{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SRURN5W6VVIDUXD3HUJS2QHF76","short_pith_number":"pith:SRURN5W6","schema_version":"1.0","canonical_sha256":"946916f6dead503a5c7b3d132d40e5ffad51d2a23a1a2b59cf26686ebbcb3314","source":{"kind":"arxiv","id":"2311.11865","version":1},"attestation_state":"computed","paper":{"title":"VLM-Eval: A General Evaluation on Video Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Jia, Qiuyue Wang, Shuailin Li, Tiancai Wang, Yingfei Liu, Yuang Zhang, Yucheng Zhao","submitted_at":"2023-11-20T16:02:10Z","abstract_excerpt":"Despite the rapid development of video Large Language Models (LLMs), a comprehensive evaluation is still absent. In this paper, we introduce a unified evaluation that encompasses multiple video tasks, including captioning, question and answering, retrieval, and action recognition. In addition to conventional metrics, we showcase how GPT-based evaluation can match human-like performance in assessing response quality across multiple aspects. We propose a simple baseline: Video-LLaVA, which uses a single linear projection and outperforms existing video LLMs. Finally, we evaluate video LLMs beyond"},"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":"2311.11865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-20T16:02:10Z","cross_cats_sorted":[],"title_canon_sha256":"030d90bc51886da6dffed60e26e226f848cbd88713b3b266523407798dffe0ad","abstract_canon_sha256":"cc94e71e283553cc5c82f87cfaaa94def5c896a7d0dacc4197f2fbcfc7c23609"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:40.127643Z","signature_b64":"S5tk1esorv4s7b+iAax0s5AJQ9rePXsK/HnKR2HEzuGG2NVVz9kv28NKM44mevWbgHiKl9gzVQObq2SvXO3CDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"946916f6dead503a5c7b3d132d40e5ffad51d2a23a1a2b59cf26686ebbcb3314","last_reissued_at":"2026-07-05T07:14:40.127172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:40.127172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM-Eval: A General Evaluation on Video Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Jia, Qiuyue Wang, Shuailin Li, Tiancai Wang, Yingfei Liu, Yuang Zhang, Yucheng Zhao","submitted_at":"2023-11-20T16:02:10Z","abstract_excerpt":"Despite the rapid development of video Large Language Models (LLMs), a comprehensive evaluation is still absent. In this paper, we introduce a unified evaluation that encompasses multiple video tasks, including captioning, question and answering, retrieval, and action recognition. In addition to conventional metrics, we showcase how GPT-based evaluation can match human-like performance in assessing response quality across multiple aspects. We propose a simple baseline: Video-LLaVA, which uses a single linear projection and outperforms existing video LLMs. Finally, we evaluate video LLMs beyond"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11865","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/2311.11865/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":"2311.11865","created_at":"2026-07-05T07:14:40.127228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.11865v1","created_at":"2026-07-05T07:14:40.127228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11865","created_at":"2026-07-05T07:14:40.127228+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRURN5W6VVID","created_at":"2026-07-05T07:14:40.127228+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRURN5W6VVIDUXD3","created_at":"2026-07-05T07:14:40.127228+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRURN5W6","created_at":"2026-07-05T07:14:40.127228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.00476","citing_title":"TempCompass: Do Video LLMs Really Understand Videos?","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRURN5W6VVIDUXD3HUJS2QHF76","json":"https://pith.science/pith/SRURN5W6VVIDUXD3HUJS2QHF76.json","graph_json":"https://pith.science/api/pith-number/SRURN5W6VVIDUXD3HUJS2QHF76/graph.json","events_json":"https://pith.science/api/pith-number/SRURN5W6VVIDUXD3HUJS2QHF76/events.json","paper":"https://pith.science/paper/SRURN5W6"},"agent_actions":{"view_html":"https://pith.science/pith/SRURN5W6VVIDUXD3HUJS2QHF76","download_json":"https://pith.science/pith/SRURN5W6VVIDUXD3HUJS2QHF76.json","view_paper":"https://pith.science/paper/SRURN5W6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.11865&json=true","fetch_graph":"https://pith.science/api/pith-number/SRURN5W6VVIDUXD3HUJS2QHF76/graph.json","fetch_events":"https://pith.science/api/pith-number/SRURN5W6VVIDUXD3HUJS2QHF76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRURN5W6VVIDUXD3HUJS2QHF76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRURN5W6VVIDUXD3HUJS2QHF76/action/storage_attestation","attest_author":"https://pith.science/pith/SRURN5W6VVIDUXD3HUJS2QHF76/action/author_attestation","sign_citation":"https://pith.science/pith/SRURN5W6VVIDUXD3HUJS2QHF76/action/citation_signature","submit_replication":"https://pith.science/pith/SRURN5W6VVIDUXD3HUJS2QHF76/action/replication_record"}},"created_at":"2026-07-05T07:14:40.127228+00:00","updated_at":"2026-07-05T07:14:40.127228+00:00"}