{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:74CX4QQKNCAW53AYNLG4CGQHMN","short_pith_number":"pith:74CX4QQK","schema_version":"1.0","canonical_sha256":"ff057e420a68816eec186acdc11a076363c08c6b249ec0bce25cf0735cc580b1","source":{"kind":"arxiv","id":"2411.04998","version":1},"attestation_state":"computed","paper":{"title":"HourVideo: 1-Hour Video-Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Agrim Gupta, Crist\\'obal Eyzaguirre, Jiajun Wu, Jimming He, Keshigeyan Chandrasegaran, Lea M. Hadzic, Li Fei-Fei, Manling Li, Taran Kota, Zane Durante","submitted_at":"2024-11-07T18:59:16Z","abstract_excerpt":"We present HourVideo, a benchmark dataset for hour-long video-language understanding. Our dataset consists of a novel task suite comprising summarization, perception (recall, tracking), visual reasoning (spatial, temporal, predictive, causal, counterfactual), and navigation (room-to-room, object retrieval) tasks. HourVideo includes 500 manually curated egocentric videos from the Ego4D dataset, spanning durations of 20 to 120 minutes, and features 12,976 high-quality, five-way multiple-choice questions. Benchmarking results reveal that multimodal models, including GPT-4 and LLaVA-NeXT, achieve "},"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":"2411.04998","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:59:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c88bbcec37eb44276ecc31f76f9c6c91b72cacdc650ab7ea5636447ae5367092","abstract_canon_sha256":"4bc2ca3aa1d1c98480b4f5be2539ed8cfde047821862ca76215eb9a1439b4c9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:37.401332Z","signature_b64":"mgaY9Lcp5NqND4y5KUsj8bTVtZHUyg4Wh9KOBoy1keaUsZO/KuRwqNS0TBYFcmOI3HI1YA0tJlQLyb+HttTvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff057e420a68816eec186acdc11a076363c08c6b249ec0bce25cf0735cc580b1","last_reissued_at":"2026-07-05T09:32:37.400827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:37.400827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HourVideo: 1-Hour Video-Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Agrim Gupta, Crist\\'obal Eyzaguirre, Jiajun Wu, Jimming He, Keshigeyan Chandrasegaran, Lea M. Hadzic, Li Fei-Fei, Manling Li, Taran Kota, Zane Durante","submitted_at":"2024-11-07T18:59:16Z","abstract_excerpt":"We present HourVideo, a benchmark dataset for hour-long video-language understanding. Our dataset consists of a novel task suite comprising summarization, perception (recall, tracking), visual reasoning (spatial, temporal, predictive, causal, counterfactual), and navigation (room-to-room, object retrieval) tasks. HourVideo includes 500 manually curated egocentric videos from the Ego4D dataset, spanning durations of 20 to 120 minutes, and features 12,976 high-quality, five-way multiple-choice questions. Benchmarking results reveal that multimodal models, including GPT-4 and LLaVA-NeXT, achieve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04998","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/2411.04998/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":"2411.04998","created_at":"2026-07-05T09:32:37.400884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04998v1","created_at":"2026-07-05T09:32:37.400884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04998","created_at":"2026-07-05T09:32:37.400884+00:00"},{"alias_kind":"pith_short_12","alias_value":"74CX4QQKNCAW","created_at":"2026-07-05T09:32:37.400884+00:00"},{"alias_kind":"pith_short_16","alias_value":"74CX4QQKNCAW53AY","created_at":"2026-07-05T09:32:37.400884+00:00"},{"alias_kind":"pith_short_8","alias_value":"74CX4QQK","created_at":"2026-07-05T09:32:37.400884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15342","citing_title":"Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00574","citing_title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2502.04326","citing_title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2501.12386","citing_title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08342","citing_title":"EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74CX4QQKNCAW53AYNLG4CGQHMN","json":"https://pith.science/pith/74CX4QQKNCAW53AYNLG4CGQHMN.json","graph_json":"https://pith.science/api/pith-number/74CX4QQKNCAW53AYNLG4CGQHMN/graph.json","events_json":"https://pith.science/api/pith-number/74CX4QQKNCAW53AYNLG4CGQHMN/events.json","paper":"https://pith.science/paper/74CX4QQK"},"agent_actions":{"view_html":"https://pith.science/pith/74CX4QQKNCAW53AYNLG4CGQHMN","download_json":"https://pith.science/pith/74CX4QQKNCAW53AYNLG4CGQHMN.json","view_paper":"https://pith.science/paper/74CX4QQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04998&json=true","fetch_graph":"https://pith.science/api/pith-number/74CX4QQKNCAW53AYNLG4CGQHMN/graph.json","fetch_events":"https://pith.science/api/pith-number/74CX4QQKNCAW53AYNLG4CGQHMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74CX4QQKNCAW53AYNLG4CGQHMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74CX4QQKNCAW53AYNLG4CGQHMN/action/storage_attestation","attest_author":"https://pith.science/pith/74CX4QQKNCAW53AYNLG4CGQHMN/action/author_attestation","sign_citation":"https://pith.science/pith/74CX4QQKNCAW53AYNLG4CGQHMN/action/citation_signature","submit_replication":"https://pith.science/pith/74CX4QQKNCAW53AYNLG4CGQHMN/action/replication_record"}},"created_at":"2026-07-05T09:32:37.400884+00:00","updated_at":"2026-07-05T09:32:37.400884+00:00"}