{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UNHQLDO5G2CLRC64IAVY4PVSRU","short_pith_number":"pith:UNHQLDO5","schema_version":"1.0","canonical_sha256":"a34f058ddd3684b88bdc402b8e3eb28d1cd907f41773a905cd0d0a959d720abd","source":{"kind":"arxiv","id":"2507.12416","version":1},"attestation_state":"computed","paper":{"title":"QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jaehyun Kwak, Ramahdani Muhammad Izaaz Inhar, Se-Young Yun, Sung-Ju Lee","submitted_at":"2025-07-16T17:06:33Z","abstract_excerpt":"Composed Image Retrieval (CIR) retrieves relevant images based on a reference image and accompanying text describing desired modifications. However, existing CIR methods only focus on retrieving the target image and disregard the relevance of other images. This limitation arises because most methods employing contrastive learning-which treats the target image as positive and all other images in the batch as negatives-can inadvertently include false negatives. This may result in retrieving irrelevant images, reducing user satisfaction even when the target image is retrieved. To address this iss"},"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":"2507.12416","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T17:06:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e25eeb15a924c288aeaf0ed6414ffc16262e3249f96a0031467e132cef983a4c","abstract_canon_sha256":"bd3465ea2b65dc027c83e7791a1f4e41bdb868b6ef46df2db539fdbad4bc59a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:19.872480Z","signature_b64":"/RbiNy/S/6odZSB2WV5bBGrEyOWRIS/5UEmXL0us5cta80mhaSjrhSWF/Zj+BRZxGsxbgWaDHDpecMeW5KjTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a34f058ddd3684b88bdc402b8e3eb28d1cd907f41773a905cd0d0a959d720abd","last_reissued_at":"2026-07-05T11:38:19.871945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:19.871945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jaehyun Kwak, Ramahdani Muhammad Izaaz Inhar, Se-Young Yun, Sung-Ju Lee","submitted_at":"2025-07-16T17:06:33Z","abstract_excerpt":"Composed Image Retrieval (CIR) retrieves relevant images based on a reference image and accompanying text describing desired modifications. However, existing CIR methods only focus on retrieving the target image and disregard the relevance of other images. This limitation arises because most methods employing contrastive learning-which treats the target image as positive and all other images in the batch as negatives-can inadvertently include false negatives. This may result in retrieving irrelevant images, reducing user satisfaction even when the target image is retrieved. To address this iss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12416","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/2507.12416/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":"2507.12416","created_at":"2026-07-05T11:38:19.872013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12416v1","created_at":"2026-07-05T11:38:19.872013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12416","created_at":"2026-07-05T11:38:19.872013+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNHQLDO5G2CL","created_at":"2026-07-05T11:38:19.872013+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNHQLDO5G2CLRC64","created_at":"2026-07-05T11:38:19.872013+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNHQLDO5","created_at":"2026-07-05T11:38:19.872013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08144","citing_title":"IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04604","citing_title":"COMBINER: Composed Image Retrieval Guided by Attribute-based Neighbor Relations","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNHQLDO5G2CLRC64IAVY4PVSRU","json":"https://pith.science/pith/UNHQLDO5G2CLRC64IAVY4PVSRU.json","graph_json":"https://pith.science/api/pith-number/UNHQLDO5G2CLRC64IAVY4PVSRU/graph.json","events_json":"https://pith.science/api/pith-number/UNHQLDO5G2CLRC64IAVY4PVSRU/events.json","paper":"https://pith.science/paper/UNHQLDO5"},"agent_actions":{"view_html":"https://pith.science/pith/UNHQLDO5G2CLRC64IAVY4PVSRU","download_json":"https://pith.science/pith/UNHQLDO5G2CLRC64IAVY4PVSRU.json","view_paper":"https://pith.science/paper/UNHQLDO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12416&json=true","fetch_graph":"https://pith.science/api/pith-number/UNHQLDO5G2CLRC64IAVY4PVSRU/graph.json","fetch_events":"https://pith.science/api/pith-number/UNHQLDO5G2CLRC64IAVY4PVSRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNHQLDO5G2CLRC64IAVY4PVSRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNHQLDO5G2CLRC64IAVY4PVSRU/action/storage_attestation","attest_author":"https://pith.science/pith/UNHQLDO5G2CLRC64IAVY4PVSRU/action/author_attestation","sign_citation":"https://pith.science/pith/UNHQLDO5G2CLRC64IAVY4PVSRU/action/citation_signature","submit_replication":"https://pith.science/pith/UNHQLDO5G2CLRC64IAVY4PVSRU/action/replication_record"}},"created_at":"2026-07-05T11:38:19.872013+00:00","updated_at":"2026-07-05T11:38:19.872013+00:00"}