{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PBT7O3SWFMFYHLTPFKRGZKVB44","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":"10bc2afdff0c56e5b615b0b83e8eb0a1607d488fa88a039f1a3a5e3f90041f63","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T08:26:58Z","title_canon_sha256":"b8a90fe05a1106be52dc1c10ad1649bbb411c0d5b5636032c1941f818089e9b6"},"schema_version":"1.0","source":{"id":"2405.16934","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16934","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16934v1","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16934","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"PBT7O3SWFMFY","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"pith_short_16","alias_value":"PBT7O3SWFMFYHLTP","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"pith_short_8","alias_value":"PBT7O3SW","created_at":"2026-07-05T08:23:37Z"}],"graph_snapshots":[{"event_id":"sha256:5d7f50603a14e92536de4878cfe3e559b684abbbebf5d0591fae02004c749d37","target":"graph","created_at":"2026-07-05T08:23:37Z","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/2405.16934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Commonsense Reasoning (VCR) calls for explanatory reasoning behind question answering over visual scenes. To achieve this goal, a model is required to provide an acceptable rationale as the reason for the predicted answers. Progress on the benchmark dataset stems largely from the recent advancement of Vision-Language Transformers (VL Transformers). These models are first pre-trained on some generic large-scale vision-text datasets, and then the learned representations are transferred to the downstream VCR task. Despite their attractive performance, this paper posits that the VL Transfor","authors_text":"Kejie Wang, Liqiang Nie, Mohan Kankanhalli, Xiaolin Chen, Yangyang Guo, Zhenyang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T08:26:58Z","title":"Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16934","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":"sha256:5b9e85b24dc5535e2fa472df78293ba3c031dd401485d15eba4f69015c1cb2fa","target":"record","created_at":"2026-07-05T08:23:37Z","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":"10bc2afdff0c56e5b615b0b83e8eb0a1607d488fa88a039f1a3a5e3f90041f63","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T08:26:58Z","title_canon_sha256":"b8a90fe05a1106be52dc1c10ad1649bbb411c0d5b5636032c1941f818089e9b6"},"schema_version":"1.0","source":{"id":"2405.16934","kind":"arxiv","version":1}},"canonical_sha256":"7867f76e562b0b83ae6f2aa26caaa1e7009e3e81060ad6e30c8b3f0c5ac18fee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7867f76e562b0b83ae6f2aa26caaa1e7009e3e81060ad6e30c8b3f0c5ac18fee","first_computed_at":"2026-07-05T08:23:37.693785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:37.693785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zUIdnMjp1WSowxxTfjPcnyzPXsYQm5ILCuCxM8PkuUvWs/pI+FrF8qhIxrvpRjpWDR9iBcg/MZ/EGMmnqG8WDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:37.694332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16934","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b9e85b24dc5535e2fa472df78293ba3c031dd401485d15eba4f69015c1cb2fa","sha256:5d7f50603a14e92536de4878cfe3e559b684abbbebf5d0591fae02004c749d37"],"state_sha256":"650986f81d6c58a0364596dbc1047bbd716b435ea13b830f3af3c7627179bfd0"}