{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XCC2NAKLO5P6QTCEHCIS4QIYOJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"89ca8ed78c49b83fe9e52fe7cf7ad8746f5cc30873178777caee573beeafe7b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T17:59:27Z","title_canon_sha256":"61bd05be18ffec92f8b45e728c2b7fe24881dc520dde698d56f71918d292fc53"},"schema_version":"1.0","source":{"id":"2607.16189","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16189","created_at":"2026-07-20T02:19:38Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16189v1","created_at":"2026-07-20T02:19:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16189","created_at":"2026-07-20T02:19:38Z"},{"alias_kind":"pith_short_12","alias_value":"XCC2NAKLO5P6","created_at":"2026-07-20T02:19:38Z"},{"alias_kind":"pith_short_16","alias_value":"XCC2NAKLO5P6QTCE","created_at":"2026-07-20T02:19:38Z"},{"alias_kind":"pith_short_8","alias_value":"XCC2NAKL","created_at":"2026-07-20T02:19:38Z"}],"graph_snapshots":[{"event_id":"sha256:27cf0df92bc38cc655f69248e02e65b963a2e60c2029595061336b10b3c6906d","target":"graph","created_at":"2026-07-20T02:19:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.16189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ce Zhang, Gedas Bertasius, Hiromi Wakaki, Mohit Bansal, Oluwatumininu Oguntola, Pranav Wagh, Qiyu Wu, Yulu Pan, Ziyang Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T17:59:27Z","title":"Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16189","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0bb6de43ad513c6b52ef3852997a34ee6be6b47d3ad89c59d9a48c3bc09dd818","target":"record","created_at":"2026-07-20T02:19:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"89ca8ed78c49b83fe9e52fe7cf7ad8746f5cc30873178777caee573beeafe7b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T17:59:27Z","title_canon_sha256":"61bd05be18ffec92f8b45e728c2b7fe24881dc520dde698d56f71918d292fc53"},"schema_version":"1.0","source":{"id":"2607.16189","kind":"arxiv","version":1}},"canonical_sha256":"b885a6814b775fe84c4438912e41187255c2e7622e5afc3eb8861e651d1b0bbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b885a6814b775fe84c4438912e41187255c2e7622e5afc3eb8861e651d1b0bbe","first_computed_at":"2026-07-20T02:19:38.610987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T02:19:38.610987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j62ML3248qbCSr7AEzuzRP7kNivnsGMstb8zl+TU0oEs56fLshLocQfOUDmiqbfOg6ViowizdIzQEAQXKiWNAw==","signature_status":"signed_v1","signed_at":"2026-07-20T02:19:38.611813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16189","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bb6de43ad513c6b52ef3852997a34ee6be6b47d3ad89c59d9a48c3bc09dd818","sha256:27cf0df92bc38cc655f69248e02e65b963a2e60c2029595061336b10b3c6906d"],"state_sha256":"fc9e284de91df714a3df92afb3d3ec7b2f467d51677b2c5b2eed594ca0b799cf"}