{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TOMQHUEH6MUD45JAQE4SV57TYS","short_pith_number":"pith:TOMQHUEH","schema_version":"1.0","canonical_sha256":"9b9903d087f3283e752081392af7f3c4bb4147e905f0edd48ef6825f74d91aa4","source":{"kind":"arxiv","id":"2606.01113","version":1},"attestation_state":"computed","paper":{"title":"R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Nie, Weili Guan, Yupeng Hu, Zhiheng Fu, Zhiwei Chen, Zixu Li","submitted_at":"2026-05-31T09:20:53Z","abstract_excerpt":"The CoVR-R challenge evaluates composed video retrieval, where a system must retrieve a target video from a large gallery given a reference video and a textual edit instruction. This setting is not a standard video-text retrieval problem: the query is defined by both the visual evidence in the source video and the transformation implied by the edit. A strong embedding model can provide scalable candidate recall, but it may under-express target-side consequences such as state changes, action replacement, object preservation, or temporal consistency. A pairwise multimodal reranker can verify suc"},"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":"2606.01113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T09:20:53Z","cross_cats_sorted":[],"title_canon_sha256":"a11d21fcf76f84fad94f7310a7ffd37a5eae09a7a5c725615941e9d17a73d945","abstract_canon_sha256":"d64721bb5c3a52f62382c54a3c7865cd46c5447e1e40cab1d0cce330477b8127"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:23.855514Z","signature_b64":"F6/J18dwkwxDMlouLikKyn4PepH88f1egzK5ond12T3snpu+kqzH5wPQFBSCRF/TeMm7DfQY02TXuGDVVraCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b9903d087f3283e752081392af7f3c4bb4147e905f0edd48ef6825f74d91aa4","last_reissued_at":"2026-06-02T02:04:23.854901Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:23.854901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Nie, Weili Guan, Yupeng Hu, Zhiheng Fu, Zhiwei Chen, Zixu Li","submitted_at":"2026-05-31T09:20:53Z","abstract_excerpt":"The CoVR-R challenge evaluates composed video retrieval, where a system must retrieve a target video from a large gallery given a reference video and a textual edit instruction. This setting is not a standard video-text retrieval problem: the query is defined by both the visual evidence in the source video and the transformation implied by the edit. A strong embedding model can provide scalable candidate recall, but it may under-express target-side consequences such as state changes, action replacement, object preservation, or temporal consistency. A pairwise multimodal reranker can verify suc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01113","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/2606.01113/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":"2606.01113","created_at":"2026-06-02T02:04:23.854971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01113v1","created_at":"2026-06-02T02:04:23.854971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01113","created_at":"2026-06-02T02:04:23.854971+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOMQHUEH6MUD","created_at":"2026-06-02T02:04:23.854971+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOMQHUEH6MUD45JA","created_at":"2026-06-02T02:04:23.854971+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOMQHUEH","created_at":"2026-06-02T02:04:23.854971+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/TOMQHUEH6MUD45JAQE4SV57TYS","json":"https://pith.science/pith/TOMQHUEH6MUD45JAQE4SV57TYS.json","graph_json":"https://pith.science/api/pith-number/TOMQHUEH6MUD45JAQE4SV57TYS/graph.json","events_json":"https://pith.science/api/pith-number/TOMQHUEH6MUD45JAQE4SV57TYS/events.json","paper":"https://pith.science/paper/TOMQHUEH"},"agent_actions":{"view_html":"https://pith.science/pith/TOMQHUEH6MUD45JAQE4SV57TYS","download_json":"https://pith.science/pith/TOMQHUEH6MUD45JAQE4SV57TYS.json","view_paper":"https://pith.science/paper/TOMQHUEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01113&json=true","fetch_graph":"https://pith.science/api/pith-number/TOMQHUEH6MUD45JAQE4SV57TYS/graph.json","fetch_events":"https://pith.science/api/pith-number/TOMQHUEH6MUD45JAQE4SV57TYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOMQHUEH6MUD45JAQE4SV57TYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOMQHUEH6MUD45JAQE4SV57TYS/action/storage_attestation","attest_author":"https://pith.science/pith/TOMQHUEH6MUD45JAQE4SV57TYS/action/author_attestation","sign_citation":"https://pith.science/pith/TOMQHUEH6MUD45JAQE4SV57TYS/action/citation_signature","submit_replication":"https://pith.science/pith/TOMQHUEH6MUD45JAQE4SV57TYS/action/replication_record"}},"created_at":"2026-06-02T02:04:23.854971+00:00","updated_at":"2026-06-02T02:04:23.854971+00:00"}