{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VRRJWUVO2RXTMYXQCBB6INCX4R","short_pith_number":"pith:VRRJWUVO","schema_version":"1.0","canonical_sha256":"ac629b52aed46f3662f01043e43457e45ac8c41644632dc1b9d1db4e2cc4e478","source":{"kind":"arxiv","id":"2411.14794","version":1},"attestation_state":"computed","paper":{"title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Hairong Shi, Le Zhuo, Shifeng Zhang, Si Liu, Songhao Han, Wei Huang, Xiaojuan Qi, Xiu Su, Xu Zhou, Yue Liao","submitted_at":"2024-11-22T08:33:36Z","abstract_excerpt":"The advancement of Large Vision Language Models (LVLMs) has significantly improved multimodal understanding, yet challenges remain in video reasoning tasks due to the scarcity of high-quality, large-scale datasets. Existing video question-answering (VideoQA) datasets often rely on costly manual annotations with insufficient granularity or automatic construction methods with redundant frame-by-frame analysis, limiting their scalability and effectiveness for complex reasoning. To address these challenges, we introduce VideoEspresso, a novel dataset that features VideoQA pairs preserving essentia"},"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":"2411.14794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T08:33:36Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e659e872010cf379d0ea481c3916ba941a0ed486abd8dd52eab727e27f21369d","abstract_canon_sha256":"c9d2dc81443e28def9728a53a741316d73d7c43e42903ef58d2f3028b632667e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:12.000518Z","signature_b64":"uBDlXGCjr5R/+Vg6ORs4lbwoViINUlsC/0VURSmmqIz5JC07TRE1DUNPMbw8yuKg9WEg96j2WuiWNFeW0Ip6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac629b52aed46f3662f01043e43457e45ac8c41644632dc1b9d1db4e2cc4e478","last_reissued_at":"2026-07-05T09:39:12.000063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:12.000063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Hairong Shi, Le Zhuo, Shifeng Zhang, Si Liu, Songhao Han, Wei Huang, Xiaojuan Qi, Xiu Su, Xu Zhou, Yue Liao","submitted_at":"2024-11-22T08:33:36Z","abstract_excerpt":"The advancement of Large Vision Language Models (LVLMs) has significantly improved multimodal understanding, yet challenges remain in video reasoning tasks due to the scarcity of high-quality, large-scale datasets. Existing video question-answering (VideoQA) datasets often rely on costly manual annotations with insufficient granularity or automatic construction methods with redundant frame-by-frame analysis, limiting their scalability and effectiveness for complex reasoning. To address these challenges, we introduce VideoEspresso, a novel dataset that features VideoQA pairs preserving essentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14794","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/2411.14794/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":"2411.14794","created_at":"2026-07-05T09:39:12.000122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14794v1","created_at":"2026-07-05T09:39:12.000122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14794","created_at":"2026-07-05T09:39:12.000122+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRRJWUVO2RXT","created_at":"2026-07-05T09:39:12.000122+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRRJWUVO2RXTMYXQ","created_at":"2026-07-05T09:39:12.000122+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRRJWUVO","created_at":"2026-07-05T09:39:12.000122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.14171","citing_title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15342","citing_title":"Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":160,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20473","citing_title":"Video-ToC: Video Tree-of-Cue Reasoning","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R","json":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R.json","graph_json":"https://pith.science/api/pith-number/VRRJWUVO2RXTMYXQCBB6INCX4R/graph.json","events_json":"https://pith.science/api/pith-number/VRRJWUVO2RXTMYXQCBB6INCX4R/events.json","paper":"https://pith.science/paper/VRRJWUVO"},"agent_actions":{"view_html":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R","download_json":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R.json","view_paper":"https://pith.science/paper/VRRJWUVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14794&json=true","fetch_graph":"https://pith.science/api/pith-number/VRRJWUVO2RXTMYXQCBB6INCX4R/graph.json","fetch_events":"https://pith.science/api/pith-number/VRRJWUVO2RXTMYXQCBB6INCX4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R/action/storage_attestation","attest_author":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R/action/author_attestation","sign_citation":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R/action/citation_signature","submit_replication":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R/action/replication_record"}},"created_at":"2026-07-05T09:39:12.000122+00:00","updated_at":"2026-07-05T09:39:12.000122+00:00"}