{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:74CX4QQKNCAW53AYNLG4CGQHMN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4bc2ca3aa1d1c98480b4f5be2539ed8cfde047821862ca76215eb9a1439b4c9e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:59:16Z","title_canon_sha256":"c88bbcec37eb44276ecc31f76f9c6c91b72cacdc650ab7ea5636447ae5367092"},"schema_version":"1.0","source":{"id":"2411.04998","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04998","created_at":"2026-07-05T09:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04998v1","created_at":"2026-07-05T09:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04998","created_at":"2026-07-05T09:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"74CX4QQKNCAW","created_at":"2026-07-05T09:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"74CX4QQKNCAW53AY","created_at":"2026-07-05T09:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"74CX4QQK","created_at":"2026-07-05T09:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:04d2b9500a4ba93beb3b4fd1b91bef86747a317e3446d14473968e33b35f1829","target":"graph","created_at":"2026-07-05T09:32:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.04998/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:59:16Z","title":"HourVideo: 1-Hour Video-Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04998","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6d8344034e8423da582ecfd147f44dbba0d89a342f562d4a934ffd36d88d746b","target":"record","created_at":"2026-07-05T09:32:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4bc2ca3aa1d1c98480b4f5be2539ed8cfde047821862ca76215eb9a1439b4c9e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:59:16Z","title_canon_sha256":"c88bbcec37eb44276ecc31f76f9c6c91b72cacdc650ab7ea5636447ae5367092"},"schema_version":"1.0","source":{"id":"2411.04998","kind":"arxiv","version":1}},"canonical_sha256":"ff057e420a68816eec186acdc11a076363c08c6b249ec0bce25cf0735cc580b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff057e420a68816eec186acdc11a076363c08c6b249ec0bce25cf0735cc580b1","first_computed_at":"2026-07-05T09:32:37.400827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:37.400827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mgaY9Lcp5NqND4y5KUsj8bTVtZHUyg4Wh9KOBoy1keaUsZO/KuRwqNS0TBYFcmOI3HI1YA0tJlQLyb+HttTvCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:37.401332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04998","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d8344034e8423da582ecfd147f44dbba0d89a342f562d4a934ffd36d88d746b","sha256:04d2b9500a4ba93beb3b4fd1b91bef86747a317e3446d14473968e33b35f1829"],"state_sha256":"39827eeb753b21f6821c7caa8448e69fedfee0f25292885228f8a3397fe0d342"}