{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EOIPWEHJQIEPBRJ3AP6VX6EIW7","short_pith_number":"pith:EOIPWEHJ","schema_version":"1.0","canonical_sha256":"2390fb10e98208f0c53b03fd5bf888b7f1e7fb374476120b9b836f126dbc14bf","source":{"kind":"arxiv","id":"2607.02959","version":1},"attestation_state":"computed","paper":{"title":"Incentivizing Vision Language Models to Search for Long Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Harsh Goel, Joungbin An, Kristen Grauman, Minkyu Choi, Sahil Shah, Sandeep P. Chinchali, S P Sharan","submitted_at":"2026-07-03T05:05:59Z","abstract_excerpt":"We introduce VSeek, an agentic framework that transforms long-video question answering (LVQA) from a passive, single-pass perception task into a multi-turn retrieval process. VSeek utilizes a natural language-driven search to identify relevant context within long videos and is post-trained with reinforcement learning (RL) to jointly formulate targeted search queries and reason over retrieved clips for LVQA. While RL post-training has revolutionized reasoning in symbolic domains such as mathematics and code, its application to long-video understanding remains hindered by a lack of verified rewa"},"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":"2607.02959","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T05:05:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"874883d17a938e5c29159f8ce449cdccbbc9431fa75501e39b8adbdcfa446440","abstract_canon_sha256":"f0bb59d7716b98eaa5056358fef45f43658f6aec0d0e695d4e40f262deeb846a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:37.909403Z","signature_b64":"TGABBHj2dAPzAQKPhNiqthdKHnIoXMMmtgM42Icd5IKo3+GgNh5x0JzlR8JLBdzw1R7gHnm89fJC/cD0xufGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2390fb10e98208f0c53b03fd5bf888b7f1e7fb374476120b9b836f126dbc14bf","last_reissued_at":"2026-07-07T01:16:37.908952Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:37.908952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incentivizing Vision Language Models to Search for Long Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Harsh Goel, Joungbin An, Kristen Grauman, Minkyu Choi, Sahil Shah, Sandeep P. Chinchali, S P Sharan","submitted_at":"2026-07-03T05:05:59Z","abstract_excerpt":"We introduce VSeek, an agentic framework that transforms long-video question answering (LVQA) from a passive, single-pass perception task into a multi-turn retrieval process. VSeek utilizes a natural language-driven search to identify relevant context within long videos and is post-trained with reinforcement learning (RL) to jointly formulate targeted search queries and reason over retrieved clips for LVQA. While RL post-training has revolutionized reasoning in symbolic domains such as mathematics and code, its application to long-video understanding remains hindered by a lack of verified rewa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02959","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/2607.02959/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":"2607.02959","created_at":"2026-07-07T01:16:37.909010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02959v1","created_at":"2026-07-07T01:16:37.909010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02959","created_at":"2026-07-07T01:16:37.909010+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOIPWEHJQIEP","created_at":"2026-07-07T01:16:37.909010+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOIPWEHJQIEPBRJ3","created_at":"2026-07-07T01:16:37.909010+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOIPWEHJ","created_at":"2026-07-07T01:16:37.909010+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/EOIPWEHJQIEPBRJ3AP6VX6EIW7","json":"https://pith.science/pith/EOIPWEHJQIEPBRJ3AP6VX6EIW7.json","graph_json":"https://pith.science/api/pith-number/EOIPWEHJQIEPBRJ3AP6VX6EIW7/graph.json","events_json":"https://pith.science/api/pith-number/EOIPWEHJQIEPBRJ3AP6VX6EIW7/events.json","paper":"https://pith.science/paper/EOIPWEHJ"},"agent_actions":{"view_html":"https://pith.science/pith/EOIPWEHJQIEPBRJ3AP6VX6EIW7","download_json":"https://pith.science/pith/EOIPWEHJQIEPBRJ3AP6VX6EIW7.json","view_paper":"https://pith.science/paper/EOIPWEHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02959&json=true","fetch_graph":"https://pith.science/api/pith-number/EOIPWEHJQIEPBRJ3AP6VX6EIW7/graph.json","fetch_events":"https://pith.science/api/pith-number/EOIPWEHJQIEPBRJ3AP6VX6EIW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOIPWEHJQIEPBRJ3AP6VX6EIW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOIPWEHJQIEPBRJ3AP6VX6EIW7/action/storage_attestation","attest_author":"https://pith.science/pith/EOIPWEHJQIEPBRJ3AP6VX6EIW7/action/author_attestation","sign_citation":"https://pith.science/pith/EOIPWEHJQIEPBRJ3AP6VX6EIW7/action/citation_signature","submit_replication":"https://pith.science/pith/EOIPWEHJQIEPBRJ3AP6VX6EIW7/action/replication_record"}},"created_at":"2026-07-07T01:16:37.909010+00:00","updated_at":"2026-07-07T01:16:37.909010+00:00"}