{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PBT7O3SWFMFYHLTPFKRGZKVB44","short_pith_number":"pith:PBT7O3SW","schema_version":"1.0","canonical_sha256":"7867f76e562b0b83ae6f2aa26caaa1e7009e3e81060ad6e30c8b3f0c5ac18fee","source":{"kind":"arxiv","id":"2405.16934","version":1},"attestation_state":"computed","paper":{"title":"Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kejie Wang, Liqiang Nie, Mohan Kankanhalli, Xiaolin Chen, Yangyang Guo, Zhenyang Li","submitted_at":"2024-05-27T08:26:58Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.16934","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T08:26:58Z","cross_cats_sorted":[],"title_canon_sha256":"b8a90fe05a1106be52dc1c10ad1649bbb411c0d5b5636032c1941f818089e9b6","abstract_canon_sha256":"10bc2afdff0c56e5b615b0b83e8eb0a1607d488fa88a039f1a3a5e3f90041f63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:37.694332Z","signature_b64":"zUIdnMjp1WSowxxTfjPcnyzPXsYQm5ILCuCxM8PkuUvWs/pI+FrF8qhIxrvpRjpWDR9iBcg/MZ/EGMmnqG8WDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7867f76e562b0b83ae6f2aa26caaa1e7009e3e81060ad6e30c8b3f0c5ac18fee","last_reissued_at":"2026-07-05T08:23:37.693785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:37.693785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kejie Wang, Liqiang Nie, Mohan Kankanhalli, Xiaolin Chen, Yangyang Guo, Zhenyang Li","submitted_at":"2024-05-27T08:26:58Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16934","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.16934/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.16934","created_at":"2026-07-05T08:23:37.693872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16934v1","created_at":"2026-07-05T08:23:37.693872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16934","created_at":"2026-07-05T08:23:37.693872+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBT7O3SWFMFY","created_at":"2026-07-05T08:23:37.693872+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBT7O3SWFMFYHLTP","created_at":"2026-07-05T08:23:37.693872+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBT7O3SW","created_at":"2026-07-05T08:23:37.693872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18421","citing_title":"Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBT7O3SWFMFYHLTPFKRGZKVB44","json":"https://pith.science/pith/PBT7O3SWFMFYHLTPFKRGZKVB44.json","graph_json":"https://pith.science/api/pith-number/PBT7O3SWFMFYHLTPFKRGZKVB44/graph.json","events_json":"https://pith.science/api/pith-number/PBT7O3SWFMFYHLTPFKRGZKVB44/events.json","paper":"https://pith.science/paper/PBT7O3SW"},"agent_actions":{"view_html":"https://pith.science/pith/PBT7O3SWFMFYHLTPFKRGZKVB44","download_json":"https://pith.science/pith/PBT7O3SWFMFYHLTPFKRGZKVB44.json","view_paper":"https://pith.science/paper/PBT7O3SW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16934&json=true","fetch_graph":"https://pith.science/api/pith-number/PBT7O3SWFMFYHLTPFKRGZKVB44/graph.json","fetch_events":"https://pith.science/api/pith-number/PBT7O3SWFMFYHLTPFKRGZKVB44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBT7O3SWFMFYHLTPFKRGZKVB44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBT7O3SWFMFYHLTPFKRGZKVB44/action/storage_attestation","attest_author":"https://pith.science/pith/PBT7O3SWFMFYHLTPFKRGZKVB44/action/author_attestation","sign_citation":"https://pith.science/pith/PBT7O3SWFMFYHLTPFKRGZKVB44/action/citation_signature","submit_replication":"https://pith.science/pith/PBT7O3SWFMFYHLTPFKRGZKVB44/action/replication_record"}},"created_at":"2026-07-05T08:23:37.693872+00:00","updated_at":"2026-07-05T08:23:37.693872+00:00"}