{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4C24DVGPITIMLEPB5RFWEOCNVM","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":"39a5e7dcd52e8668e3acb6afac07514e3aa80f6afd535e490e603e6f86584f86","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T02:21:07Z","title_canon_sha256":"b8a977c829446e5b7196914e67998c100948dedf07e3155a2ba7f72f725c7a12"},"schema_version":"1.0","source":{"id":"2503.02199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02199","created_at":"2026-07-05T10:23:38Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02199v1","created_at":"2026-07-05T10:23:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02199","created_at":"2026-07-05T10:23:38Z"},{"alias_kind":"pith_short_12","alias_value":"4C24DVGPITIM","created_at":"2026-07-05T10:23:38Z"},{"alias_kind":"pith_short_16","alias_value":"4C24DVGPITIMLEPB","created_at":"2026-07-05T10:23:38Z"},{"alias_kind":"pith_short_8","alias_value":"4C24DVGP","created_at":"2026-07-05T10:23:38Z"}],"graph_snapshots":[{"event_id":"sha256:2d8e8acdca49235737b9d568fe7e0f07d38688722c0575592c03508507f22030","target":"graph","created_at":"2026-07-05T10:23:38Z","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/2503.02199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) excel in integrating visual and textual information for vision-centric tasks, but their handling of inconsistencies between modalities is underexplored. We investigate VLMs' modality preferences when faced with visual data and varied textual inputs in vision-centered settings. By introducing textual variations to four vision-centric tasks and evaluating ten Vision-Language Models (VLMs), we discover a \\emph{``blind faith in text''} phenomenon: VLMs disproportionately trust textual data over visual data when inconsistencies arise, leading to significant performance","authors_text":"Ailin Deng, Bryan Hooi, Tri Cao, Zhirui Chen","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T02:21:07Z","title":"Words or Vision: Do Vision-Language Models Have Blind Faith in Text?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02199","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":"sha256:194f4152360a96c19f92fcb749852b1189f56239c3acdd5ea8ccbb4d11404b3e","target":"record","created_at":"2026-07-05T10:23:38Z","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":"39a5e7dcd52e8668e3acb6afac07514e3aa80f6afd535e490e603e6f86584f86","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T02:21:07Z","title_canon_sha256":"b8a977c829446e5b7196914e67998c100948dedf07e3155a2ba7f72f725c7a12"},"schema_version":"1.0","source":{"id":"2503.02199","kind":"arxiv","version":1}},"canonical_sha256":"e0b5c1d4cf44d0c591e1ec4b62384dab1ed94755cfffb3369cb65c6122cac774","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0b5c1d4cf44d0c591e1ec4b62384dab1ed94755cfffb3369cb65c6122cac774","first_computed_at":"2026-07-05T10:23:38.973028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:38.973028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sh6Ezg6R8tuVqtfqdigV7KqnbKKCZ+5H1EM1Nj30qgXvLJsnSuA5XwQySELQRn1IY0SSR2Avl9V5BAeUgNcgBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:38.973878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.02199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:194f4152360a96c19f92fcb749852b1189f56239c3acdd5ea8ccbb4d11404b3e","sha256:2d8e8acdca49235737b9d568fe7e0f07d38688722c0575592c03508507f22030"],"state_sha256":"20d0e6af8146ae930e525432f071a28d85051af06319dc137126ceff32a48df2"}