{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PDDOMNKUFLCX2ZRX5CVEOIPGD7","short_pith_number":"pith:PDDOMNKU","schema_version":"1.0","canonical_sha256":"78c6e635542ac57d6637e8aa4721e61fdb16500046ba3b5e09656554cba433b2","source":{"kind":"arxiv","id":"2411.06908","version":3},"attestation_state":"computed","paper":{"title":"EVQAScore: A Fine-grained Metric for Video Question Answering Data Quality Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hao Liang, Hejun Dong, Wentao Zhang, Zirong Chen","submitted_at":"2024-11-11T12:11:36Z","abstract_excerpt":"Video question-answering (QA) is a core task in video understanding. Evaluating the quality of video QA and video caption data quality for training video large language models (VideoLLMs) is an essential challenge. Although various methods have been proposed for assessing video caption quality, there remains a lack of dedicated evaluation methods for Video QA. To address this gap, we introduce EVQAScore, a reference-free method that leverages keyword extraction to assess both video caption and video QA data quality. Additionally, we incorporate frame sampling and rescaling techniques to enhanc"},"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":"2411.06908","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T12:11:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d10bdb1c0be7bc1b853fb63cd682b13969eab132fd84f0c5e538566c24eb22ff","abstract_canon_sha256":"f0e53c65b8026dfe8889c3b98a757d1c502e9bb8c072d0d29757a63c71f9e282"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:28.873712Z","signature_b64":"RSV/pKWynuEhrYaHWzu7qj3CNBVPh6zMQT65t8POC8cR5i642zYxBVi3jqz60I9kOybMG+eJAFbtCbOCgvRLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78c6e635542ac57d6637e8aa4721e61fdb16500046ba3b5e09656554cba433b2","last_reissued_at":"2026-07-05T10:10:28.873295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:28.873295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EVQAScore: A Fine-grained Metric for Video Question Answering Data Quality Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hao Liang, Hejun Dong, Wentao Zhang, Zirong Chen","submitted_at":"2024-11-11T12:11:36Z","abstract_excerpt":"Video question-answering (QA) is a core task in video understanding. Evaluating the quality of video QA and video caption data quality for training video large language models (VideoLLMs) is an essential challenge. Although various methods have been proposed for assessing video caption quality, there remains a lack of dedicated evaluation methods for Video QA. To address this gap, we introduce EVQAScore, a reference-free method that leverages keyword extraction to assess both video caption and video QA data quality. Additionally, we incorporate frame sampling and rescaling techniques to enhanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06908","kind":"arxiv","version":3},"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/2411.06908/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":"2411.06908","created_at":"2026-07-05T10:10:28.873360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.06908v3","created_at":"2026-07-05T10:10:28.873360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06908","created_at":"2026-07-05T10:10:28.873360+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDDOMNKUFLCX","created_at":"2026-07-05T10:10:28.873360+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDDOMNKUFLCX2ZRX","created_at":"2026-07-05T10:10:28.873360+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDDOMNKU","created_at":"2026-07-05T10:10:28.873360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04707","citing_title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDDOMNKUFLCX2ZRX5CVEOIPGD7","json":"https://pith.science/pith/PDDOMNKUFLCX2ZRX5CVEOIPGD7.json","graph_json":"https://pith.science/api/pith-number/PDDOMNKUFLCX2ZRX5CVEOIPGD7/graph.json","events_json":"https://pith.science/api/pith-number/PDDOMNKUFLCX2ZRX5CVEOIPGD7/events.json","paper":"https://pith.science/paper/PDDOMNKU"},"agent_actions":{"view_html":"https://pith.science/pith/PDDOMNKUFLCX2ZRX5CVEOIPGD7","download_json":"https://pith.science/pith/PDDOMNKUFLCX2ZRX5CVEOIPGD7.json","view_paper":"https://pith.science/paper/PDDOMNKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.06908&json=true","fetch_graph":"https://pith.science/api/pith-number/PDDOMNKUFLCX2ZRX5CVEOIPGD7/graph.json","fetch_events":"https://pith.science/api/pith-number/PDDOMNKUFLCX2ZRX5CVEOIPGD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDDOMNKUFLCX2ZRX5CVEOIPGD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDDOMNKUFLCX2ZRX5CVEOIPGD7/action/storage_attestation","attest_author":"https://pith.science/pith/PDDOMNKUFLCX2ZRX5CVEOIPGD7/action/author_attestation","sign_citation":"https://pith.science/pith/PDDOMNKUFLCX2ZRX5CVEOIPGD7/action/citation_signature","submit_replication":"https://pith.science/pith/PDDOMNKUFLCX2ZRX5CVEOIPGD7/action/replication_record"}},"created_at":"2026-07-05T10:10:28.873360+00:00","updated_at":"2026-07-05T10:10:28.873360+00:00"}