{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FCUMUHGLKTB3VCTD4Y6ELMW4RW","short_pith_number":"pith:FCUMUHGL","schema_version":"1.0","canonical_sha256":"28a8ca1ccb54c3ba8a63e63c45b2dc8dbf181ee8050f010416464e059499a92c","source":{"kind":"arxiv","id":"2606.09064","version":1},"attestation_state":"computed","paper":{"title":"See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bowen Liu, Chen Jia, Naiming Liu, Shuning Wang, Shuo Nie, Weijie Zhu, YiNuo Lu, Yumeng Zhang, Zhiheng Wu","submitted_at":"2026-06-08T06:02:05Z","abstract_excerpt":"Recent advances in Video Large Language Models (Video-LLMs) have enabled performance on long-video understanding tasks. However, existing methods still face two key limitations: evidence acquisition often relies on a single search intent, and answer generation lacks an effective visual feedback mechanism. To address these limitations, we propose \\textbf{CoVER}, a Comprehensive Visual Evidence and Reflection framework for long-video understanding. CoVER enables Video-LLMs to \\textbf{See More} by dynamically gathering query-expanded visual evidence, and \\textbf{Think Deeper} by verifying draft a"},"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":"2606.09064","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T06:02:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4181653bd730ffb6b00dd431c125272ff15b0c631f7b2586dcab7a1480c570de","abstract_canon_sha256":"ce251e68a8a539b7bb96b3b7b3ee02ad3a7eeb212cf6fb8c7bcecb93c65ed174"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:56.522258Z","signature_b64":"6dlZUVVjNvtMlW3uWMKp17pH7sWb8uq7g+klLBOfFGc4QPAxzZE5H225tAaGx3KK6KakMMhP5UncFKz+r5YBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28a8ca1ccb54c3ba8a63e63c45b2dc8dbf181ee8050f010416464e059499a92c","last_reissued_at":"2026-06-09T02:07:56.520944Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:56.520944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bowen Liu, Chen Jia, Naiming Liu, Shuning Wang, Shuo Nie, Weijie Zhu, YiNuo Lu, Yumeng Zhang, Zhiheng Wu","submitted_at":"2026-06-08T06:02:05Z","abstract_excerpt":"Recent advances in Video Large Language Models (Video-LLMs) have enabled performance on long-video understanding tasks. However, existing methods still face two key limitations: evidence acquisition often relies on a single search intent, and answer generation lacks an effective visual feedback mechanism. To address these limitations, we propose \\textbf{CoVER}, a Comprehensive Visual Evidence and Reflection framework for long-video understanding. CoVER enables Video-LLMs to \\textbf{See More} by dynamically gathering query-expanded visual evidence, and \\textbf{Think Deeper} by verifying draft a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09064","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/2606.09064/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":"2606.09064","created_at":"2026-06-09T02:07:56.521109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09064v1","created_at":"2026-06-09T02:07:56.521109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09064","created_at":"2026-06-09T02:07:56.521109+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCUMUHGLKTB3","created_at":"2026-06-09T02:07:56.521109+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCUMUHGLKTB3VCTD","created_at":"2026-06-09T02:07:56.521109+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCUMUHGL","created_at":"2026-06-09T02:07:56.521109+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/FCUMUHGLKTB3VCTD4Y6ELMW4RW","json":"https://pith.science/pith/FCUMUHGLKTB3VCTD4Y6ELMW4RW.json","graph_json":"https://pith.science/api/pith-number/FCUMUHGLKTB3VCTD4Y6ELMW4RW/graph.json","events_json":"https://pith.science/api/pith-number/FCUMUHGLKTB3VCTD4Y6ELMW4RW/events.json","paper":"https://pith.science/paper/FCUMUHGL"},"agent_actions":{"view_html":"https://pith.science/pith/FCUMUHGLKTB3VCTD4Y6ELMW4RW","download_json":"https://pith.science/pith/FCUMUHGLKTB3VCTD4Y6ELMW4RW.json","view_paper":"https://pith.science/paper/FCUMUHGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09064&json=true","fetch_graph":"https://pith.science/api/pith-number/FCUMUHGLKTB3VCTD4Y6ELMW4RW/graph.json","fetch_events":"https://pith.science/api/pith-number/FCUMUHGLKTB3VCTD4Y6ELMW4RW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCUMUHGLKTB3VCTD4Y6ELMW4RW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCUMUHGLKTB3VCTD4Y6ELMW4RW/action/storage_attestation","attest_author":"https://pith.science/pith/FCUMUHGLKTB3VCTD4Y6ELMW4RW/action/author_attestation","sign_citation":"https://pith.science/pith/FCUMUHGLKTB3VCTD4Y6ELMW4RW/action/citation_signature","submit_replication":"https://pith.science/pith/FCUMUHGLKTB3VCTD4Y6ELMW4RW/action/replication_record"}},"created_at":"2026-06-09T02:07:56.521109+00:00","updated_at":"2026-06-09T02:07:56.521109+00:00"}