{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UIADQ6SGZEEZHALKO36FPTEZEP","short_pith_number":"pith:UIADQ6SG","schema_version":"1.0","canonical_sha256":"a200387a46c90993816a76fc57cc9923d3b98eda55eebd0a353cdaa0d1ff2395","source":{"kind":"arxiv","id":"2403.14743","version":3},"attestation_state":"computed","paper":{"title":"VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmad Mahmood, Ashmal Vayani, Fahad Shahbaz Khan, Muzammal Naseer, Salman Khan","submitted_at":"2024-03-21T18:00:00Z","abstract_excerpt":"Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In contrast, this paper introduces a Video Understanding and Reasoning Framework (VURF) based on the reasoning power of LLMs. Ours is a novel approach to extend the utility of LLMs in the context of video tasks, leveraging their capacity to generalize from minimal input and output demonstrations within a contextual framework. We harness their contextual learning "},"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":"2403.14743","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T18:00:00Z","cross_cats_sorted":[],"title_canon_sha256":"545e5bd1c20b8c80b9f7cee0c272f47fd3e2e9086f3f153f1a5d22a72a38f697","abstract_canon_sha256":"05271cc886c4ef433bfc8c74e6341747fd695b1f7b44a82fce89587c1eb90477"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:08.833144Z","signature_b64":"30DW7nLciIZVsabtOHGQt992qbvpllquS7b8AzUq9gbGcTVK8j5Mf3HLPCZLD+xtLnvBctxHGy2QILN2DHRuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a200387a46c90993816a76fc57cc9923d3b98eda55eebd0a353cdaa0d1ff2395","last_reissued_at":"2026-07-05T10:27:08.832647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:08.832647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmad Mahmood, Ashmal Vayani, Fahad Shahbaz Khan, Muzammal Naseer, Salman Khan","submitted_at":"2024-03-21T18:00:00Z","abstract_excerpt":"Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In contrast, this paper introduces a Video Understanding and Reasoning Framework (VURF) based on the reasoning power of LLMs. Ours is a novel approach to extend the utility of LLMs in the context of video tasks, leveraging their capacity to generalize from minimal input and output demonstrations within a contextual framework. We harness their contextual learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14743","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/2403.14743/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":"2403.14743","created_at":"2026-07-05T10:27:08.832706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14743v3","created_at":"2026-07-05T10:27:08.832706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14743","created_at":"2026-07-05T10:27:08.832706+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIADQ6SGZEEZ","created_at":"2026-07-05T10:27:08.832706+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIADQ6SGZEEZHALK","created_at":"2026-07-05T10:27:08.832706+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIADQ6SG","created_at":"2026-07-05T10:27:08.832706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07994","citing_title":"STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UIADQ6SGZEEZHALKO36FPTEZEP","json":"https://pith.science/pith/UIADQ6SGZEEZHALKO36FPTEZEP.json","graph_json":"https://pith.science/api/pith-number/UIADQ6SGZEEZHALKO36FPTEZEP/graph.json","events_json":"https://pith.science/api/pith-number/UIADQ6SGZEEZHALKO36FPTEZEP/events.json","paper":"https://pith.science/paper/UIADQ6SG"},"agent_actions":{"view_html":"https://pith.science/pith/UIADQ6SGZEEZHALKO36FPTEZEP","download_json":"https://pith.science/pith/UIADQ6SGZEEZHALKO36FPTEZEP.json","view_paper":"https://pith.science/paper/UIADQ6SG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14743&json=true","fetch_graph":"https://pith.science/api/pith-number/UIADQ6SGZEEZHALKO36FPTEZEP/graph.json","fetch_events":"https://pith.science/api/pith-number/UIADQ6SGZEEZHALKO36FPTEZEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIADQ6SGZEEZHALKO36FPTEZEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIADQ6SGZEEZHALKO36FPTEZEP/action/storage_attestation","attest_author":"https://pith.science/pith/UIADQ6SGZEEZHALKO36FPTEZEP/action/author_attestation","sign_citation":"https://pith.science/pith/UIADQ6SGZEEZHALKO36FPTEZEP/action/citation_signature","submit_replication":"https://pith.science/pith/UIADQ6SGZEEZHALKO36FPTEZEP/action/replication_record"}},"created_at":"2026-07-05T10:27:08.832706+00:00","updated_at":"2026-07-05T10:27:08.832706+00:00"}