{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XCC2NAKLO5P6QTCEHCIS4QIYOJ","short_pith_number":"pith:XCC2NAKL","schema_version":"1.0","canonical_sha256":"b885a6814b775fe84c4438912e41187255c2e7622e5afc3eb8861e651d1b0bbe","source":{"kind":"arxiv","id":"2607.16189","version":1},"attestation_state":"computed","paper":{"title":"Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Gedas Bertasius, Hiromi Wakaki, Mohit Bansal, Oluwatumininu Oguntola, Pranav Wagh, Qiyu Wu, Yulu Pan, Ziyang Wang","submitted_at":"2026-07-17T17:59:27Z","abstract_excerpt":"Grounded long-video question answering (Grounded LVQA) requires answering a question about a long video while localizing the short evidence interval that supports the answer. Recent agentic methods frame this task as multi-turn exploration with a single crop_video(start, end) action, which supports coarse-to-fine narrowing but provides no primitive for fine-to-coarse backtracking. As a result, these agents typically converge prematurely and cannot recover from an early mistake. We propose VideoTreeSearch (VTS), a framework that casts grounded LVQA as iterative self-correcting search over an ad"},"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":"2607.16189","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T17:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"61bd05be18ffec92f8b45e728c2b7fe24881dc520dde698d56f71918d292fc53","abstract_canon_sha256":"89ca8ed78c49b83fe9e52fe7cf7ad8746f5cc30873178777caee573beeafe7b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T02:19:38.611813Z","signature_b64":"j62ML3248qbCSr7AEzuzRP7kNivnsGMstb8zl+TU0oEs56fLshLocQfOUDmiqbfOg6ViowizdIzQEAQXKiWNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b885a6814b775fe84c4438912e41187255c2e7622e5afc3eb8861e651d1b0bbe","last_reissued_at":"2026-07-20T02:19:38.610987Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T02:19:38.610987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Gedas Bertasius, Hiromi Wakaki, Mohit Bansal, Oluwatumininu Oguntola, Pranav Wagh, Qiyu Wu, Yulu Pan, Ziyang Wang","submitted_at":"2026-07-17T17:59:27Z","abstract_excerpt":"Grounded long-video question answering (Grounded LVQA) requires answering a question about a long video while localizing the short evidence interval that supports the answer. Recent agentic methods frame this task as multi-turn exploration with a single crop_video(start, end) action, which supports coarse-to-fine narrowing but provides no primitive for fine-to-coarse backtracking. As a result, these agents typically converge prematurely and cannot recover from an early mistake. We propose VideoTreeSearch (VTS), a framework that casts grounded LVQA as iterative self-correcting search over an ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16189","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/2607.16189/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":"2607.16189","created_at":"2026-07-20T02:19:38.611412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16189v1","created_at":"2026-07-20T02:19:38.611412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16189","created_at":"2026-07-20T02:19:38.611412+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCC2NAKLO5P6","created_at":"2026-07-20T02:19:38.611412+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCC2NAKLO5P6QTCE","created_at":"2026-07-20T02:19:38.611412+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCC2NAKL","created_at":"2026-07-20T02:19:38.611412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ","json":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ.json","graph_json":"https://pith.science/api/pith-number/XCC2NAKLO5P6QTCEHCIS4QIYOJ/graph.json","events_json":"https://pith.science/api/pith-number/XCC2NAKLO5P6QTCEHCIS4QIYOJ/events.json","paper":"https://pith.science/paper/XCC2NAKL"},"agent_actions":{"view_html":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ","download_json":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ.json","view_paper":"https://pith.science/paper/XCC2NAKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16189&json=true","fetch_graph":"https://pith.science/api/pith-number/XCC2NAKLO5P6QTCEHCIS4QIYOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XCC2NAKLO5P6QTCEHCIS4QIYOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ/action/storage_attestation","attest_author":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ/action/author_attestation","sign_citation":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ/action/citation_signature","submit_replication":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ/action/replication_record"}},"created_at":"2026-07-20T02:19:38.611412+00:00","updated_at":"2026-07-20T02:19:38.611412+00:00"}