{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6O35T6ULXGPKZYVMUUT5BQKD4I","short_pith_number":"pith:6O35T6UL","schema_version":"1.0","canonical_sha256":"f3b7d9fa8bb99eace2aca527d0c143e21358d4f5ebbc2a3b9646deebb0dc43cd","source":{"kind":"arxiv","id":"2505.03829","version":1},"attestation_state":"computed","paper":{"title":"VideoLLM Benchmarks and Evaluation: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Yogesh Kumar","submitted_at":"2025-05-03T20:56:09Z","abstract_excerpt":"The rapid development of Large Language Models (LLMs) has catalyzed significant advancements in video understanding technologies. This survey provides a comprehensive analysis of benchmarks and evaluation methodologies specifically designed or used for Video Large Language Models (VideoLLMs). We examine the current landscape of video understanding benchmarks, discussing their characteristics, evaluation protocols, and limitations. The paper analyzes various evaluation methodologies, including closed-set, open-set, and specialized evaluations for temporal and spatiotemporal understanding tasks."},"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":"2505.03829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-03T20:56:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3cdb300887fc429d524c0f3cc6c6f0be38b94247c5e23ed6c4ec8374649c628d","abstract_canon_sha256":"7780280363d6b9b10810c1210cbf6d2b5714d4e3c962b719f48c6e62ca8209af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:32.245755Z","signature_b64":"v79/pWEX+FjhPxunRee4SAYWJMfJdTP5UuYbI1eg0DioqHDoI2ViqL8hbSUUHRL5L9Pzg9mOei40rrVvkCMfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3b7d9fa8bb99eace2aca527d0c143e21358d4f5ebbc2a3b9646deebb0dc43cd","last_reissued_at":"2026-07-05T10:59:32.245122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:32.245122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoLLM Benchmarks and Evaluation: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Yogesh Kumar","submitted_at":"2025-05-03T20:56:09Z","abstract_excerpt":"The rapid development of Large Language Models (LLMs) has catalyzed significant advancements in video understanding technologies. This survey provides a comprehensive analysis of benchmarks and evaluation methodologies specifically designed or used for Video Large Language Models (VideoLLMs). We examine the current landscape of video understanding benchmarks, discussing their characteristics, evaluation protocols, and limitations. The paper analyzes various evaluation methodologies, including closed-set, open-set, and specialized evaluations for temporal and spatiotemporal understanding tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03829","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/2505.03829/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":"2505.03829","created_at":"2026-07-05T10:59:32.245203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03829v1","created_at":"2026-07-05T10:59:32.245203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03829","created_at":"2026-07-05T10:59:32.245203+00:00"},{"alias_kind":"pith_short_12","alias_value":"6O35T6ULXGPK","created_at":"2026-07-05T10:59:32.245203+00:00"},{"alias_kind":"pith_short_16","alias_value":"6O35T6ULXGPKZYVM","created_at":"2026-07-05T10:59:32.245203+00:00"},{"alias_kind":"pith_short_8","alias_value":"6O35T6UL","created_at":"2026-07-05T10:59:32.245203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6O35T6ULXGPKZYVMUUT5BQKD4I","json":"https://pith.science/pith/6O35T6ULXGPKZYVMUUT5BQKD4I.json","graph_json":"https://pith.science/api/pith-number/6O35T6ULXGPKZYVMUUT5BQKD4I/graph.json","events_json":"https://pith.science/api/pith-number/6O35T6ULXGPKZYVMUUT5BQKD4I/events.json","paper":"https://pith.science/paper/6O35T6UL"},"agent_actions":{"view_html":"https://pith.science/pith/6O35T6ULXGPKZYVMUUT5BQKD4I","download_json":"https://pith.science/pith/6O35T6ULXGPKZYVMUUT5BQKD4I.json","view_paper":"https://pith.science/paper/6O35T6UL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03829&json=true","fetch_graph":"https://pith.science/api/pith-number/6O35T6ULXGPKZYVMUUT5BQKD4I/graph.json","fetch_events":"https://pith.science/api/pith-number/6O35T6ULXGPKZYVMUUT5BQKD4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6O35T6ULXGPKZYVMUUT5BQKD4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6O35T6ULXGPKZYVMUUT5BQKD4I/action/storage_attestation","attest_author":"https://pith.science/pith/6O35T6ULXGPKZYVMUUT5BQKD4I/action/author_attestation","sign_citation":"https://pith.science/pith/6O35T6ULXGPKZYVMUUT5BQKD4I/action/citation_signature","submit_replication":"https://pith.science/pith/6O35T6ULXGPKZYVMUUT5BQKD4I/action/replication_record"}},"created_at":"2026-07-05T10:59:32.245203+00:00","updated_at":"2026-07-05T10:59:32.245203+00:00"}