to fine-tune a diffusion model to maximize a reward function that corresponds to some property. Even with access to online queries of the ground-truth reward function, e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16359","kind":"arxiv","version":3},"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/2402.16359/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":"2026-07-05T08:45:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"glkx+8nVPsNaaPB6AuTbBn682ZbLwubw0i/83d7bY4xlbUFz8W/Mw31fCCHLV8Z5FkUArlM2/fvI0ijljTXWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:08:20.766981Z"},"content_sha256":"77b9c54d3f05e0b03e63588328fdd11674a6f531e7911ad6b3f8dbcfd86d43c0","schema_version":"1.0","event_id":"sha256:77b9c54d3f05e0b03e63588328fdd11674a6f531e7911ad6b3f8dbcfd86d43c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36AYBKONZTR6PLT4IK37BZVXXK/bundle.json","state_url":"https://pith.science/pith/36AYBKONZTR6PLT4IK37BZVXXK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36AYBKONZTR6PLT4IK37BZVXXK/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":"2026-08-13T11:08:20Z","links":{"resolver":"https://pith.science/pith/36AYBKONZTR6PLT4IK37BZVXXK","bundle":"https://pith.science/pith/36AYBKONZTR6PLT4IK37BZVXXK/bundle.json","state":"https://pith.science/pith/36AYBKONZTR6PLT4IK37BZVXXK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36AYBKONZTR6PLT4IK37BZVXXK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:36AYBKONZTR6PLT4IK37BZVXXK","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":"8472ca3b161a296fa62cbe14695a481ca36d02d40fb531eeeba8d87527eabb9b","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T07:24:32Z","title_canon_sha256":"e71b82e6c73650ab0e691e5e0c3e01a9d6bd7832dce75e8d93d83055d7136127"},"schema_version":"1.0","source":{"id":"2402.16359","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16359","created_at":"2026-07-05T08:45:25Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16359v3","created_at":"2026-07-05T08:45:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16359","created_at":"2026-07-05T08:45:25Z"},{"alias_kind":"pith_short_12","alias_value":"36AYBKONZTR6","created_at":"2026-07-05T08:45:25Z"},{"alias_kind":"pith_short_16","alias_value":"36AYBKONZTR6PLT4","created_at":"2026-07-05T08:45:25Z"},{"alias_kind":"pith_short_8","alias_value":"36AYBKON","created_at":"2026-07-05T08:45:25Z"}],"graph_snapshots":[{"event_id":"sha256:77b9c54d3f05e0b03e63588328fdd11674a6f531e7911ad6b3f8dbcfd86d43c0","target":"graph","created_at":"2026-07-05T08:45:25Z","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/2402.16359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models excel at modeling complex data distributions, including those of images, proteins, and small molecules. However, in many cases, our goal is to model parts of the distribution that maximize certain properties: for example, we may want to generate images with high aesthetic quality, or molecules with high bioactivity. It is natural to frame this as a reinforcement learning (RL) problem, in which the objective is to fine-tune a diffusion model to maximize a reward function that corresponds to some property. Even with access to online queries of the ground-truth reward function, e","authors_text":"Alex M Tseng, Ehsan Hajiramezanali, Gabriele Scalia, Kevin Black, Masatoshi Uehara, Nathaniel Lee Diamant, 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":"2024-02-26T07:24:32Z","title":"Feedback Efficient Online Fine-Tuning of Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16359","kind":"arxiv","version":3},"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:effeeb43d8745331c42b314e6fb1dfdf1ebe2f8f2e541e402d28390bce8d23eb","target":"record","created_at":"2026-07-05T08:45:25Z","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":"8472ca3b161a296fa62cbe14695a481ca36d02d40fb531eeeba8d87527eabb9b","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T07:24:32Z","title_canon_sha256":"e71b82e6c73650ab0e691e5e0c3e01a9d6bd7832dce75e8d93d83055d7136127"},"schema_version":"1.0","source":{"id":"2402.16359","kind":"arxiv","version":3}},"canonical_sha256":"df8180a9cdcce3e7ae7c42b7f0e6b7baa1eddafd903e617a4b9253075904a865","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df8180a9cdcce3e7ae7c42b7f0e6b7baa1eddafd903e617a4b9253075904a865","first_computed_at":"2026-07-05T08:45:25.502901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:25.502901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PKA/v8GmhXrfNxjb3s0LYtngdtixdKYMX5TqhUEyXGod0vaShVDyGvb9evpr4N0YnefrtJRnIlhTSbaO3KN/Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:25.503395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16359","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:effeeb43d8745331c42b314e6fb1dfdf1ebe2f8f2e541e402d28390bce8d23eb","sha256:77b9c54d3f05e0b03e63588328fdd11674a6f531e7911ad6b3f8dbcfd86d43c0"],"state_sha256":"803062efe7158989f64d7d3ed82398dda8071d6a8b032221dff34a667829ef77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mOUvmWQbU9C/MudYQktj6bqyeaAllepEryJGTGPencGh7dvfw8XhscPFCbU6TO50HUiOPT1A3VEEV76hbdp0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T11:08:20.780083Z","bundle_sha256":"07bcdf7e2fa0cdcecc03036f4392405d9dcb2c3585930c8f98e9127ac645a350"}}