{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C73Q53ZYH26YDFRVQUUIWTSKG5","short_pith_number":"pith:C73Q53ZY","schema_version":"1.0","canonical_sha256":"17f70eef383ebd81963585288b4e4a377706d032a9eb104454fe0e32936882d4","source":{"kind":"arxiv","id":"2407.06491","version":1},"attestation_state":"computed","paper":{"title":"VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Wang, Kunchang Li, Limin Wang, Xinhao Li, Zhenpeng Huang","submitted_at":"2024-07-09T01:49:08Z","abstract_excerpt":"With the growth of high-quality data and advancement in visual pre-training paradigms, Video Foundation Models (VFMs) have made significant progress recently, demonstrating their remarkable performance on traditional video understanding benchmarks. However, the existing benchmarks (e.g. Kinetics) and their evaluation protocols are often limited by relatively poor diversity, high evaluation costs, and saturated performance metrics. In this paper, we build a comprehensive benchmark suite to address these issues, namely VideoEval. Specifically, we establish the Video Task Adaption Benchmark (VidT"},"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":"2407.06491","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T01:49:08Z","cross_cats_sorted":[],"title_canon_sha256":"2966145edf6a9d59611b8edc721877e898f2bd78b5cb6c5a059a6f017d7afaec","abstract_canon_sha256":"aa2b295890aac4577a83f13bce15040f8f8909719462f038e0db903ea7c216e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:49.375236Z","signature_b64":"ziQc/tKGMbTVwyc1FdDkX23f/sT+SunhxPaQ3vzx89em23v5/PqCw33IUc5EVSC4vHnOSKwwA3XPGT/qZgvUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17f70eef383ebd81963585288b4e4a377706d032a9eb104454fe0e32936882d4","last_reissued_at":"2026-07-05T08:41:49.374765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:49.374765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Wang, Kunchang Li, Limin Wang, Xinhao Li, Zhenpeng Huang","submitted_at":"2024-07-09T01:49:08Z","abstract_excerpt":"With the growth of high-quality data and advancement in visual pre-training paradigms, Video Foundation Models (VFMs) have made significant progress recently, demonstrating their remarkable performance on traditional video understanding benchmarks. However, the existing benchmarks (e.g. Kinetics) and their evaluation protocols are often limited by relatively poor diversity, high evaluation costs, and saturated performance metrics. In this paper, we build a comprehensive benchmark suite to address these issues, namely VideoEval. Specifically, we establish the Video Task Adaption Benchmark (VidT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06491","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/2407.06491/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":"2407.06491","created_at":"2026-07-05T08:41:49.374820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06491v1","created_at":"2026-07-05T08:41:49.374820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06491","created_at":"2026-07-05T08:41:49.374820+00:00"},{"alias_kind":"pith_short_12","alias_value":"C73Q53ZYH26Y","created_at":"2026-07-05T08:41:49.374820+00:00"},{"alias_kind":"pith_short_16","alias_value":"C73Q53ZYH26YDFRV","created_at":"2026-07-05T08:41:49.374820+00:00"},{"alias_kind":"pith_short_8","alias_value":"C73Q53ZY","created_at":"2026-07-05T08:41:49.374820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03837","citing_title":"Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2504.06958","citing_title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C73Q53ZYH26YDFRVQUUIWTSKG5","json":"https://pith.science/pith/C73Q53ZYH26YDFRVQUUIWTSKG5.json","graph_json":"https://pith.science/api/pith-number/C73Q53ZYH26YDFRVQUUIWTSKG5/graph.json","events_json":"https://pith.science/api/pith-number/C73Q53ZYH26YDFRVQUUIWTSKG5/events.json","paper":"https://pith.science/paper/C73Q53ZY"},"agent_actions":{"view_html":"https://pith.science/pith/C73Q53ZYH26YDFRVQUUIWTSKG5","download_json":"https://pith.science/pith/C73Q53ZYH26YDFRVQUUIWTSKG5.json","view_paper":"https://pith.science/paper/C73Q53ZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06491&json=true","fetch_graph":"https://pith.science/api/pith-number/C73Q53ZYH26YDFRVQUUIWTSKG5/graph.json","fetch_events":"https://pith.science/api/pith-number/C73Q53ZYH26YDFRVQUUIWTSKG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C73Q53ZYH26YDFRVQUUIWTSKG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C73Q53ZYH26YDFRVQUUIWTSKG5/action/storage_attestation","attest_author":"https://pith.science/pith/C73Q53ZYH26YDFRVQUUIWTSKG5/action/author_attestation","sign_citation":"https://pith.science/pith/C73Q53ZYH26YDFRVQUUIWTSKG5/action/citation_signature","submit_replication":"https://pith.science/pith/C73Q53ZYH26YDFRVQUUIWTSKG5/action/replication_record"}},"created_at":"2026-07-05T08:41:49.374820+00:00","updated_at":"2026-07-05T08:41:49.374820+00:00"}