{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7ITWCBY2SJD7BT22GTNPGR5X54","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":"e39260891554bf74e820f3407c027b1a17726a9bbc929dfd3e4fe532fb035136","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T12:33:15Z","title_canon_sha256":"803975d00de8e8c3b8dcd0e18f60ae77307fa2be7935b1839bab95c278329a4c"},"schema_version":"1.0","source":{"id":"2606.30220","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30220","created_at":"2026-06-30T02:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30220v1","created_at":"2026-06-30T02:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30220","created_at":"2026-06-30T02:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"7ITWCBY2SJD7","created_at":"2026-06-30T02:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"7ITWCBY2SJD7BT22","created_at":"2026-06-30T02:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"7ITWCBY2","created_at":"2026-06-30T02:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:37a80ba565043d94f79a53fe028a67fcf66e9e48c66b2335c1676572dc1f94aa","target":"graph","created_at":"2026-06-30T02:17:54Z","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/2606.30220/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High benchmark accuracy does not guarantee genuine use of visual evidence. We study this problem in traffic accident Video Question Answering (VideoQA), where correct answers should depend on scene-specific visual evidence but may instead be inferred from textual shortcuts. Through an audit of four public benchmarks, we find that several recent open-weight Vision-Language Models (VLMs) perform competitively, and sometimes better, without video input. On the MM-AU benchmark, removing video consistently improves accuracy, and adding more frames further degrades performance. To quantify visual de","authors_text":"Mar\\'ia Alejandra Bravo Sarmiento, Sanghwan Kim, Sena Korkut, Zeynep Akata","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T12:33:15Z","title":"From Accuracy to Visual Dependence: Auditing and Filtering Modality Collapse in Traffic VideoQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30220","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:def93cd3c63d3008a0e23c894b503c9acefcfee3e683fced6d6e5debbf3a467b","target":"record","created_at":"2026-06-30T02:17:54Z","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":"e39260891554bf74e820f3407c027b1a17726a9bbc929dfd3e4fe532fb035136","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T12:33:15Z","title_canon_sha256":"803975d00de8e8c3b8dcd0e18f60ae77307fa2be7935b1839bab95c278329a4c"},"schema_version":"1.0","source":{"id":"2606.30220","kind":"arxiv","version":1}},"canonical_sha256":"fa2761071a9247f0cf5a34daf347b7ef33fb2bfcb9009977c609328178829d88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa2761071a9247f0cf5a34daf347b7ef33fb2bfcb9009977c609328178829d88","first_computed_at":"2026-06-30T02:17:54.941137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:54.941137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mm2QUFV18uTsoeCBLFqY6cXC6AZBX/yHhXwE1DdYFa2jOu86+AmxSjZCCRKVv+3rxR19/tqL6rJ/n7mpaQXpAw==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:54.941775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30220","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:def93cd3c63d3008a0e23c894b503c9acefcfee3e683fced6d6e5debbf3a467b","sha256:37a80ba565043d94f79a53fe028a67fcf66e9e48c66b2335c1676572dc1f94aa"],"state_sha256":"a547a9806fe1471773a203a02a5852d3c6da32eea4e9735c05fb420f4d28f782"}