{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YHJ7VMJHTM22WCEEMTTDFKCK33","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":"fc7a4fb8cacb830af0919fe8eb9d7b4d5c550d03c5b166021b4f41b592750bbb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T20:07:34Z","title_canon_sha256":"613531d8aadf203bac76e8cd589047d7feffefa67be0e34bde09dfe62d77318a"},"schema_version":"1.0","source":{"id":"2312.03766","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03766","created_at":"2026-07-05T08:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03766v2","created_at":"2026-07-05T08:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03766","created_at":"2026-07-05T08:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"YHJ7VMJHTM22","created_at":"2026-07-05T08:44:49Z"},{"alias_kind":"pith_short_16","alias_value":"YHJ7VMJHTM22WCEE","created_at":"2026-07-05T08:44:49Z"},{"alias_kind":"pith_short_8","alias_value":"YHJ7VMJH","created_at":"2026-07-05T08:44:49Z"}],"graph_snapshots":[{"event_id":"sha256:9b0294b1de83669a14011d927e37219b22898a85bcf51cce24aadf1328266257","target":"graph","created_at":"2026-07-05T08:44:49Z","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/2312.03766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While existing image-text alignment models reach high quality binary assessments, they fall short of pinpointing the exact source of misalignment. In this paper, we present a method to provide detailed textual and visual explanation of detected misalignments between text-image pairs. We leverage large language models and visual grounding models to automatically construct a training set that holds plausible misaligned captions for a given image and corresponding textual explanations and visual indicators. We also publish a new human curated test set comprising ground-truth textual and visual mi","authors_text":"Brian Gordon, Daniel Cohen-Or, Dani Lischinski, Idan Szpektor, Roopal Garg, Xi Chen, Yonatan Bitton, Yonatan Shafir","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T20:07:34Z","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03766","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:b476bd7f336f6ed3710ec827c1737ccf53ced94eede8171e646fd2fb4c61c6e2","target":"record","created_at":"2026-07-05T08:44:49Z","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":"fc7a4fb8cacb830af0919fe8eb9d7b4d5c550d03c5b166021b4f41b592750bbb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T20:07:34Z","title_canon_sha256":"613531d8aadf203bac76e8cd589047d7feffefa67be0e34bde09dfe62d77318a"},"schema_version":"1.0","source":{"id":"2312.03766","kind":"arxiv","version":2}},"canonical_sha256":"c1d3fab1279b35ab088464e632a84adeef78d0c6e2a11d033308e84a6ec6fa7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1d3fab1279b35ab088464e632a84adeef78d0c6e2a11d033308e84a6ec6fa7b","first_computed_at":"2026-07-05T08:44:49.724548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:49.724548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"054eSpnWJjYkdk3Prh0/TvZmQN5qEtC4PNzwA5KKTOxJK+8f6YDIQE9aH73wiRik5J5WnoGwZVpbFuRKwY23DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:49.725128Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.03766","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b476bd7f336f6ed3710ec827c1737ccf53ced94eede8171e646fd2fb4c61c6e2","sha256:9b0294b1de83669a14011d927e37219b22898a85bcf51cce24aadf1328266257"],"state_sha256":"14356cdd360b08c38402e7f28684930806341da1ab5b755fc822aac6308e2dca"}