{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EKQV6T3LMDZWWJERPGPDL2T4PW","short_pith_number":"pith:EKQV6T3L","schema_version":"1.0","canonical_sha256":"22a15f4f6b60f36b2491799e35ea7c7d994044b87abe176cb31b241e6c9bdcc8","source":{"kind":"arxiv","id":"2312.08924","version":2},"attestation_state":"computed","paper":{"title":"Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanghua Ye, Shaogang Gong, Shitong Sun","submitted_at":"2023-12-14T13:31:01Z","abstract_excerpt":"Composed image retrieval attempts to retrieve an image of interest from gallery images through a composed query of a reference image and its corresponding modified text. It has recently attracted attention due to the collaboration of information-rich images and concise language to precisely express the requirements of target images. Most current composed image retrieval methods follow a supervised learning approach to training on a costly triplet dataset composed of a reference image, modified text, and a corresponding target image. To avoid difficult to-obtain labeled triplet training data, z"},"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":"2312.08924","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T13:31:01Z","cross_cats_sorted":[],"title_canon_sha256":"92b9a58a44e51f59752cd0ffbdcb71a60371c7c1563d0afd61ecb555cda294f8","abstract_canon_sha256":"9f86bea3dcb31ce0de1240042880e1f420e171bf7f6534be0b8e38b762b6c61b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:58.855759Z","signature_b64":"RdXmvAJe5BoOOUq9rstVG+YH00+409ob5i54BEsP0dBh8plRJfydZioIGHGlIBzCcmGq6EzbPy9XrwiBJklBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22a15f4f6b60f36b2491799e35ea7c7d994044b87abe176cb31b241e6c9bdcc8","last_reissued_at":"2026-07-05T07:59:58.855200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:58.855200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanghua Ye, Shaogang Gong, Shitong Sun","submitted_at":"2023-12-14T13:31:01Z","abstract_excerpt":"Composed image retrieval attempts to retrieve an image of interest from gallery images through a composed query of a reference image and its corresponding modified text. It has recently attracted attention due to the collaboration of information-rich images and concise language to precisely express the requirements of target images. Most current composed image retrieval methods follow a supervised learning approach to training on a costly triplet dataset composed of a reference image, modified text, and a corresponding target image. To avoid difficult to-obtain labeled triplet training data, z"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08924","kind":"arxiv","version":2},"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/2312.08924/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":"2312.08924","created_at":"2026-07-05T07:59:58.855275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08924v2","created_at":"2026-07-05T07:59:58.855275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08924","created_at":"2026-07-05T07:59:58.855275+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKQV6T3LMDZW","created_at":"2026-07-05T07:59:58.855275+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKQV6T3LMDZWWJER","created_at":"2026-07-05T07:59:58.855275+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKQV6T3L","created_at":"2026-07-05T07:59:58.855275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31222","citing_title":"Thinking Before Retrieving: Robust Zero-Shot Composed Image Retrieval via Strategic Planning and Self-Criticism","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08411","citing_title":"A Sketch+Text Composed Image Retrieval Dataset for Thangka","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02892","citing_title":"AlbumFill: Album-Guided Reasoning and Retrieval for Personalized Image Completion","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKQV6T3LMDZWWJERPGPDL2T4PW","json":"https://pith.science/pith/EKQV6T3LMDZWWJERPGPDL2T4PW.json","graph_json":"https://pith.science/api/pith-number/EKQV6T3LMDZWWJERPGPDL2T4PW/graph.json","events_json":"https://pith.science/api/pith-number/EKQV6T3LMDZWWJERPGPDL2T4PW/events.json","paper":"https://pith.science/paper/EKQV6T3L"},"agent_actions":{"view_html":"https://pith.science/pith/EKQV6T3LMDZWWJERPGPDL2T4PW","download_json":"https://pith.science/pith/EKQV6T3LMDZWWJERPGPDL2T4PW.json","view_paper":"https://pith.science/paper/EKQV6T3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08924&json=true","fetch_graph":"https://pith.science/api/pith-number/EKQV6T3LMDZWWJERPGPDL2T4PW/graph.json","fetch_events":"https://pith.science/api/pith-number/EKQV6T3LMDZWWJERPGPDL2T4PW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKQV6T3LMDZWWJERPGPDL2T4PW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKQV6T3LMDZWWJERPGPDL2T4PW/action/storage_attestation","attest_author":"https://pith.science/pith/EKQV6T3LMDZWWJERPGPDL2T4PW/action/author_attestation","sign_citation":"https://pith.science/pith/EKQV6T3LMDZWWJERPGPDL2T4PW/action/citation_signature","submit_replication":"https://pith.science/pith/EKQV6T3LMDZWWJERPGPDL2T4PW/action/replication_record"}},"created_at":"2026-07-05T07:59:58.855275+00:00","updated_at":"2026-07-05T07:59:58.855275+00:00"}