{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YXTLSHPZT6XBZDNAZSGPTQJMHA","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":"df2521d41e9fa08f0177933e6dd088f30965f11b12f0e36e2ba13bbc5b57b89a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T03:42:14Z","title_canon_sha256":"6b5eb2bae6968da6ef99b7ca3b24af5e20923f462274cf385cb38d794ecbb2a7"},"schema_version":"1.0","source":{"id":"2404.14715","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.14715","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"arxiv_version","alias_value":"2404.14715v2","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14715","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"pith_short_12","alias_value":"YXTLSHPZT6XB","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"pith_short_16","alias_value":"YXTLSHPZT6XBZDNA","created_at":"2026-07-05T08:46:24Z"},{"alias_kind":"pith_short_8","alias_value":"YXTLSHPZ","created_at":"2026-07-05T08:46:24Z"}],"graph_snapshots":[{"event_id":"sha256:b52ce600f74d0e433a0d27086996a67f456678a71c2baa70d48fb456b50abdc7","target":"graph","created_at":"2026-07-05T08:46:24Z","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/2404.14715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in large-scale pre-training has led to the development of advanced vision-language models (VLMs) with remarkable proficiency in comprehending and generating multimodal content. Despite the impressive ability to perform complex reasoning for VLMs, current models often struggle to effectively and precisely capture the compositional information on both the image and text sides. To address this, we propose FineMatch, a new aspect-based fine-grained text and image matching benchmark, focusing on text and image mismatch detection and correction. This benchmark introduces a novel task","authors_text":"Daoan Zhang, Hang Hua, Jiebo Luo, Jing Shi, John Collomosse, Kushal Kafle, Scott Cohen, Simon Jenni","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T03:42:14Z","title":"FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14715","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":"sha256:896b5e261bfcc42fe80f6bab6a76f3a598b71bd5bb464446a88f68d243938323","target":"record","created_at":"2026-07-05T08:46:24Z","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":"df2521d41e9fa08f0177933e6dd088f30965f11b12f0e36e2ba13bbc5b57b89a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T03:42:14Z","title_canon_sha256":"6b5eb2bae6968da6ef99b7ca3b24af5e20923f462274cf385cb38d794ecbb2a7"},"schema_version":"1.0","source":{"id":"2404.14715","kind":"arxiv","version":2}},"canonical_sha256":"c5e6b91df99fae1c8da0cc8cf9c12c383d9bc86a2117398b48c9789cad7637dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5e6b91df99fae1c8da0cc8cf9c12c383d9bc86a2117398b48c9789cad7637dc","first_computed_at":"2026-07-05T08:46:24.332100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:24.332100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+vw662bgTyZQSLOXcLzCT5Trxvjji4RjVeUlHOUSCPcMutR/1ueZTgTjYjWV41UthpPh76Q57RHlPR7tk0aLCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:24.332603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.14715","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:896b5e261bfcc42fe80f6bab6a76f3a598b71bd5bb464446a88f68d243938323","sha256:b52ce600f74d0e433a0d27086996a67f456678a71c2baa70d48fb456b50abdc7"],"state_sha256":"02436a39f31f6e0f4d0195aa8d3dab856dcfe72902a9758a4b85998966822f21"}