{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YBX47OOSSJ4MRMXFSBFAVIDEDL","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":"c78f84f8ac35523d9dad07ee4354dc80a4bfe8ddc98d0b3c6cca05746e855e39","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T09:14:45Z","title_canon_sha256":"4352ca9b5b5a9e04062f6026885a158059638ba21564c851fa18d95cefae051c"},"schema_version":"1.0","source":{"id":"2409.11007","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11007","created_at":"2026-07-05T09:08:00Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11007v1","created_at":"2026-07-05T09:08:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11007","created_at":"2026-07-05T09:08:00Z"},{"alias_kind":"pith_short_12","alias_value":"YBX47OOSSJ4M","created_at":"2026-07-05T09:08:00Z"},{"alias_kind":"pith_short_16","alias_value":"YBX47OOSSJ4MRMXF","created_at":"2026-07-05T09:08:00Z"},{"alias_kind":"pith_short_8","alias_value":"YBX47OOS","created_at":"2026-07-05T09:08:00Z"}],"graph_snapshots":[{"event_id":"sha256:37da10d183329b1ec674e3dcf51c994b49c668111b946161156739b0ad595ccf","target":"graph","created_at":"2026-07-05T09:08:00Z","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/2409.11007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) are typically evaluated with Visual Question Answering (VQA) tasks which assess a model's understanding of scenes. Good VQA performance is taken as evidence that the model will perform well on a broader range of tasks that require both visual and language inputs. However, scene-aware VQA does not fully capture input biases or assess hallucinations caused by a misalignment between modalities. To address this, we propose a Cross-modal Alignment Similarity Test (CAST) to probe VLMs for self-consistency across modalities. This test involves asking the models to identi","authors_text":"Anil Batra, Gautier Dagan, Olga Loginova","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T09:14:45Z","title":"CAST: Cross-modal Alignment Similarity Test for Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11007","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:e6f6a44215fe30d2f396c8738dd324bfec95110412fa7c5bf602ed8cb09b6643","target":"record","created_at":"2026-07-05T09:08:00Z","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":"c78f84f8ac35523d9dad07ee4354dc80a4bfe8ddc98d0b3c6cca05746e855e39","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T09:14:45Z","title_canon_sha256":"4352ca9b5b5a9e04062f6026885a158059638ba21564c851fa18d95cefae051c"},"schema_version":"1.0","source":{"id":"2409.11007","kind":"arxiv","version":1}},"canonical_sha256":"c06fcfb9d29278c8b2e5904a0aa0641ad4c3f2caa97cb31abaa71016342c5c6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c06fcfb9d29278c8b2e5904a0aa0641ad4c3f2caa97cb31abaa71016342c5c6a","first_computed_at":"2026-07-05T09:08:00.622773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:00.622773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x1NcyvDAYvVKXXFqcQ8+AMic4gza37AnK5jsYIbU6e5g6VdHIObnGGIXghb1492c3sx+fLSsg4pDLTCE1UrvAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:00.623239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11007","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6f6a44215fe30d2f396c8738dd324bfec95110412fa7c5bf602ed8cb09b6643","sha256:37da10d183329b1ec674e3dcf51c994b49c668111b946161156739b0ad595ccf"],"state_sha256":"f09446db9874f25e3e961902bea53853ffd3d96a50940e55d80e3b8471bdaa51"}