{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PYI7MSHDCQKK2VPPPMOUVU7V7W","short_pith_number":"pith:PYI7MSHD","schema_version":"1.0","canonical_sha256":"7e11f648e31414ad55ef7b1d4ad3f5fd8c7b0866382be2038b6199dc321b5e6a","source":{"kind":"arxiv","id":"2501.13536","version":1},"attestation_state":"computed","paper":{"title":"ReasVQA: Advancing VideoQA with Imperfect Reasoning Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dongyan Zhao, Huishuai Zhang, Jiansheng Wei, Jianxin Liang, Xiaojun Meng, Yueqian Wang","submitted_at":"2025-01-23T10:35:22Z","abstract_excerpt":"Video Question Answering (VideoQA) is a challenging task that requires understanding complex visual and temporal relationships within videos to answer questions accurately. In this work, we introduce \\textbf{ReasVQA} (Reasoning-enhanced Video Question Answering), a novel approach that leverages reasoning processes generated by Multimodal Large Language Models (MLLMs) to improve the performance of VideoQA models. Our approach consists of three phases: reasoning generation, reasoning refinement, and learning from reasoning. First, we generate detailed reasoning processes using additional MLLMs, "},"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":"2501.13536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T10:35:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"64d4f35c09da53e0e0f9e7bb78f2b246fe8351cbf7535a933e6cf870ec1add1f","abstract_canon_sha256":"668af5065ccc1737ef789e495149ecf42674d022a6ac86e9ca1b15d13f5a60a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:30.035017Z","signature_b64":"wGFpSyPz66i6VFyMXbloDDAvLfjIHjcskHoFFwTyHo4BAkqhAtvhUyP6RbZmelXWBmFXGQ7fv/drhDlhRa87Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e11f648e31414ad55ef7b1d4ad3f5fd8c7b0866382be2038b6199dc321b5e6a","last_reissued_at":"2026-07-05T10:04:30.034564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:30.034564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReasVQA: Advancing VideoQA with Imperfect Reasoning Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dongyan Zhao, Huishuai Zhang, Jiansheng Wei, Jianxin Liang, Xiaojun Meng, Yueqian Wang","submitted_at":"2025-01-23T10:35:22Z","abstract_excerpt":"Video Question Answering (VideoQA) is a challenging task that requires understanding complex visual and temporal relationships within videos to answer questions accurately. In this work, we introduce \\textbf{ReasVQA} (Reasoning-enhanced Video Question Answering), a novel approach that leverages reasoning processes generated by Multimodal Large Language Models (MLLMs) to improve the performance of VideoQA models. Our approach consists of three phases: reasoning generation, reasoning refinement, and learning from reasoning. First, we generate detailed reasoning processes using additional MLLMs, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13536","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/2501.13536/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":"2501.13536","created_at":"2026-07-05T10:04:30.034618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13536v1","created_at":"2026-07-05T10:04:30.034618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13536","created_at":"2026-07-05T10:04:30.034618+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYI7MSHDCQKK","created_at":"2026-07-05T10:04:30.034618+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYI7MSHDCQKK2VPP","created_at":"2026-07-05T10:04:30.034618+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYI7MSHD","created_at":"2026-07-05T10:04:30.034618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23145","citing_title":"UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PYI7MSHDCQKK2VPPPMOUVU7V7W","json":"https://pith.science/pith/PYI7MSHDCQKK2VPPPMOUVU7V7W.json","graph_json":"https://pith.science/api/pith-number/PYI7MSHDCQKK2VPPPMOUVU7V7W/graph.json","events_json":"https://pith.science/api/pith-number/PYI7MSHDCQKK2VPPPMOUVU7V7W/events.json","paper":"https://pith.science/paper/PYI7MSHD"},"agent_actions":{"view_html":"https://pith.science/pith/PYI7MSHDCQKK2VPPPMOUVU7V7W","download_json":"https://pith.science/pith/PYI7MSHDCQKK2VPPPMOUVU7V7W.json","view_paper":"https://pith.science/paper/PYI7MSHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13536&json=true","fetch_graph":"https://pith.science/api/pith-number/PYI7MSHDCQKK2VPPPMOUVU7V7W/graph.json","fetch_events":"https://pith.science/api/pith-number/PYI7MSHDCQKK2VPPPMOUVU7V7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYI7MSHDCQKK2VPPPMOUVU7V7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYI7MSHDCQKK2VPPPMOUVU7V7W/action/storage_attestation","attest_author":"https://pith.science/pith/PYI7MSHDCQKK2VPPPMOUVU7V7W/action/author_attestation","sign_citation":"https://pith.science/pith/PYI7MSHDCQKK2VPPPMOUVU7V7W/action/citation_signature","submit_replication":"https://pith.science/pith/PYI7MSHDCQKK2VPPPMOUVU7V7W/action/replication_record"}},"created_at":"2026-07-05T10:04:30.034618+00:00","updated_at":"2026-07-05T10:04:30.034618+00:00"}