{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DYOSRTHTFRVBXSTIEE3563CI6M","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"125ba9a0894a3062b3d18f491190a86616af1751cbf1c0a13a0b73dca77aee32","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-15T07:09:02Z","title_canon_sha256":"ef4a19dd172168043cb6eb75c1def83fb13709b023ae67d5d8f6a15b060470e2"},"schema_version":"1.0","source":{"id":"2412.11087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11087","created_at":"2026-07-05T09:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11087v1","created_at":"2026-07-05T09:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11087","created_at":"2026-07-05T09:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"DYOSRTHTFRVB","created_at":"2026-07-05T09:49:27Z"},{"alias_kind":"pith_short_16","alias_value":"DYOSRTHTFRVBXSTI","created_at":"2026-07-05T09:49:27Z"},{"alias_kind":"pith_short_8","alias_value":"DYOSRTHT","created_at":"2026-07-05T09:49:27Z"}],"graph_snapshots":[{"event_id":"sha256:658c2cc80321da4a8777b3900892b20305d31d577dde5e510b584ca20c28b9cb","target":"graph","created_at":"2026-07-05T09:49:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.11087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dong Jing, Guoxing Yang, Nanyi Fei, Zelong Sun, Zhiwu Lu","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-15T07:09:02Z","title":"Leveraging Large Vision-Language Model as User Intent-aware Encoder for Composed Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11087","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c80974338c8ed9623eaf71f4aadce7f54781fb890e6598e3e4d4326fa5893381","target":"record","created_at":"2026-07-05T09:49:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"125ba9a0894a3062b3d18f491190a86616af1751cbf1c0a13a0b73dca77aee32","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-15T07:09:02Z","title_canon_sha256":"ef4a19dd172168043cb6eb75c1def83fb13709b023ae67d5d8f6a15b060470e2"},"schema_version":"1.0","source":{"id":"2412.11087","kind":"arxiv","version":1}},"canonical_sha256":"1e1d28ccf32c6a1bca682137df6c48f32d6f647c5bedf6b0ab723a90969d16df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e1d28ccf32c6a1bca682137df6c48f32d6f647c5bedf6b0ab723a90969d16df","first_computed_at":"2026-07-05T09:49:27.363998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:27.363998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rdRJkX2fuNyoWUXh3tQ38FVITIo8+Z+g1+V2jJVe4pURhgZLbsUWPNGAHqrmEMIYtfFuBb8Rn80mF6r5/lfMAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:27.364501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c80974338c8ed9623eaf71f4aadce7f54781fb890e6598e3e4d4326fa5893381","sha256:658c2cc80321da4a8777b3900892b20305d31d577dde5e510b584ca20c28b9cb"],"state_sha256":"70ff1698eb9807e833d781eef7c5fb5c9e7927b4e5157503271c21decb1de4a2"}