{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B54UADACZ2FQQEO2XXJTXJPDRU","short_pith_number":"pith:B54UADAC","schema_version":"1.0","canonical_sha256":"0f79400c02ce8b0811dabdd33ba5e38d2f3324d0ac4094eaca2c81958d33782e","source":{"kind":"arxiv","id":"2606.09641","version":1},"attestation_state":"computed","paper":{"title":"MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Luo, Haochen Liang, Hao Zhou, Jie Zhang, Qilang Ye","submitted_at":"2026-06-08T15:36:15Z","abstract_excerpt":"The dominant paradigm in video retrieval relies on embedding-based full-corpus scanning, which suffers from inherent computational inefficiency and the semantic asymmetry between information-dense videos and sparse textual queries. To bridge this gap, we introduce \\textbf{MAVIS}, a novel multi-agent framework that rethinks retrieval as cooperative reasoning rather than brute-force search. MAVIS first bridges the granularity mismatch by parsing raw videos into a \\textbf{Structured Semantic Library}, enabling explicit attribute-level indexing. During retrieval, a planner decomposes complex user "},"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":"2606.09641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T15:36:15Z","cross_cats_sorted":[],"title_canon_sha256":"c9aa7d8179f838485e964bc7edb8626872dd7a96a722a42f967978e24d198df3","abstract_canon_sha256":"19e87bee1c12400afa2e24a9b6ab4915e9ec0d302e8756eac84acf74fe90e580"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:00.774505Z","signature_b64":"Uc+LrUGf/VhpbQzhP/xV5VjXHSfv4Cf/tswY/h/pW+qgb0KdhnQs22bFufTbtce4XwML99D32ewTkrKLJbEvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f79400c02ce8b0811dabdd33ba5e38d2f3324d0ac4094eaca2c81958d33782e","last_reissued_at":"2026-06-09T02:09:00.773424Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:00.773424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Luo, Haochen Liang, Hao Zhou, Jie Zhang, Qilang Ye","submitted_at":"2026-06-08T15:36:15Z","abstract_excerpt":"The dominant paradigm in video retrieval relies on embedding-based full-corpus scanning, which suffers from inherent computational inefficiency and the semantic asymmetry between information-dense videos and sparse textual queries. To bridge this gap, we introduce \\textbf{MAVIS}, a novel multi-agent framework that rethinks retrieval as cooperative reasoning rather than brute-force search. MAVIS first bridges the granularity mismatch by parsing raw videos into a \\textbf{Structured Semantic Library}, enabling explicit attribute-level indexing. During retrieval, a planner decomposes complex user "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09641","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/2606.09641/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":"2606.09641","created_at":"2026-06-09T02:09:00.773614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09641v1","created_at":"2026-06-09T02:09:00.773614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09641","created_at":"2026-06-09T02:09:00.773614+00:00"},{"alias_kind":"pith_short_12","alias_value":"B54UADACZ2FQ","created_at":"2026-06-09T02:09:00.773614+00:00"},{"alias_kind":"pith_short_16","alias_value":"B54UADACZ2FQQEO2","created_at":"2026-06-09T02:09:00.773614+00:00"},{"alias_kind":"pith_short_8","alias_value":"B54UADAC","created_at":"2026-06-09T02:09:00.773614+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/B54UADACZ2FQQEO2XXJTXJPDRU","json":"https://pith.science/pith/B54UADACZ2FQQEO2XXJTXJPDRU.json","graph_json":"https://pith.science/api/pith-number/B54UADACZ2FQQEO2XXJTXJPDRU/graph.json","events_json":"https://pith.science/api/pith-number/B54UADACZ2FQQEO2XXJTXJPDRU/events.json","paper":"https://pith.science/paper/B54UADAC"},"agent_actions":{"view_html":"https://pith.science/pith/B54UADACZ2FQQEO2XXJTXJPDRU","download_json":"https://pith.science/pith/B54UADACZ2FQQEO2XXJTXJPDRU.json","view_paper":"https://pith.science/paper/B54UADAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09641&json=true","fetch_graph":"https://pith.science/api/pith-number/B54UADACZ2FQQEO2XXJTXJPDRU/graph.json","fetch_events":"https://pith.science/api/pith-number/B54UADACZ2FQQEO2XXJTXJPDRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B54UADACZ2FQQEO2XXJTXJPDRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B54UADACZ2FQQEO2XXJTXJPDRU/action/storage_attestation","attest_author":"https://pith.science/pith/B54UADACZ2FQQEO2XXJTXJPDRU/action/author_attestation","sign_citation":"https://pith.science/pith/B54UADACZ2FQQEO2XXJTXJPDRU/action/citation_signature","submit_replication":"https://pith.science/pith/B54UADACZ2FQQEO2XXJTXJPDRU/action/replication_record"}},"created_at":"2026-06-09T02:09:00.773614+00:00","updated_at":"2026-06-09T02:09:00.773614+00:00"}