{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DYOSRTHTFRVBXSTIEE3563CI6M","short_pith_number":"pith:DYOSRTHT","schema_version":"1.0","canonical_sha256":"1e1d28ccf32c6a1bca682137df6c48f32d6f647c5bedf6b0ab723a90969d16df","source":{"kind":"arxiv","id":"2412.11087","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Large Vision-Language Model as User Intent-aware Encoder for Composed Image Retrieval","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dong Jing, Guoxing Yang, Nanyi Fei, Zelong Sun, Zhiwu Lu","submitted_at":"2024-12-15T07:09:02Z","abstract_excerpt":"Composed Image Retrieval (CIR) aims to retrieve target images from candidate set using a hybrid-modality query consisting of a reference image and a relative caption that describes the user intent. Recent studies attempt to utilize Vision-Language Pre-training Models (VLPMs) with various fusion strategies for addressing the task.However, these methods typically fail to simultaneously meet two key requirements of CIR: comprehensively extracting visual information and faithfully following the user intent. In this work, we propose CIR-LVLM, a novel framework that leverages the large vision-langua"},"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":"2412.11087","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-15T07:09:02Z","cross_cats_sorted":[],"title_canon_sha256":"ef4a19dd172168043cb6eb75c1def83fb13709b023ae67d5d8f6a15b060470e2","abstract_canon_sha256":"125ba9a0894a3062b3d18f491190a86616af1751cbf1c0a13a0b73dca77aee32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:27.364501Z","signature_b64":"rdRJkX2fuNyoWUXh3tQ38FVITIo8+Z+g1+V2jJVe4pURhgZLbsUWPNGAHqrmEMIYtfFuBb8Rn80mF6r5/lfMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e1d28ccf32c6a1bca682137df6c48f32d6f647c5bedf6b0ab723a90969d16df","last_reissued_at":"2026-07-05T09:49:27.363998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:27.363998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Large Vision-Language Model as User Intent-aware Encoder for Composed Image Retrieval","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dong Jing, Guoxing Yang, Nanyi Fei, Zelong Sun, Zhiwu Lu","submitted_at":"2024-12-15T07:09:02Z","abstract_excerpt":"Composed Image Retrieval (CIR) aims to retrieve target images from candidate set using a hybrid-modality query consisting of a reference image and a relative caption that describes the user intent. Recent studies attempt to utilize Vision-Language Pre-training Models (VLPMs) with various fusion strategies for addressing the task.However, these methods typically fail to simultaneously meet two key requirements of CIR: comprehensively extracting visual information and faithfully following the user intent. In this work, we propose CIR-LVLM, a novel framework that leverages the large vision-langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11087","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/2412.11087/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":"2412.11087","created_at":"2026-07-05T09:49:27.364082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11087v1","created_at":"2026-07-05T09:49:27.364082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11087","created_at":"2026-07-05T09:49:27.364082+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYOSRTHTFRVB","created_at":"2026-07-05T09:49:27.364082+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYOSRTHTFRVBXSTI","created_at":"2026-07-05T09:49:27.364082+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYOSRTHT","created_at":"2026-07-05T09:49:27.364082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05583","citing_title":"WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M","json":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M.json","graph_json":"https://pith.science/api/pith-number/DYOSRTHTFRVBXSTIEE3563CI6M/graph.json","events_json":"https://pith.science/api/pith-number/DYOSRTHTFRVBXSTIEE3563CI6M/events.json","paper":"https://pith.science/paper/DYOSRTHT"},"agent_actions":{"view_html":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M","download_json":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M.json","view_paper":"https://pith.science/paper/DYOSRTHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11087&json=true","fetch_graph":"https://pith.science/api/pith-number/DYOSRTHTFRVBXSTIEE3563CI6M/graph.json","fetch_events":"https://pith.science/api/pith-number/DYOSRTHTFRVBXSTIEE3563CI6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M/action/storage_attestation","attest_author":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M/action/author_attestation","sign_citation":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M/action/citation_signature","submit_replication":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M/action/replication_record"}},"created_at":"2026-07-05T09:49:27.364082+00:00","updated_at":"2026-07-05T09:49:27.364082+00:00"}