{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SPJUXULNN4JE4UQRFHHXZSCSAY","short_pith_number":"pith:SPJUXULN","canonical_record":{"source":{"id":"2304.05977","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T16:58:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f2bea333ec06346ae3ca24704e7cd5a4403cecd391ec84abcf98b3cc6f950f2b","abstract_canon_sha256":"95921b1a4aaf28fe73ba5d3a75e3425e7a578af7d6e4b0d60a91b4f8190baae2"},"schema_version":"1.0"},"canonical_sha256":"93d34bd16d6f124e521129cf7cc852060b2e2022d838b418a307d54ca561b405","source":{"kind":"arxiv","id":"2304.05977","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05977","created_at":"2026-07-05T07:28:27Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05977v4","created_at":"2026-07-05T07:28:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05977","created_at":"2026-07-05T07:28:27Z"},{"alias_kind":"pith_short_12","alias_value":"SPJUXULNN4JE","created_at":"2026-07-05T07:28:27Z"},{"alias_kind":"pith_short_16","alias_value":"SPJUXULNN4JE4UQR","created_at":"2026-07-05T07:28:27Z"},{"alias_kind":"pith_short_8","alias_value":"SPJUXULN","created_at":"2026-07-05T07:28:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SPJUXULNN4JE4UQRFHHXZSCSAY","target":"record","payload":{"canonical_record":{"source":{"id":"2304.05977","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T16:58:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f2bea333ec06346ae3ca24704e7cd5a4403cecd391ec84abcf98b3cc6f950f2b","abstract_canon_sha256":"95921b1a4aaf28fe73ba5d3a75e3425e7a578af7d6e4b0d60a91b4f8190baae2"},"schema_version":"1.0"},"canonical_sha256":"93d34bd16d6f124e521129cf7cc852060b2e2022d838b418a307d54ca561b405","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:27.842094Z","signature_b64":"xDpcLfaZ7Pl7DyPeEyPrYlJKD6ukbfJ70vTUYWs+puiHmvsLAQ/50dyffC0P0Uk+wWjuaQaxjnV2vAAbbTUsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93d34bd16d6f124e521129cf7cc852060b2e2022d838b418a307d54ca561b405","last_reissued_at":"2026-07-05T07:28:27.841669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:27.841669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.05977","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sw2PDNvdTqSIcZI2C98G2+Y9PGRBaa4p+VRiysQ5FrtBwc1XyD7YOGBpRZxRltJMohZXgV12PPiQ2S/a7EQPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T12:27:55.345988Z"},"content_sha256":"602e39a07bfcafb80d6586d1e96637b94bf1db446ed614623bc7baed2041c721","schema_version":"1.0","event_id":"sha256:602e39a07bfcafb80d6586d1e96637b94bf1db446ed614623bc7baed2041c721"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SPJUXULNN4JE4UQRFHHXZSCSAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiazheng Xu, Jie Tang, Ming Ding, Qinkai Li, Xiao Liu, Yuchen Wu, Yuxiao Dong, Yuxuan Tong","submitted_at":"2023-04-12T16:58:13Z","abstract_excerpt":"We present a comprehensive solution to learn and improve text-to-image models from human preference feedback. To begin with, we build ImageReward -- the first general-purpose text-to-image human preference reward model -- to effectively encode human preferences. Its training is based on our systematic annotation pipeline including rating and ranking, which collects 137k expert comparisons to date. In human evaluation, ImageReward outperforms existing scoring models and metrics, making it a promising automatic metric for evaluating text-to-image synthesis. On top of it, we propose Reward Feedba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05977","kind":"arxiv","version":4},"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/2304.05977/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":"2026-07-05T07:28:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t2GYwNgGJ8tclx35LkLnelxdopukJSa+hgU5lkIFCwb9hluL4bLxoRekJE0XFR+n+i+ZIXDp/nQ/z3wMtY0ZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T12:27:55.346512Z"},"content_sha256":"6770b930a3871c13766691028933dfdba0e1b2e95d044c04e8ab915757e3703b","schema_version":"1.0","event_id":"sha256:6770b930a3871c13766691028933dfdba0e1b2e95d044c04e8ab915757e3703b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SPJUXULNN4JE4UQRFHHXZSCSAY/bundle.json","state_url":"https://pith.science/pith/SPJUXULNN4JE4UQRFHHXZSCSAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SPJUXULNN4JE4UQRFHHXZSCSAY/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":"2026-08-02T12:27:55Z","links":{"resolver":"https://pith.science/pith/SPJUXULNN4JE4UQRFHHXZSCSAY","bundle":"https://pith.science/pith/SPJUXULNN4JE4UQRFHHXZSCSAY/bundle.json","state":"https://pith.science/pith/SPJUXULNN4JE4UQRFHHXZSCSAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SPJUXULNN4JE4UQRFHHXZSCSAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SPJUXULNN4JE4UQRFHHXZSCSAY","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":"95921b1a4aaf28fe73ba5d3a75e3425e7a578af7d6e4b0d60a91b4f8190baae2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T16:58:13Z","title_canon_sha256":"f2bea333ec06346ae3ca24704e7cd5a4403cecd391ec84abcf98b3cc6f950f2b"},"schema_version":"1.0","source":{"id":"2304.05977","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05977","created_at":"2026-07-05T07:28:27Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05977v4","created_at":"2026-07-05T07:28:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05977","created_at":"2026-07-05T07:28:27Z"},{"alias_kind":"pith_short_12","alias_value":"SPJUXULNN4JE","created_at":"2026-07-05T07:28:27Z"},{"alias_kind":"pith_short_16","alias_value":"SPJUXULNN4JE4UQR","created_at":"2026-07-05T07:28:27Z"},{"alias_kind":"pith_short_8","alias_value":"SPJUXULN","created_at":"2026-07-05T07:28:27Z"}],"graph_snapshots":[{"event_id":"sha256:6770b930a3871c13766691028933dfdba0e1b2e95d044c04e8ab915757e3703b","target":"graph","created_at":"2026-07-05T07:28:27Z","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/2304.05977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a comprehensive solution to learn and improve text-to-image models from human preference feedback. To begin with, we build ImageReward -- the first general-purpose text-to-image human preference reward model -- to effectively encode human preferences. Its training is based on our systematic annotation pipeline including rating and ranking, which collects 137k expert comparisons to date. In human evaluation, ImageReward outperforms existing scoring models and metrics, making it a promising automatic metric for evaluating text-to-image synthesis. On top of it, we propose Reward Feedba","authors_text":"Jiazheng Xu, Jie Tang, Ming Ding, Qinkai Li, Xiao Liu, Yuchen Wu, Yuxiao Dong, Yuxuan Tong","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T16:58:13Z","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05977","kind":"arxiv","version":4},"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":"sha256:602e39a07bfcafb80d6586d1e96637b94bf1db446ed614623bc7baed2041c721","target":"record","created_at":"2026-07-05T07:28:27Z","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":"95921b1a4aaf28fe73ba5d3a75e3425e7a578af7d6e4b0d60a91b4f8190baae2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T16:58:13Z","title_canon_sha256":"f2bea333ec06346ae3ca24704e7cd5a4403cecd391ec84abcf98b3cc6f950f2b"},"schema_version":"1.0","source":{"id":"2304.05977","kind":"arxiv","version":4}},"canonical_sha256":"93d34bd16d6f124e521129cf7cc852060b2e2022d838b418a307d54ca561b405","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93d34bd16d6f124e521129cf7cc852060b2e2022d838b418a307d54ca561b405","first_computed_at":"2026-07-05T07:28:27.841669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:27.841669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xDpcLfaZ7Pl7DyPeEyPrYlJKD6ukbfJ70vTUYWs+puiHmvsLAQ/50dyffC0P0Uk+wWjuaQaxjnV2vAAbbTUsAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:27.842094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.05977","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:602e39a07bfcafb80d6586d1e96637b94bf1db446ed614623bc7baed2041c721","sha256:6770b930a3871c13766691028933dfdba0e1b2e95d044c04e8ab915757e3703b"],"state_sha256":"82e1fd5c96ba411507ca302a7f897b4ed72f74f49ba24f71e47d6245131c2ff8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GkZuo1/75/xZ1DeYSmzGW4za/uTiNL3k25koWEQgT240FSsP58kzFTVda2m2OR+pDVBDWhIYKKIT2qNW8H+mCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T12:27:55.351244Z","bundle_sha256":"abddbd0861b30a381768c054164937ee99ba5f0bf75df2b3fea53dbbc1dc42e8"}}