{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DYOSRTHTFRVBXSTIEE3563CI6M","short_pith_number":"pith:DYOSRTHT","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"},"canonical_sha256":"1e1d28ccf32c6a1bca682137df6c48f32d6f647c5bedf6b0ab723a90969d16df","source":{"kind":"arxiv","id":"2412.11087","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DYOSRTHTFRVBXSTIEE3563CI6M","target":"record","payload":{"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"},"canonical_sha256":"1e1d28ccf32c6a1bca682137df6c48f32d6f647c5bedf6b0ab723a90969d16df","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"},"source_kind":"arxiv","source_id":"2412.11087","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vwfClf/Ll8lQ7pvObdxL2w5ZkvlP/IvoslGvu5ATZFLuAnovlmI3Su72I174ecQKt6mlF7jyeBIHmEcQ9SexDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:13:19.536515Z"},"content_sha256":"c80974338c8ed9623eaf71f4aadce7f54781fb890e6598e3e4d4326fa5893381","schema_version":"1.0","event_id":"sha256:c80974338c8ed9623eaf71f4aadce7f54781fb890e6598e3e4d4326fa5893381"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DYOSRTHTFRVBXSTIEE3563CI6M","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EgSLzkUVr9QTMS/bzcjvcrrDdOo8rNuNwlJvLvKweYPbw7/C5o64Yv2785XTR+BB906fcv8YVIX/5iEuRRBAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:13:19.536874Z"},"content_sha256":"658c2cc80321da4a8777b3900892b20305d31d577dde5e510b584ca20c28b9cb","schema_version":"1.0","event_id":"sha256:658c2cc80321da4a8777b3900892b20305d31d577dde5e510b584ca20c28b9cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M/bundle.json","state_url":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DYOSRTHTFRVBXSTIEE3563CI6M/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T17:13:19Z","links":{"resolver":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M","bundle":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M/bundle.json","state":"https://pith.science/pith/DYOSRTHTFRVBXSTIEE3563CI6M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DYOSRTHTFRVBXSTIEE3563CI6M/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q80lFzjI5UlmXxWsK5zn34LYcirCjS/eqmnB4rvNouKlcbjrOwN0PjDIZC7u+x46vQA85GQQsUjOih1sQNioCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:13:19.538741Z","bundle_sha256":"6936b1e033bd251b06523fe6c41ee98d09c0d453977d06ab13f1e13d120bafef"}}