{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5FKUAMJUCZQNDBO4ON4I36YN65","short_pith_number":"pith:5FKUAMJU","canonical_record":{"source":{"id":"2406.04312","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:56:40Z","cross_cats_sorted":[],"title_canon_sha256":"48d7e104b0dad4fd5a1daede6ec9bee896c83559bc97af4d0d844ef3e96ace27","abstract_canon_sha256":"7f2774ce264bc3134f6efcc5a90426976653c167f83b52b175382dc7e5f3e22c"},"schema_version":"1.0"},"canonical_sha256":"e9554031341660d185dc73788dfb0df7746c3b66d2c267ff42f941d66460365e","source":{"kind":"arxiv","id":"2406.04312","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04312","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04312v2","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04312","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_12","alias_value":"5FKUAMJUCZQN","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"5FKUAMJUCZQNDBO4","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"5FKUAMJU","created_at":"2026-07-05T09:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5FKUAMJUCZQNDBO4ON4I36YN65","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04312","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:56:40Z","cross_cats_sorted":[],"title_canon_sha256":"48d7e104b0dad4fd5a1daede6ec9bee896c83559bc97af4d0d844ef3e96ace27","abstract_canon_sha256":"7f2774ce264bc3134f6efcc5a90426976653c167f83b52b175382dc7e5f3e22c"},"schema_version":"1.0"},"canonical_sha256":"e9554031341660d185dc73788dfb0df7746c3b66d2c267ff42f941d66460365e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:14.751155Z","signature_b64":"QjRt+mLk9GKFgqCF3UKYcU7c1hm3Y44DLq/X91liNe3v39vEyK/kTpu0XJELjtK8L7nf2E/5uzRzoNUaFpIZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9554031341660d185dc73788dfb0df7746c3b66d2c267ff42f941d66460365e","last_reissued_at":"2026-07-05T09:29:14.750672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:14.750672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04312","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":"2026-07-05T09:29:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FlXzODbj7e94fHzzcas1em1mPGjpumDMG+3DK5W/mfuZFRvbpRN45jBVrbxRkbIZr4vP/Ag2RV7Icx1zXH1dBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:19:14.455558Z"},"content_sha256":"d97df3bb54e758e6fceb9eab6758cccb9d58a5656feebc44b574d6f2e39c0983","schema_version":"1.0","event_id":"sha256:d97df3bb54e758e6fceb9eab6758cccb9d58a5656feebc44b574d6f2e39c0983"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5FKUAMJUCZQNDBO4ON4I36YN65","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexey Dosovitskiy, Karsten Roth, Luca Eyring, Shyamgopal Karthik, Zeynep Akata","submitted_at":"2024-06-06T17:56:40Z","abstract_excerpt":"Text-to-Image (T2I) models have made significant advancements in recent years, but they still struggle to accurately capture intricate details specified in complex compositional prompts. While fine-tuning T2I models with reward objectives has shown promise, it suffers from \"reward hacking\" and may not generalize well to unseen prompt distributions. In this work, we propose Reward-based Noise Optimization (ReNO), a novel approach that enhances T2I models at inference by optimizing the initial noise based on the signal from one or multiple human preference reward models. Remarkably, solving this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04312","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/2406.04312/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":"2026-07-05T09:29:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d9EYKd8Jpms8oXDEAEwCfO8JE9YAh0e3B+myiyxPHobEoJCD16+FbkH7+UO1QdM9xDcwxc3vjUBAwuXgJh1+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:19:14.456227Z"},"content_sha256":"72524cfbdb8516a42775e2d2587e6405cec57eccb2ef36d6a94659a46ded2636","schema_version":"1.0","event_id":"sha256:72524cfbdb8516a42775e2d2587e6405cec57eccb2ef36d6a94659a46ded2636"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FKUAMJUCZQNDBO4ON4I36YN65/bundle.json","state_url":"https://pith.science/pith/5FKUAMJUCZQNDBO4ON4I36YN65/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FKUAMJUCZQNDBO4ON4I36YN65/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":"2026-08-10T22:19:14Z","links":{"resolver":"https://pith.science/pith/5FKUAMJUCZQNDBO4ON4I36YN65","bundle":"https://pith.science/pith/5FKUAMJUCZQNDBO4ON4I36YN65/bundle.json","state":"https://pith.science/pith/5FKUAMJUCZQNDBO4ON4I36YN65/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FKUAMJUCZQNDBO4ON4I36YN65/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5FKUAMJUCZQNDBO4ON4I36YN65","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":"7f2774ce264bc3134f6efcc5a90426976653c167f83b52b175382dc7e5f3e22c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:56:40Z","title_canon_sha256":"48d7e104b0dad4fd5a1daede6ec9bee896c83559bc97af4d0d844ef3e96ace27"},"schema_version":"1.0","source":{"id":"2406.04312","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04312","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04312v2","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04312","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_12","alias_value":"5FKUAMJUCZQN","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"5FKUAMJUCZQNDBO4","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"5FKUAMJU","created_at":"2026-07-05T09:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:72524cfbdb8516a42775e2d2587e6405cec57eccb2ef36d6a94659a46ded2636","target":"graph","created_at":"2026-07-05T09:29:14Z","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/2406.04312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-Image (T2I) models have made significant advancements in recent years, but they still struggle to accurately capture intricate details specified in complex compositional prompts. While fine-tuning T2I models with reward objectives has shown promise, it suffers from \"reward hacking\" and may not generalize well to unseen prompt distributions. In this work, we propose Reward-based Noise Optimization (ReNO), a novel approach that enhances T2I models at inference by optimizing the initial noise based on the signal from one or multiple human preference reward models. Remarkably, solving this","authors_text":"Alexey Dosovitskiy, Karsten Roth, Luca Eyring, Shyamgopal Karthik, Zeynep Akata","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:56:40Z","title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04312","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:d97df3bb54e758e6fceb9eab6758cccb9d58a5656feebc44b574d6f2e39c0983","target":"record","created_at":"2026-07-05T09:29:14Z","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":"7f2774ce264bc3134f6efcc5a90426976653c167f83b52b175382dc7e5f3e22c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:56:40Z","title_canon_sha256":"48d7e104b0dad4fd5a1daede6ec9bee896c83559bc97af4d0d844ef3e96ace27"},"schema_version":"1.0","source":{"id":"2406.04312","kind":"arxiv","version":2}},"canonical_sha256":"e9554031341660d185dc73788dfb0df7746c3b66d2c267ff42f941d66460365e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9554031341660d185dc73788dfb0df7746c3b66d2c267ff42f941d66460365e","first_computed_at":"2026-07-05T09:29:14.750672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:14.750672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QjRt+mLk9GKFgqCF3UKYcU7c1hm3Y44DLq/X91liNe3v39vEyK/kTpu0XJELjtK8L7nf2E/5uzRzoNUaFpIZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:14.751155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04312","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d97df3bb54e758e6fceb9eab6758cccb9d58a5656feebc44b574d6f2e39c0983","sha256:72524cfbdb8516a42775e2d2587e6405cec57eccb2ef36d6a94659a46ded2636"],"state_sha256":"ba0bd46e8dafde2881855254889978cc75b848a43dc5c6f32f472919a5e2f78e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nFtdDDLSqD9kbNBLvDdAd4y1KHzjMCFYOQRqTR0b12cdJRlnJ6Ey1/CjhuHiHl/UGWWv7UozEqIbtjU3QadDCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T22:19:14.463395Z","bundle_sha256":"5fed43b380858e824f6b7ae3bb206384cf392321cda8ec0f572f05f047ceac64"}}