{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WF6OMV5TLJD425752TR757VGSA","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":"48ac07b6f7a1bc3ca29ecae34cf416b64eac4cbed21331bd999b4a85a21ad55b","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-10T17:54:57Z","title_canon_sha256":"20c3138fc56b4f032d70cf2a4137de01c28635d4067d3b55ab059799f8035c68"},"schema_version":"1.0","source":{"id":"2307.04749","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04749","created_at":"2026-07-05T07:20:52Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04749v2","created_at":"2026-07-05T07:20:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04749","created_at":"2026-07-05T07:20:52Z"},{"alias_kind":"pith_short_12","alias_value":"WF6OMV5TLJD4","created_at":"2026-07-05T07:20:52Z"},{"alias_kind":"pith_short_16","alias_value":"WF6OMV5TLJD42575","created_at":"2026-07-05T07:20:52Z"},{"alias_kind":"pith_short_8","alias_value":"WF6OMV5T","created_at":"2026-07-05T07:20:52Z"}],"graph_snapshots":[{"event_id":"sha256:8e6cd298e530fd4b88a716647cfa634b28bebb9058b4248be6c3d2b73bb2745a","target":"graph","created_at":"2026-07-05T07:20:52Z","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/2307.04749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The field of text-conditioned image generation has made unparalleled progress with the recent advent of latent diffusion models. While remarkable, as the complexity of given text input increases, the state-of-the-art diffusion models may still fail in generating images which accurately convey the semantics of the given prompt. Furthermore, it has been observed that such misalignments are often left undetected by pretrained multi-modal models such as CLIP. To address these problems, in this paper we explore a simple yet effective decompositional approach towards both evaluation and improvement ","authors_text":"Jaskirat Singh, Liang Zheng","cross_cats":["cs.AI","cs.LG","cs.MM","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-10T17:54:57Z","title":"Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04749","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":"sha256:08515cd42d6f0e713547975413c5129f0a8352ec70251d0f94e30ff183801dc6","target":"record","created_at":"2026-07-05T07:20:52Z","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":"48ac07b6f7a1bc3ca29ecae34cf416b64eac4cbed21331bd999b4a85a21ad55b","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-10T17:54:57Z","title_canon_sha256":"20c3138fc56b4f032d70cf2a4137de01c28635d4067d3b55ab059799f8035c68"},"schema_version":"1.0","source":{"id":"2307.04749","kind":"arxiv","version":2}},"canonical_sha256":"b17ce657b35a47cd77fdd4e3fefea69000cb4f2d1bb177167b81ce8a6e55fba6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b17ce657b35a47cd77fdd4e3fefea69000cb4f2d1bb177167b81ce8a6e55fba6","first_computed_at":"2026-07-05T07:20:52.566912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:52.566912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XvPTPLMUDM4iYxFx0yWDuf/ySAvTp3yE68aCoXPOkN9ifi/GL8wFyMSS0V2dlk4gK2hJzfwYb2xa/Is/fLulCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:52.567297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.04749","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08515cd42d6f0e713547975413c5129f0a8352ec70251d0f94e30ff183801dc6","sha256:8e6cd298e530fd4b88a716647cfa634b28bebb9058b4248be6c3d2b73bb2745a"],"state_sha256":"672e6e8239002b4932dba1463e2c188d405ab78560b1182c8e95bc73ecc66394"}