{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZLAFCHZ7JEKPUPNKOIHG5PMCOO","short_pith_number":"pith:ZLAFCHZ7","canonical_record":{"source":{"id":"2305.16381","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T17:35:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e12813477ebfb7df2be616f1fdc3665e0c513aaa38bf104eaefe1648c294399c","abstract_canon_sha256":"cde2a1e416185a89253c16ac4968342c6bff53f878fb1fe12e0b1612b23f10d0"},"schema_version":"1.0"},"canonical_sha256":"cac0511f3f4914fa3daa720e6ebd82739efb4f737d6a4d6a9a66c91779b83191","source":{"kind":"arxiv","id":"2305.16381","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16381","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16381v3","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16381","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZLAFCHZ7JEKP","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZLAFCHZ7JEKPUPNK","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZLAFCHZ7","created_at":"2026-07-05T07:07:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZLAFCHZ7JEKPUPNKOIHG5PMCOO","target":"record","payload":{"canonical_record":{"source":{"id":"2305.16381","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T17:35:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e12813477ebfb7df2be616f1fdc3665e0c513aaa38bf104eaefe1648c294399c","abstract_canon_sha256":"cde2a1e416185a89253c16ac4968342c6bff53f878fb1fe12e0b1612b23f10d0"},"schema_version":"1.0"},"canonical_sha256":"cac0511f3f4914fa3daa720e6ebd82739efb4f737d6a4d6a9a66c91779b83191","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:37.910573Z","signature_b64":"hqaC3am/TJZA7lwOrm1OBifm+EuDaSW95oaqKMxIfWSvIB5fkzp2mkGZF6ST3+GEq0a7zNJfQ/AjMaNbF9SmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cac0511f3f4914fa3daa720e6ebd82739efb4f737d6a4d6a9a66c91779b83191","last_reissued_at":"2026-07-05T07:07:37.910070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:37.910070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.16381","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":"2026-07-05T07:07:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+uSf71zvkLneZLsoD+H6Gxepdi6qABls39dyMH5Yz72hcAiNyLlzfg7X2Wr0yN87akFLzjpRbeK2Aj6d9+CqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:17:53.930650Z"},"content_sha256":"5d645656f76e41561ff517a7d42412ad9426bba2cdca27f0e18d74b6abe83de4","schema_version":"1.0","event_id":"sha256:5d645656f76e41561ff517a7d42412ad9426bba2cdca27f0e18d74b6abe83de4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZLAFCHZ7JEKPUPNKOIHG5PMCOO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Craig Boutilier, Hao Liu, Kangwook Lee, Kimin Lee, Mohammad Ghavamzadeh, Moonkyung Ryu, Olivia Watkins, Pieter Abbeel, Ying Fan, Yuqing Du","submitted_at":"2023-05-25T17:35:38Z","abstract_excerpt":"Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and then improve the models based on the learned reward function. Even though relatively simple approaches (e.g., rejection sampling based on reward scores) have been investigated, fine-tuning text-to-image models with the reward function remains challenging. In this work, we propose using online reinforcement learning (RL) to fine-tune text-to-image models. We focus on diffusion models, defining the fine-tuning task as an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16381","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/2305.16381/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":"2026-07-05T07:07:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VbvU4/1Es6as/QLA0Y42IdNvxwCBFKgeb+xORDqW6YgML9NAW8sEumHKo0j3+EU96wvsYDnFerN5gPcDwg+rDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:17:53.931053Z"},"content_sha256":"af6606b20fe382cf46d89cad9d1d262955400c5f16707d696d5b7470a6a15492","schema_version":"1.0","event_id":"sha256:af6606b20fe382cf46d89cad9d1d262955400c5f16707d696d5b7470a6a15492"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLAFCHZ7JEKPUPNKOIHG5PMCOO/bundle.json","state_url":"https://pith.science/pith/ZLAFCHZ7JEKPUPNKOIHG5PMCOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLAFCHZ7JEKPUPNKOIHG5PMCOO/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":"2026-08-04T08:17:53Z","links":{"resolver":"https://pith.science/pith/ZLAFCHZ7JEKPUPNKOIHG5PMCOO","bundle":"https://pith.science/pith/ZLAFCHZ7JEKPUPNKOIHG5PMCOO/bundle.json","state":"https://pith.science/pith/ZLAFCHZ7JEKPUPNKOIHG5PMCOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLAFCHZ7JEKPUPNKOIHG5PMCOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZLAFCHZ7JEKPUPNKOIHG5PMCOO","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":"cde2a1e416185a89253c16ac4968342c6bff53f878fb1fe12e0b1612b23f10d0","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T17:35:38Z","title_canon_sha256":"e12813477ebfb7df2be616f1fdc3665e0c513aaa38bf104eaefe1648c294399c"},"schema_version":"1.0","source":{"id":"2305.16381","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16381","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16381v3","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16381","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZLAFCHZ7JEKP","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZLAFCHZ7JEKPUPNK","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZLAFCHZ7","created_at":"2026-07-05T07:07:37Z"}],"graph_snapshots":[{"event_id":"sha256:af6606b20fe382cf46d89cad9d1d262955400c5f16707d696d5b7470a6a15492","target":"graph","created_at":"2026-07-05T07:07:37Z","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/2305.16381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and then improve the models based on the learned reward function. Even though relatively simple approaches (e.g., rejection sampling based on reward scores) have been investigated, fine-tuning text-to-image models with the reward function remains challenging. In this work, we propose using online reinforcement learning (RL) to fine-tune text-to-image models. We focus on diffusion models, defining the fine-tuning task as an ","authors_text":"Craig Boutilier, Hao Liu, Kangwook Lee, Kimin Lee, Mohammad Ghavamzadeh, Moonkyung Ryu, Olivia Watkins, Pieter Abbeel, Ying Fan, Yuqing Du","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T17:35:38Z","title":"DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16381","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":"sha256:5d645656f76e41561ff517a7d42412ad9426bba2cdca27f0e18d74b6abe83de4","target":"record","created_at":"2026-07-05T07:07:37Z","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":"cde2a1e416185a89253c16ac4968342c6bff53f878fb1fe12e0b1612b23f10d0","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T17:35:38Z","title_canon_sha256":"e12813477ebfb7df2be616f1fdc3665e0c513aaa38bf104eaefe1648c294399c"},"schema_version":"1.0","source":{"id":"2305.16381","kind":"arxiv","version":3}},"canonical_sha256":"cac0511f3f4914fa3daa720e6ebd82739efb4f737d6a4d6a9a66c91779b83191","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cac0511f3f4914fa3daa720e6ebd82739efb4f737d6a4d6a9a66c91779b83191","first_computed_at":"2026-07-05T07:07:37.910070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:37.910070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hqaC3am/TJZA7lwOrm1OBifm+EuDaSW95oaqKMxIfWSvIB5fkzp2mkGZF6ST3+GEq0a7zNJfQ/AjMaNbF9SmBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:37.910573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16381","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d645656f76e41561ff517a7d42412ad9426bba2cdca27f0e18d74b6abe83de4","sha256:af6606b20fe382cf46d89cad9d1d262955400c5f16707d696d5b7470a6a15492"],"state_sha256":"0337e5c483c1ced59e5c129b4e0d73f49315dfa5479af7e52c235e181f0842ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmRp2lK3iKrYhu0XTdV3IXOcAXkkT9XcfZau9FQX5C2z9LPcX2SKSHokAeEU1ROxE1ZA4gtqMmIhD6xXtxSoBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:17:53.934129Z","bundle_sha256":"f07bdd2d7cfeade5224b7d2d236942af7c8133ceb17bf2daf7152a39bd9ce84c"}}