{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RPAWD7RJBB5RZJVJUWP3CZPGZK","short_pith_number":"pith:RPAWD7RJ","schema_version":"1.0","canonical_sha256":"8bc161fe29087b1ca6a9a59fb165e6ca8cc74fdd63999ac70035e8a3d191e8a3","source":{"kind":"arxiv","id":"2501.01645","version":3},"attestation_state":"computed","paper":{"title":"HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fengmao Lv, Guangcong Wang, Guiyang Xie, Hansheng Zhang, Heqing Zou, Huaijian Zhang, Junyang Chen, Tianze Luo, Victor Xiao Jie Zhang, Zhuochen Wang","submitted_at":"2025-01-03T05:32:37Z","abstract_excerpt":"Multimodal large language models have become a popular topic in deep visual understanding due to many promising real-world applications. However, hour-long video understanding, spanning over one hour and containing tens of thousands of visual frames, remains under-explored because of 1) challenging long-term video analyses, 2) inefficient large-model approaches, and 3) lack of large-scale benchmark datasets. Among them, in this paper, we focus on building a large-scale hour-long long video benchmark, HLV-1K, designed to evaluate long video understanding models. HLV-1K comprises 1009 hour-long "},"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":"2501.01645","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T05:32:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"45a3b0c1a5643428dafdfff7873030d58bca5ee9f8e8892726c3441ee1a1c69f","abstract_canon_sha256":"11645f18a9d1e3b48496ffa150fe03361976ccb77ee6a39067bc077cbb7629c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:16.099743Z","signature_b64":"5mBbO8nCngSX9kb2iVOUwfL0CpHPikGw4/L6w6XjEtvcDc4nWXaySb9vfNUjRgxsS2gs2RAU8wdjkdJizvhzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bc161fe29087b1ca6a9a59fb165e6ca8cc74fdd63999ac70035e8a3d191e8a3","last_reissued_at":"2026-07-05T11:02:16.099376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:16.099376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fengmao Lv, Guangcong Wang, Guiyang Xie, Hansheng Zhang, Heqing Zou, Huaijian Zhang, Junyang Chen, Tianze Luo, Victor Xiao Jie Zhang, Zhuochen Wang","submitted_at":"2025-01-03T05:32:37Z","abstract_excerpt":"Multimodal large language models have become a popular topic in deep visual understanding due to many promising real-world applications. However, hour-long video understanding, spanning over one hour and containing tens of thousands of visual frames, remains under-explored because of 1) challenging long-term video analyses, 2) inefficient large-model approaches, and 3) lack of large-scale benchmark datasets. Among them, in this paper, we focus on building a large-scale hour-long long video benchmark, HLV-1K, designed to evaluate long video understanding models. HLV-1K comprises 1009 hour-long "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01645","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/2501.01645/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":"2501.01645","created_at":"2026-07-05T11:02:16.099433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01645v3","created_at":"2026-07-05T11:02:16.099433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01645","created_at":"2026-07-05T11:02:16.099433+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPAWD7RJBB5R","created_at":"2026-07-05T11:02:16.099433+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPAWD7RJBB5RZJVJ","created_at":"2026-07-05T11:02:16.099433+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPAWD7RJ","created_at":"2026-07-05T11:02:16.099433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23922","citing_title":"ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPAWD7RJBB5RZJVJUWP3CZPGZK","json":"https://pith.science/pith/RPAWD7RJBB5RZJVJUWP3CZPGZK.json","graph_json":"https://pith.science/api/pith-number/RPAWD7RJBB5RZJVJUWP3CZPGZK/graph.json","events_json":"https://pith.science/api/pith-number/RPAWD7RJBB5RZJVJUWP3CZPGZK/events.json","paper":"https://pith.science/paper/RPAWD7RJ"},"agent_actions":{"view_html":"https://pith.science/pith/RPAWD7RJBB5RZJVJUWP3CZPGZK","download_json":"https://pith.science/pith/RPAWD7RJBB5RZJVJUWP3CZPGZK.json","view_paper":"https://pith.science/paper/RPAWD7RJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01645&json=true","fetch_graph":"https://pith.science/api/pith-number/RPAWD7RJBB5RZJVJUWP3CZPGZK/graph.json","fetch_events":"https://pith.science/api/pith-number/RPAWD7RJBB5RZJVJUWP3CZPGZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPAWD7RJBB5RZJVJUWP3CZPGZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPAWD7RJBB5RZJVJUWP3CZPGZK/action/storage_attestation","attest_author":"https://pith.science/pith/RPAWD7RJBB5RZJVJUWP3CZPGZK/action/author_attestation","sign_citation":"https://pith.science/pith/RPAWD7RJBB5RZJVJUWP3CZPGZK/action/citation_signature","submit_replication":"https://pith.science/pith/RPAWD7RJBB5RZJVJUWP3CZPGZK/action/replication_record"}},"created_at":"2026-07-05T11:02:16.099433+00:00","updated_at":"2026-07-05T11:02:16.099433+00:00"}