{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MIRWZLLTW3TGW6WCRDO4TKNSLU","short_pith_number":"pith:MIRWZLLT","schema_version":"1.0","canonical_sha256":"62236cad73b6e66b7ac288ddc9a9b25d272be79e4500e1c26feb04eafdf0ed60","source":{"kind":"arxiv","id":"2405.08813","version":3},"attestation_state":"computed","paper":{"title":"CinePile: A Long Video Question Answering Dataset and Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"David Jacobs, Gowthami Somepalli, Khalid Saifullah, Miquel Farr\\'e, Ronen Basri, Ruchit Rawal, Tom Goldstein","submitted_at":"2024-05-14T17:59:02Z","abstract_excerpt":"Current datasets for long-form video understanding often fall short of providing genuine long-form comprehension challenges, as many tasks derived from these datasets can be successfully tackled by analyzing just one or a few random frames from a video. To address this issue, we present a novel dataset and benchmark, CinePile, specifically designed for authentic long-form video understanding. This paper details our innovative approach for creating a question-answer dataset, utilizing advanced LLMs with human-in-the-loop and building upon human-generated raw data. Our comprehensive dataset comp"},"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":"2405.08813","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-14T17:59:02Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"996a922fc1d33ec38b571bc848065c0fddfb150bae6d34a0b2df8a169cbb49d7","abstract_canon_sha256":"ad6805d0f9e861a8257330e23f15edbeb377b7ee2414fae5febf2a0e001a346e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:05.796383Z","signature_b64":"JyDNfl5axNmMkH6gU8CzXKys3NLy7Mswfs/4i4fSENZ0qWiRZGT1MMXg+lkVZ8udxPdbcVmusk2EdSBSkC9DDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62236cad73b6e66b7ac288ddc9a9b25d272be79e4500e1c26feb04eafdf0ed60","last_reissued_at":"2026-07-05T09:23:05.795867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:05.795867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CinePile: A Long Video Question Answering Dataset and Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"David Jacobs, Gowthami Somepalli, Khalid Saifullah, Miquel Farr\\'e, Ronen Basri, Ruchit Rawal, Tom Goldstein","submitted_at":"2024-05-14T17:59:02Z","abstract_excerpt":"Current datasets for long-form video understanding often fall short of providing genuine long-form comprehension challenges, as many tasks derived from these datasets can be successfully tackled by analyzing just one or a few random frames from a video. To address this issue, we present a novel dataset and benchmark, CinePile, specifically designed for authentic long-form video understanding. This paper details our innovative approach for creating a question-answer dataset, utilizing advanced LLMs with human-in-the-loop and building upon human-generated raw data. Our comprehensive dataset comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08813","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/2405.08813/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":"2405.08813","created_at":"2026-07-05T09:23:05.795922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.08813v3","created_at":"2026-07-05T09:23:05.795922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08813","created_at":"2026-07-05T09:23:05.795922+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIRWZLLTW3TG","created_at":"2026-07-05T09:23:05.795922+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIRWZLLTW3TGW6WC","created_at":"2026-07-05T09:23:05.795922+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIRWZLLT","created_at":"2026-07-05T09:23:05.795922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24477","citing_title":"video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02096","citing_title":"LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":298,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06338","citing_title":"StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03635","citing_title":"VidMsg: A Benchmark for Implicit Message Inference in Short Videos","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27828","citing_title":"Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00640","citing_title":"An Attribute-Based Measure of Video Complexity","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05067","citing_title":"LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15342","citing_title":"Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2406.08035","citing_title":"LVBench: An Extreme Long Video Understanding Benchmark","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05425","citing_title":"SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00574","citing_title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2511.15578","citing_title":"AVATAAR: Agentic Video Answering via Temporal Adaptive Alignment and Reasoning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10611","citing_title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11627","citing_title":"POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07593","citing_title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13106","citing_title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIRWZLLTW3TGW6WCRDO4TKNSLU","json":"https://pith.science/pith/MIRWZLLTW3TGW6WCRDO4TKNSLU.json","graph_json":"https://pith.science/api/pith-number/MIRWZLLTW3TGW6WCRDO4TKNSLU/graph.json","events_json":"https://pith.science/api/pith-number/MIRWZLLTW3TGW6WCRDO4TKNSLU/events.json","paper":"https://pith.science/paper/MIRWZLLT"},"agent_actions":{"view_html":"https://pith.science/pith/MIRWZLLTW3TGW6WCRDO4TKNSLU","download_json":"https://pith.science/pith/MIRWZLLTW3TGW6WCRDO4TKNSLU.json","view_paper":"https://pith.science/paper/MIRWZLLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.08813&json=true","fetch_graph":"https://pith.science/api/pith-number/MIRWZLLTW3TGW6WCRDO4TKNSLU/graph.json","fetch_events":"https://pith.science/api/pith-number/MIRWZLLTW3TGW6WCRDO4TKNSLU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIRWZLLTW3TGW6WCRDO4TKNSLU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIRWZLLTW3TGW6WCRDO4TKNSLU/action/storage_attestation","attest_author":"https://pith.science/pith/MIRWZLLTW3TGW6WCRDO4TKNSLU/action/author_attestation","sign_citation":"https://pith.science/pith/MIRWZLLTW3TGW6WCRDO4TKNSLU/action/citation_signature","submit_replication":"https://pith.science/pith/MIRWZLLTW3TGW6WCRDO4TKNSLU/action/replication_record"}},"created_at":"2026-07-05T09:23:05.795922+00:00","updated_at":"2026-07-05T09:23:05.795922+00:00"}