{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QZNDROGDYGBSTQN6NMFPEMAQAU","short_pith_number":"pith:QZNDROGD","canonical_record":{"source":{"id":"2311.12908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T15:24:05Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"0c48f642bd5cc2c59586651ce93c7e2aab0bfe119c32665bbf87a077ec140ce5","abstract_canon_sha256":"75e56cfefa7d9e84b624200cb77effc4b60bb4c3e3c532fff5bc9420194523f1"},"schema_version":"1.0"},"canonical_sha256":"865a38b8c3c18329c1be6b0af23010053bbcf4365d0b3969a1700a9d44c73db3","source":{"kind":"arxiv","id":"2311.12908","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.12908","created_at":"2026-07-05T07:15:20Z"},{"alias_kind":"arxiv_version","alias_value":"2311.12908v1","created_at":"2026-07-05T07:15:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12908","created_at":"2026-07-05T07:15:20Z"},{"alias_kind":"pith_short_12","alias_value":"QZNDROGDYGBS","created_at":"2026-07-05T07:15:20Z"},{"alias_kind":"pith_short_16","alias_value":"QZNDROGDYGBSTQN6","created_at":"2026-07-05T07:15:20Z"},{"alias_kind":"pith_short_8","alias_value":"QZNDROGD","created_at":"2026-07-05T07:15:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QZNDROGDYGBSTQN6NMFPEMAQAU","target":"record","payload":{"canonical_record":{"source":{"id":"2311.12908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T15:24:05Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"0c48f642bd5cc2c59586651ce93c7e2aab0bfe119c32665bbf87a077ec140ce5","abstract_canon_sha256":"75e56cfefa7d9e84b624200cb77effc4b60bb4c3e3c532fff5bc9420194523f1"},"schema_version":"1.0"},"canonical_sha256":"865a38b8c3c18329c1be6b0af23010053bbcf4365d0b3969a1700a9d44c73db3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:20.424730Z","signature_b64":"nDDiYCrhMo0agPGH5FfyGJuir2nSWp1UxWhwDKLBt2KmLgFIi4VYNwTFrVRRSQokIGXfiorW2vA6a6h2mI5yCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"865a38b8c3c18329c1be6b0af23010053bbcf4365d0b3969a1700a9d44c73db3","last_reissued_at":"2026-07-05T07:15:20.424204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:20.424204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.12908","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":"2026-07-05T07:15:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/GwT8A4w86h4ErtCQGXbGvbyKmtb0bVUHdLzUXvi5ejlxs0TIUE9jC1VAbWFMweQHNvZVFYJfH41tkCyWwGuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:36:48.888582Z"},"content_sha256":"316f6ebb5f3c46d12e67c9d36adf49805b711c5a091c4e9dbf77389c1709bd75","schema_version":"1.0","event_id":"sha256:316f6ebb5f3c46d12e67c9d36adf49805b711c5a091c4e9dbf77389c1709bd75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QZNDROGDYGBSTQN6NMFPEMAQAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion Model Alignment Using Direct Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron Lou, Bram Wallace, Caiming Xiong, Linqi Zhou, Meihua Dang, Nikhil Naik, Rafael Rafailov, Senthil Purushwalkam, Shafiq Joty, Stefano Ermon","submitted_at":"2023-11-21T15:24:05Z","abstract_excerpt":"Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has not been widely explored in text-to-image diffusion models; the best existing approach is to fine-tune a pretrained model using carefully curated high quality images and captions to improve visual appeal and text alignment. We propose Diffusion-DPO, a method to align diffusion models to human preferences by directly optimizing on human comparison data. Diffus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12908","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/2311.12908/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":"2026-07-05T07:15:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZEgBEOi0OBPUn3A3xx9j3YVwkvCMIUJHUSizBzuOgbtTRPlnGoiWXkGVruA0wpECZ+uiFRs5SQN+bUu7t9eFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:36:48.889606Z"},"content_sha256":"2dd8ad5a091e42d1d983290586860a508c486d2de8b3362eff1164c5cb48eed1","schema_version":"1.0","event_id":"sha256:2dd8ad5a091e42d1d983290586860a508c486d2de8b3362eff1164c5cb48eed1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QZNDROGDYGBSTQN6NMFPEMAQAU/bundle.json","state_url":"https://pith.science/pith/QZNDROGDYGBSTQN6NMFPEMAQAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QZNDROGDYGBSTQN6NMFPEMAQAU/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":"2026-08-15T14:36:48Z","links":{"resolver":"https://pith.science/pith/QZNDROGDYGBSTQN6NMFPEMAQAU","bundle":"https://pith.science/pith/QZNDROGDYGBSTQN6NMFPEMAQAU/bundle.json","state":"https://pith.science/pith/QZNDROGDYGBSTQN6NMFPEMAQAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QZNDROGDYGBSTQN6NMFPEMAQAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QZNDROGDYGBSTQN6NMFPEMAQAU","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":"75e56cfefa7d9e84b624200cb77effc4b60bb4c3e3c532fff5bc9420194523f1","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T15:24:05Z","title_canon_sha256":"0c48f642bd5cc2c59586651ce93c7e2aab0bfe119c32665bbf87a077ec140ce5"},"schema_version":"1.0","source":{"id":"2311.12908","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.12908","created_at":"2026-07-05T07:15:20Z"},{"alias_kind":"arxiv_version","alias_value":"2311.12908v1","created_at":"2026-07-05T07:15:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12908","created_at":"2026-07-05T07:15:20Z"},{"alias_kind":"pith_short_12","alias_value":"QZNDROGDYGBS","created_at":"2026-07-05T07:15:20Z"},{"alias_kind":"pith_short_16","alias_value":"QZNDROGDYGBSTQN6","created_at":"2026-07-05T07:15:20Z"},{"alias_kind":"pith_short_8","alias_value":"QZNDROGD","created_at":"2026-07-05T07:15:20Z"}],"graph_snapshots":[{"event_id":"sha256:2dd8ad5a091e42d1d983290586860a508c486d2de8b3362eff1164c5cb48eed1","target":"graph","created_at":"2026-07-05T07:15:20Z","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/2311.12908/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has not been widely explored in text-to-image diffusion models; the best existing approach is to fine-tune a pretrained model using carefully curated high quality images and captions to improve visual appeal and text alignment. We propose Diffusion-DPO, a method to align diffusion models to human preferences by directly optimizing on human comparison data. Diffus","authors_text":"Aaron Lou, Bram Wallace, Caiming Xiong, Linqi Zhou, Meihua Dang, Nikhil Naik, Rafael Rafailov, Senthil Purushwalkam, Shafiq Joty, Stefano Ermon","cross_cats":["cs.AI","cs.GR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T15:24:05Z","title":"Diffusion Model Alignment Using Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12908","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":"sha256:316f6ebb5f3c46d12e67c9d36adf49805b711c5a091c4e9dbf77389c1709bd75","target":"record","created_at":"2026-07-05T07:15:20Z","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":"75e56cfefa7d9e84b624200cb77effc4b60bb4c3e3c532fff5bc9420194523f1","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T15:24:05Z","title_canon_sha256":"0c48f642bd5cc2c59586651ce93c7e2aab0bfe119c32665bbf87a077ec140ce5"},"schema_version":"1.0","source":{"id":"2311.12908","kind":"arxiv","version":1}},"canonical_sha256":"865a38b8c3c18329c1be6b0af23010053bbcf4365d0b3969a1700a9d44c73db3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"865a38b8c3c18329c1be6b0af23010053bbcf4365d0b3969a1700a9d44c73db3","first_computed_at":"2026-07-05T07:15:20.424204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:15:20.424204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nDDiYCrhMo0agPGH5FfyGJuir2nSWp1UxWhwDKLBt2KmLgFIi4VYNwTFrVRRSQokIGXfiorW2vA6a6h2mI5yCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:15:20.424730Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.12908","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:316f6ebb5f3c46d12e67c9d36adf49805b711c5a091c4e9dbf77389c1709bd75","sha256:2dd8ad5a091e42d1d983290586860a508c486d2de8b3362eff1164c5cb48eed1"],"state_sha256":"1ee2f06ff162d4d75d723f10a935c64c5b302dc7e1e0c35092aaa6ce585752d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l0U+O96KsYRnLj6oWMks5arOr5yoRtcayrwNDTq2VyKXKC9q3B/SB4E5O6K7+sNSb01oy1AoOtWoZnbNonLSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T14:36:48.899834Z","bundle_sha256":"e77d32148ae834cc82f5b42b69b713b5c8bd50c3461f76824d0eaadf612655a9"}}