{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YHJ7VMJHTM22WCEEMTTDFKCK33","short_pith_number":"pith:YHJ7VMJH","schema_version":"1.0","canonical_sha256":"c1d3fab1279b35ab088464e632a84adeef78d0c6e2a11d033308e84a6ec6fa7b","source":{"kind":"arxiv","id":"2312.03766","version":2},"attestation_state":"computed","paper":{"title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Brian Gordon, Daniel Cohen-Or, Dani Lischinski, Idan Szpektor, Roopal Garg, Xi Chen, Yonatan Bitton, Yonatan Shafir","submitted_at":"2023-12-05T20:07:34Z","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"},"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":"2312.03766","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T20:07:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"613531d8aadf203bac76e8cd589047d7feffefa67be0e34bde09dfe62d77318a","abstract_canon_sha256":"fc7a4fb8cacb830af0919fe8eb9d7b4d5c550d03c5b166021b4f41b592750bbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:49.725128Z","signature_b64":"054eSpnWJjYkdk3Prh0/TvZmQN5qEtC4PNzwA5KKTOxJK+8f6YDIQE9aH73wiRik5J5WnoGwZVpbFuRKwY23DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1d3fab1279b35ab088464e632a84adeef78d0c6e2a11d033308e84a6ec6fa7b","last_reissued_at":"2026-07-05T08:44:49.724548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:49.724548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Brian Gordon, Daniel Cohen-Or, Dani Lischinski, Idan Szpektor, Roopal Garg, Xi Chen, Yonatan Bitton, Yonatan Shafir","submitted_at":"2023-12-05T20:07:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03766","kind":"arxiv","version":2},"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/2312.03766/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":"2312.03766","created_at":"2026-07-05T08:44:49.724615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03766v2","created_at":"2026-07-05T08:44:49.724615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03766","created_at":"2026-07-05T08:44:49.724615+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHJ7VMJHTM22","created_at":"2026-07-05T08:44:49.724615+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHJ7VMJHTM22WCEE","created_at":"2026-07-05T08:44:49.724615+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHJ7VMJH","created_at":"2026-07-05T08:44:49.724615+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/YHJ7VMJHTM22WCEEMTTDFKCK33","json":"https://pith.science/pith/YHJ7VMJHTM22WCEEMTTDFKCK33.json","graph_json":"https://pith.science/api/pith-number/YHJ7VMJHTM22WCEEMTTDFKCK33/graph.json","events_json":"https://pith.science/api/pith-number/YHJ7VMJHTM22WCEEMTTDFKCK33/events.json","paper":"https://pith.science/paper/YHJ7VMJH"},"agent_actions":{"view_html":"https://pith.science/pith/YHJ7VMJHTM22WCEEMTTDFKCK33","download_json":"https://pith.science/pith/YHJ7VMJHTM22WCEEMTTDFKCK33.json","view_paper":"https://pith.science/paper/YHJ7VMJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03766&json=true","fetch_graph":"https://pith.science/api/pith-number/YHJ7VMJHTM22WCEEMTTDFKCK33/graph.json","fetch_events":"https://pith.science/api/pith-number/YHJ7VMJHTM22WCEEMTTDFKCK33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHJ7VMJHTM22WCEEMTTDFKCK33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHJ7VMJHTM22WCEEMTTDFKCK33/action/storage_attestation","attest_author":"https://pith.science/pith/YHJ7VMJHTM22WCEEMTTDFKCK33/action/author_attestation","sign_citation":"https://pith.science/pith/YHJ7VMJHTM22WCEEMTTDFKCK33/action/citation_signature","submit_replication":"https://pith.science/pith/YHJ7VMJHTM22WCEEMTTDFKCK33/action/replication_record"}},"created_at":"2026-07-05T08:44:49.724615+00:00","updated_at":"2026-07-05T08:44:49.724615+00:00"}