{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XCC2NAKLO5P6QTCEHCIS4QIYOJ","short_pith_number":"pith:XCC2NAKL","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"},"canonical_sha256":"b885a6814b775fe84c4438912e41187255c2e7622e5afc3eb8861e651d1b0bbe","source":{"kind":"arxiv","id":"2607.16189","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XCC2NAKLO5P6QTCEHCIS4QIYOJ","target":"record","payload":{"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"},"canonical_sha256":"b885a6814b775fe84c4438912e41187255c2e7622e5afc3eb8861e651d1b0bbe","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"},"source_kind":"arxiv","source_id":"2607.16189","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-20T02:19:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PbH6y/iYxnjn41GMEs6JNdJmkiS2mcaNxcbkWqWWOfqfK77OTbsRV19t5AbZ1M9aGgfQT8/i0HN5UVWokYXBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:25:52.878163Z"},"content_sha256":"0bb6de43ad513c6b52ef3852997a34ee6be6b47d3ad89c59d9a48c3bc09dd818","schema_version":"1.0","event_id":"sha256:0bb6de43ad513c6b52ef3852997a34ee6be6b47d3ad89c59d9a48c3bc09dd818"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XCC2NAKLO5P6QTCEHCIS4QIYOJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-20T02:19:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F4vY7IxWfrJECEm/YKVkqAICQyY0flq5eRpl+OYBE2doZGkZjZGATZQQ3ZFbnx/Wn3XMPoBl5FsIkgp4zikQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:25:52.879197Z"},"content_sha256":"27cf0df92bc38cc655f69248e02e65b963a2e60c2029595061336b10b3c6906d","schema_version":"1.0","event_id":"sha256:27cf0df92bc38cc655f69248e02e65b963a2e60c2029595061336b10b3c6906d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ/bundle.json","state_url":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T00:25:52Z","links":{"resolver":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ","bundle":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ/bundle.json","state":"https://pith.science/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCC2NAKLO5P6QTCEHCIS4QIYOJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7dvr7+T9fVK17fhzjrfJqyv5ckZhjdDyG+gBud9gjH/49OnS6GZBFlZlqu70h4ZEba3Z+oGu6Nac5V6XuonkBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:25:52.885566Z","bundle_sha256":"aa46cce1acdedafffe4aadda5db9b299ecbf1514f5131330296b7a1f1e7581d8"}}