{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BC32GMNFOK5IV7KZZBEKDCSGPF","short_pith_number":"pith:BC32GMNF","schema_version":"1.0","canonical_sha256":"08b7a331a572ba8afd59c848a18a4679741b3c1d4b239d5478514af7e4ed1bbe","source":{"kind":"arxiv","id":"2501.05037","version":2},"attestation_state":"computed","paper":{"title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hai Ci, Haozhe Zhao, Qing Li, Rujie Wu, Xiaojian Ma, Yizhou Wang, Yue Fan, Yuxuan Wang","submitted_at":"2025-01-09T07:51:14Z","abstract_excerpt":"This paper introduces LongViTU, a large-scale (~121k QA pairs, ~900h videos), automatically generated dataset for long-form video understanding. We propose a systematic approach that organizes videos into a hierarchical tree structure for QA generation and incorporates self-revision mechanisms to ensure high-quality QA pairs. Each QA pair in LongViTU features: 1) long-term context (average certificate length of 4.6 minutes); 2) rich knowledge and condensed reasoning (commonsense, causality, planning, etc.)). We also offer explicit timestamp annotations of relevant events for each QA pair. We h"},"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":"2501.05037","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T07:51:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"05c2ff597bb8968c324ba3721ed41eaff53d581f73564bd477a13558a304931e","abstract_canon_sha256":"ce7ceccc88c5c9fca7b626489d903bbba65e47a6c7c88a48c47c11520fe1f9f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:16.133473Z","signature_b64":"7Lf1F5pNabo2elGXLvUsbpB95Pc0nWISOOgdnq54fbJ/uIz3PGbQNaswx+LSzPNgVrPBJUBMWUkjquMALe9UAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b7a331a572ba8afd59c848a18a4679741b3c1d4b239d5478514af7e4ed1bbe","last_reissued_at":"2026-07-05T10:40:16.132960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:16.132960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hai Ci, Haozhe Zhao, Qing Li, Rujie Wu, Xiaojian Ma, Yizhou Wang, Yue Fan, Yuxuan Wang","submitted_at":"2025-01-09T07:51:14Z","abstract_excerpt":"This paper introduces LongViTU, a large-scale (~121k QA pairs, ~900h videos), automatically generated dataset for long-form video understanding. We propose a systematic approach that organizes videos into a hierarchical tree structure for QA generation and incorporates self-revision mechanisms to ensure high-quality QA pairs. Each QA pair in LongViTU features: 1) long-term context (average certificate length of 4.6 minutes); 2) rich knowledge and condensed reasoning (commonsense, causality, planning, etc.)). We also offer explicit timestamp annotations of relevant events for each QA pair. We h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05037","kind":"arxiv","version":2},"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/2501.05037/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":"2501.05037","created_at":"2026-07-05T10:40:16.133027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05037v2","created_at":"2026-07-05T10:40:16.133027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05037","created_at":"2026-07-05T10:40:16.133027+00:00"},{"alias_kind":"pith_short_12","alias_value":"BC32GMNFOK5I","created_at":"2026-07-05T10:40:16.133027+00:00"},{"alias_kind":"pith_short_16","alias_value":"BC32GMNFOK5IV7KZ","created_at":"2026-07-05T10:40:16.133027+00:00"},{"alias_kind":"pith_short_8","alias_value":"BC32GMNF","created_at":"2026-07-05T10:40:16.133027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05259","citing_title":"VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BC32GMNFOK5IV7KZZBEKDCSGPF","json":"https://pith.science/pith/BC32GMNFOK5IV7KZZBEKDCSGPF.json","graph_json":"https://pith.science/api/pith-number/BC32GMNFOK5IV7KZZBEKDCSGPF/graph.json","events_json":"https://pith.science/api/pith-number/BC32GMNFOK5IV7KZZBEKDCSGPF/events.json","paper":"https://pith.science/paper/BC32GMNF"},"agent_actions":{"view_html":"https://pith.science/pith/BC32GMNFOK5IV7KZZBEKDCSGPF","download_json":"https://pith.science/pith/BC32GMNFOK5IV7KZZBEKDCSGPF.json","view_paper":"https://pith.science/paper/BC32GMNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05037&json=true","fetch_graph":"https://pith.science/api/pith-number/BC32GMNFOK5IV7KZZBEKDCSGPF/graph.json","fetch_events":"https://pith.science/api/pith-number/BC32GMNFOK5IV7KZZBEKDCSGPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BC32GMNFOK5IV7KZZBEKDCSGPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BC32GMNFOK5IV7KZZBEKDCSGPF/action/storage_attestation","attest_author":"https://pith.science/pith/BC32GMNFOK5IV7KZZBEKDCSGPF/action/author_attestation","sign_citation":"https://pith.science/pith/BC32GMNFOK5IV7KZZBEKDCSGPF/action/citation_signature","submit_replication":"https://pith.science/pith/BC32GMNFOK5IV7KZZBEKDCSGPF/action/replication_record"}},"created_at":"2026-07-05T10:40:16.133027+00:00","updated_at":"2026-07-05T10:40:16.133027+00:00"}