{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XBQE3LCEM5QYCQXSYJSED2EAIY","short_pith_number":"pith:XBQE3LCE","schema_version":"1.0","canonical_sha256":"b8604dac4467618142f2c26441e880460245371654563ea2874a7bf68ec2e286","source":{"kind":"arxiv","id":"2503.16032","version":1},"attestation_state":"computed","paper":{"title":"Agentic Keyframe Search for Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Meng-Hao Guo, Shuojin Yang, Sunqi Fan","submitted_at":"2025-03-20T10:58:12Z","abstract_excerpt":"Video question answering (VideoQA) enables machines to extract and comprehend key information from videos through natural language interaction, which is a critical step towards achieving intelligence. However, the demand for a thorough understanding of videos and high computational costs still limit the widespread applications of VideoQA. To address it, we propose Agentic Keyframe Search (AKeyS), a simple yet powerful algorithm for identifying keyframes in the VideoQA task. It can effectively distinguish key information from redundant, irrelevant content by leveraging modern language agents to"},"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":"2503.16032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T10:58:12Z","cross_cats_sorted":[],"title_canon_sha256":"bab100b6257b82ac399f7257dc09b701cc6eab510c7960689efd12d075b03189","abstract_canon_sha256":"27a3cecb566229c9586538a0de84db4b611a0302da73c598a11da195f842a9f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:04.466354Z","signature_b64":"vib9b/aIF+3JZ/H96phqHp/8dXgw6qP4xjbXOISl7TQJP3OBiWEgRaZJWA99DqnaRrrFTIQRQR9X871QE0hvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8604dac4467618142f2c26441e880460245371654563ea2874a7bf68ec2e286","last_reissued_at":"2026-07-05T10:36:04.465651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:04.465651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agentic Keyframe Search for Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Meng-Hao Guo, Shuojin Yang, Sunqi Fan","submitted_at":"2025-03-20T10:58:12Z","abstract_excerpt":"Video question answering (VideoQA) enables machines to extract and comprehend key information from videos through natural language interaction, which is a critical step towards achieving intelligence. However, the demand for a thorough understanding of videos and high computational costs still limit the widespread applications of VideoQA. To address it, we propose Agentic Keyframe Search (AKeyS), a simple yet powerful algorithm for identifying keyframes in the VideoQA task. It can effectively distinguish key information from redundant, irrelevant content by leveraging modern language agents to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16032","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/2503.16032/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":"2503.16032","created_at":"2026-07-05T10:36:04.465717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16032v1","created_at":"2026-07-05T10:36:04.465717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16032","created_at":"2026-07-05T10:36:04.465717+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBQE3LCEM5QY","created_at":"2026-07-05T10:36:04.465717+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBQE3LCEM5QYCQXS","created_at":"2026-07-05T10:36:04.465717+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBQE3LCE","created_at":"2026-07-05T10:36:04.465717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08231","citing_title":"Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29445","citing_title":"Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21444","citing_title":"HiCrew: Hierarchical Reasoning for Long-Form Video Understanding via Question-Aware Multi-Agent Collaboration","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBQE3LCEM5QYCQXSYJSED2EAIY","json":"https://pith.science/pith/XBQE3LCEM5QYCQXSYJSED2EAIY.json","graph_json":"https://pith.science/api/pith-number/XBQE3LCEM5QYCQXSYJSED2EAIY/graph.json","events_json":"https://pith.science/api/pith-number/XBQE3LCEM5QYCQXSYJSED2EAIY/events.json","paper":"https://pith.science/paper/XBQE3LCE"},"agent_actions":{"view_html":"https://pith.science/pith/XBQE3LCEM5QYCQXSYJSED2EAIY","download_json":"https://pith.science/pith/XBQE3LCEM5QYCQXSYJSED2EAIY.json","view_paper":"https://pith.science/paper/XBQE3LCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16032&json=true","fetch_graph":"https://pith.science/api/pith-number/XBQE3LCEM5QYCQXSYJSED2EAIY/graph.json","fetch_events":"https://pith.science/api/pith-number/XBQE3LCEM5QYCQXSYJSED2EAIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBQE3LCEM5QYCQXSYJSED2EAIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBQE3LCEM5QYCQXSYJSED2EAIY/action/storage_attestation","attest_author":"https://pith.science/pith/XBQE3LCEM5QYCQXSYJSED2EAIY/action/author_attestation","sign_citation":"https://pith.science/pith/XBQE3LCEM5QYCQXSYJSED2EAIY/action/citation_signature","submit_replication":"https://pith.science/pith/XBQE3LCEM5QYCQXSYJSED2EAIY/action/replication_record"}},"created_at":"2026-07-05T10:36:04.465717+00:00","updated_at":"2026-07-05T10:36:04.465717+00:00"}