{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JJ36LGQIZKBFTZQKSX33TK4M74","short_pith_number":"pith:JJ36LGQI","schema_version":"1.0","canonical_sha256":"4a77e59a08ca8259e60a95f7b9ab8cff1fa254acaf19343590353f5ba66c225c","source":{"kind":"arxiv","id":"2403.13352","version":6},"attestation_state":"computed","paper":{"title":"AGFSync: Leveraging AI-Generated Feedback for Preference Optimization in Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohua Chen, Chengwei Pan, Enshen Zhou, Haoran Feng, Jingkun An, Xijie Huang, Yemin Shi, Yinghao Zhu, Zongjian Li","submitted_at":"2024-03-20T07:31:07Z","abstract_excerpt":"Text-to-Image (T2I) diffusion models have achieved remarkable success in image generation. Despite their progress, challenges remain in both prompt-following ability, image quality and lack of high-quality datasets, which are essential for refining these models. As acquiring labeled data is costly, we introduce AGFSync, a framework that enhances T2I diffusion models through Direct Preference Optimization (DPO) in a fully AI-driven approach. AGFSync utilizes Vision-Language Models (VLM) to assess image quality across style, coherence, and aesthetics, generating feedback data within an AI-driven"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.13352","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T07:31:07Z","cross_cats_sorted":[],"title_canon_sha256":"1ab6d9c303db25180f904042cc801cd6fbb8de22b592d7946fb98d2a41e1d1a9","abstract_canon_sha256":"0d7976a209d154ce43af22cca1a53b2398142798867185ebbde55a5e113b1e86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:55.729110Z","signature_b64":"wdIRSCUaR64vkf7PQV59uKII/XL7Fl8G4Z/Sqtw1AXI5uOJVJOwfMjpEX2pR+d9cX2LQgfNTXF/aZvjpDzFCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a77e59a08ca8259e60a95f7b9ab8cff1fa254acaf19343590353f5ba66c225c","last_reissued_at":"2026-07-05T09:55:55.728460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:55.728460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AGFSync: Leveraging AI-Generated Feedback for Preference Optimization in Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohua Chen, Chengwei Pan, Enshen Zhou, Haoran Feng, Jingkun An, Xijie Huang, Yemin Shi, Yinghao Zhu, Zongjian Li","submitted_at":"2024-03-20T07:31:07Z","abstract_excerpt":"Text-to-Image (T2I) diffusion models have achieved remarkable success in image generation. Despite their progress, challenges remain in both prompt-following ability, image quality and lack of high-quality datasets, which are essential for refining these models. As acquiring labeled data is costly, we introduce AGFSync, a framework that enhances T2I diffusion models through Direct Preference Optimization (DPO) in a fully AI-driven approach. AGFSync utilizes Vision-Language Models (VLM) to assess image quality across style, coherence, and aesthetics, generating feedback data within an AI-driven"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13352","kind":"arxiv","version":6},"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/2403.13352/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.13352","created_at":"2026-07-05T09:55:55.728540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13352v6","created_at":"2026-07-05T09:55:55.728540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13352","created_at":"2026-07-05T09:55:55.728540+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJ36LGQIZKBF","created_at":"2026-07-05T09:55:55.728540+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJ36LGQIZKBFTZQK","created_at":"2026-07-05T09:55:55.728540+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJ36LGQI","created_at":"2026-07-05T09:55:55.728540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJ36LGQIZKBFTZQKSX33TK4M74","json":"https://pith.science/pith/JJ36LGQIZKBFTZQKSX33TK4M74.json","graph_json":"https://pith.science/api/pith-number/JJ36LGQIZKBFTZQKSX33TK4M74/graph.json","events_json":"https://pith.science/api/pith-number/JJ36LGQIZKBFTZQKSX33TK4M74/events.json","paper":"https://pith.science/paper/JJ36LGQI"},"agent_actions":{"view_html":"https://pith.science/pith/JJ36LGQIZKBFTZQKSX33TK4M74","download_json":"https://pith.science/pith/JJ36LGQIZKBFTZQKSX33TK4M74.json","view_paper":"https://pith.science/paper/JJ36LGQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13352&json=true","fetch_graph":"https://pith.science/api/pith-number/JJ36LGQIZKBFTZQKSX33TK4M74/graph.json","fetch_events":"https://pith.science/api/pith-number/JJ36LGQIZKBFTZQKSX33TK4M74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJ36LGQIZKBFTZQKSX33TK4M74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJ36LGQIZKBFTZQKSX33TK4M74/action/storage_attestation","attest_author":"https://pith.science/pith/JJ36LGQIZKBFTZQKSX33TK4M74/action/author_attestation","sign_citation":"https://pith.science/pith/JJ36LGQIZKBFTZQKSX33TK4M74/action/citation_signature","submit_replication":"https://pith.science/pith/JJ36LGQIZKBFTZQKSX33TK4M74/action/replication_record"}},"created_at":"2026-07-05T09:55:55.728540+00:00","updated_at":"2026-07-05T09:55:55.728540+00:00"}