{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G5MBAKPQCYYVM4A7S6WDWVOCMF","short_pith_number":"pith:G5MBAKPQ","schema_version":"1.0","canonical_sha256":"37581029f0163156701f97ac3b55c26150ce10227cda52969ab61994ea484498","source":{"kind":"arxiv","id":"2606.02321","version":1},"attestation_state":"computed","paper":{"title":"Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peisong Wen, Qianqian Xu, Qingming Huang, Siran Dai, Yang Liu","submitted_at":"2026-06-01T14:35:23Z","abstract_excerpt":"Recent advances in large vision-language models have expanded video retrieval from simple text-based search to more flexible scenarios, where users may specify the desired result through both visual examples and textual instructions. In the CVPR 2026 Reason-Aware Composed Video Retrieval Challenge, the system is required to retrieve a target video according to a reference video and a modification instruction. To address this task, we develop Visual Representation-Guided Video-LLM Reasoning for Training-Free Composed Video Retrieval. Our framework first uses frozen DINOv3 models to obtain a com"},"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":"2606.02321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T14:35:23Z","cross_cats_sorted":[],"title_canon_sha256":"5be1157f3a0c9192d1c5359970c03d0eda27f3bf106838719e50f56eff0a4320","abstract_canon_sha256":"d87ff114902a616f9f2374b1051b1657378406c4b5a95de1ce77b775d8f38188"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:56.084588Z","signature_b64":"LP6DsJhwmnNBXfP6C09MA+jrzn0P/wbJL6xKvYwB7F/NtwMBhIEW9jtcD31l8SKZgBIyFo7pXmBHIZgQItLdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37581029f0163156701f97ac3b55c26150ce10227cda52969ab61994ea484498","last_reissued_at":"2026-06-02T03:04:56.084216Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:56.084216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peisong Wen, Qianqian Xu, Qingming Huang, Siran Dai, Yang Liu","submitted_at":"2026-06-01T14:35:23Z","abstract_excerpt":"Recent advances in large vision-language models have expanded video retrieval from simple text-based search to more flexible scenarios, where users may specify the desired result through both visual examples and textual instructions. In the CVPR 2026 Reason-Aware Composed Video Retrieval Challenge, the system is required to retrieve a target video according to a reference video and a modification instruction. To address this task, we develop Visual Representation-Guided Video-LLM Reasoning for Training-Free Composed Video Retrieval. Our framework first uses frozen DINOv3 models to obtain a com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02321","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/2606.02321/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":"2606.02321","created_at":"2026-06-02T03:04:56.084270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02321v1","created_at":"2026-06-02T03:04:56.084270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02321","created_at":"2026-06-02T03:04:56.084270+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5MBAKPQCYYV","created_at":"2026-06-02T03:04:56.084270+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5MBAKPQCYYVM4A7","created_at":"2026-06-02T03:04:56.084270+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5MBAKPQ","created_at":"2026-06-02T03:04:56.084270+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/G5MBAKPQCYYVM4A7S6WDWVOCMF","json":"https://pith.science/pith/G5MBAKPQCYYVM4A7S6WDWVOCMF.json","graph_json":"https://pith.science/api/pith-number/G5MBAKPQCYYVM4A7S6WDWVOCMF/graph.json","events_json":"https://pith.science/api/pith-number/G5MBAKPQCYYVM4A7S6WDWVOCMF/events.json","paper":"https://pith.science/paper/G5MBAKPQ"},"agent_actions":{"view_html":"https://pith.science/pith/G5MBAKPQCYYVM4A7S6WDWVOCMF","download_json":"https://pith.science/pith/G5MBAKPQCYYVM4A7S6WDWVOCMF.json","view_paper":"https://pith.science/paper/G5MBAKPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02321&json=true","fetch_graph":"https://pith.science/api/pith-number/G5MBAKPQCYYVM4A7S6WDWVOCMF/graph.json","fetch_events":"https://pith.science/api/pith-number/G5MBAKPQCYYVM4A7S6WDWVOCMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5MBAKPQCYYVM4A7S6WDWVOCMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5MBAKPQCYYVM4A7S6WDWVOCMF/action/storage_attestation","attest_author":"https://pith.science/pith/G5MBAKPQCYYVM4A7S6WDWVOCMF/action/author_attestation","sign_citation":"https://pith.science/pith/G5MBAKPQCYYVM4A7S6WDWVOCMF/action/citation_signature","submit_replication":"https://pith.science/pith/G5MBAKPQCYYVM4A7S6WDWVOCMF/action/replication_record"}},"created_at":"2026-06-02T03:04:56.084270+00:00","updated_at":"2026-06-02T03:04:56.084270+00:00"}