{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UDTQA4TGDULJB3DVI5H3MTYQM5","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":"844318e6128697bc761e6261bf0494ea39fbceef2fc57c8cdafc3acedab82031","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T15:42:01Z","title_canon_sha256":"c1a0c00b82505ebfd53bf48d260f288a19fc9f634ef634878b8eacd97c37ef5b"},"schema_version":"1.0","source":{"id":"2403.17804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17804","created_at":"2026-07-05T08:00:55Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17804v1","created_at":"2026-07-05T08:00:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17804","created_at":"2026-07-05T08:00:55Z"},{"alias_kind":"pith_short_12","alias_value":"UDTQA4TGDULJ","created_at":"2026-07-05T08:00:55Z"},{"alias_kind":"pith_short_16","alias_value":"UDTQA4TGDULJB3DV","created_at":"2026-07-05T08:00:55Z"},{"alias_kind":"pith_short_8","alias_value":"UDTQA4TG","created_at":"2026-07-05T08:00:55Z"}],"graph_snapshots":[{"event_id":"sha256:43d6d14b84125ca8e70bb559497f4d7731c854c0e00ed884ecbfadbcc0c4e19a","target":"graph","created_at":"2026-07-05T08:00:55Z","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/2403.17804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Impressive advances in text-to-image (T2I) generative models have yielded a plethora of high performing models which are able to generate aesthetically appealing, photorealistic images. Despite the progress, these models still struggle to produce images that are consistent with the input prompt, oftentimes failing to capture object quantities, relations and attributes properly. Existing solutions to improve prompt-image consistency suffer from the following challenges: (1) they oftentimes require model fine-tuning, (2) they only focus on nearby prompt samples, and (3) they are affected by unfa","authors_text":"Adina Williams, Adriana Romero-Soriano, Aishwarya Agrawal, Candace Ross, Jack Urbanek, Melissa Hall, Michal Drozdzal, Oscar Ma\\~nas, Pietro Astolfi","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T15:42:01Z","title":"Improving Text-to-Image Consistency via Automatic Prompt Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17804","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:e64139bd40ac059d4dc0ed122b0defe2ba7ba958f559737a6fa538a58d93e2d8","target":"record","created_at":"2026-07-05T08:00:55Z","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":"844318e6128697bc761e6261bf0494ea39fbceef2fc57c8cdafc3acedab82031","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T15:42:01Z","title_canon_sha256":"c1a0c00b82505ebfd53bf48d260f288a19fc9f634ef634878b8eacd97c37ef5b"},"schema_version":"1.0","source":{"id":"2403.17804","kind":"arxiv","version":1}},"canonical_sha256":"a0e70072661d1690ec75474fb64f10674ff7fad99e43aedd6e3a90ac628d0025","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0e70072661d1690ec75474fb64f10674ff7fad99e43aedd6e3a90ac628d0025","first_computed_at":"2026-07-05T08:00:55.562733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:55.562733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/CuFNtTu1llQQvFXwn1XyIJUSCAfCa3LraHkEJbhN4RF46G4NNAIbP35VQ44TLtgscPYz9R5kR/GUmQSCDmQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:55.563204Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.17804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e64139bd40ac059d4dc0ed122b0defe2ba7ba958f559737a6fa538a58d93e2d8","sha256:43d6d14b84125ca8e70bb559497f4d7731c854c0e00ed884ecbfadbcc0c4e19a"],"state_sha256":"94f3a17d4e16ba9a6a5fe80646189d7a581e349400c916a817d463366e9cc100"}