{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K6WOUAJX7NGUKSFDAJMBMQ6KS7","short_pith_number":"pith:K6WOUAJX","schema_version":"1.0","canonical_sha256":"57acea0137fb4d4548a302581643ca97c46b0d6aa58ea091a4c4d19fdcf80b7b","source":{"kind":"arxiv","id":"2303.11916","version":4},"attestation_state":"computed","paper":{"title":"CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Geonmo Gu, HeeJae Jun, Sangdoo Yun, Sanghyuk Chun, Wonjae Kim, Yoohoon Kang","submitted_at":"2023-03-21T15:06:35Z","abstract_excerpt":"This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion. This paper also introduces a new synthetic dataset, named SynthTriplets18M, with 18.8 million reference images, conditions, and corresponding target image triplets to train CIR models. CompoDiff and SynthTriplets18M tackle the shortages of the previous CIR approaches, such as poor generalizability due to the small dataset scale and the limited types of conditions. CompoDiff not only achieves a new state-of-the-art on four ZS-CIR benchmarks, including Fash"},"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":"2303.11916","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-21T15:06:35Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"23e357f7935354b06b56116db725c08f373f8fa26447f854dc2390d22dd5f981","abstract_canon_sha256":"a7ccd6f60f12bce94c7dbcf7eed0c273d2d2d1d31d6f4c1acfa7372ad5d6b5f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:08.526600Z","signature_b64":"JedUP/OrRqed2t1QcJ/LUvN7JbLTsBk23QSm0W2s+c6BbZrqe1Zxl9aet1cWFpux7ytRNrP9TVxDuumzlLJwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57acea0137fb4d4548a302581643ca97c46b0d6aa58ea091a4c4d19fdcf80b7b","last_reissued_at":"2026-07-05T08:44:08.526122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:08.526122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Geonmo Gu, HeeJae Jun, Sangdoo Yun, Sanghyuk Chun, Wonjae Kim, Yoohoon Kang","submitted_at":"2023-03-21T15:06:35Z","abstract_excerpt":"This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion. This paper also introduces a new synthetic dataset, named SynthTriplets18M, with 18.8 million reference images, conditions, and corresponding target image triplets to train CIR models. CompoDiff and SynthTriplets18M tackle the shortages of the previous CIR approaches, such as poor generalizability due to the small dataset scale and the limited types of conditions. CompoDiff not only achieves a new state-of-the-art on four ZS-CIR benchmarks, including Fash"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11916","kind":"arxiv","version":4},"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/2303.11916/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":"2303.11916","created_at":"2026-07-05T08:44:08.526181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11916v4","created_at":"2026-07-05T08:44:08.526181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11916","created_at":"2026-07-05T08:44:08.526181+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6WOUAJX7NGU","created_at":"2026-07-05T08:44:08.526181+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6WOUAJX7NGUKSFD","created_at":"2026-07-05T08:44:08.526181+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6WOUAJX","created_at":"2026-07-05T08:44:08.526181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19684","citing_title":"Exploring Multi-Modal Large Language Models and Two-Stage Fine-Tuning for Fashion Image Retrieval","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22478","citing_title":"DeliCIR: Memory-Guided Test-Time Deliberation via Multi-Agent Collaboration for Composed Image Retrieval","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2410.18715","citing_title":"ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22478","citing_title":"DeliCIR: Memory-Guided Test-Time Deliberation via Multi-Agent Collaboration for Composed Image Retrieval","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21261","citing_title":"STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12904","citing_title":"A Sanity Check on Composed Image Retrieval","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6WOUAJX7NGUKSFDAJMBMQ6KS7","json":"https://pith.science/pith/K6WOUAJX7NGUKSFDAJMBMQ6KS7.json","graph_json":"https://pith.science/api/pith-number/K6WOUAJX7NGUKSFDAJMBMQ6KS7/graph.json","events_json":"https://pith.science/api/pith-number/K6WOUAJX7NGUKSFDAJMBMQ6KS7/events.json","paper":"https://pith.science/paper/K6WOUAJX"},"agent_actions":{"view_html":"https://pith.science/pith/K6WOUAJX7NGUKSFDAJMBMQ6KS7","download_json":"https://pith.science/pith/K6WOUAJX7NGUKSFDAJMBMQ6KS7.json","view_paper":"https://pith.science/paper/K6WOUAJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11916&json=true","fetch_graph":"https://pith.science/api/pith-number/K6WOUAJX7NGUKSFDAJMBMQ6KS7/graph.json","fetch_events":"https://pith.science/api/pith-number/K6WOUAJX7NGUKSFDAJMBMQ6KS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6WOUAJX7NGUKSFDAJMBMQ6KS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6WOUAJX7NGUKSFDAJMBMQ6KS7/action/storage_attestation","attest_author":"https://pith.science/pith/K6WOUAJX7NGUKSFDAJMBMQ6KS7/action/author_attestation","sign_citation":"https://pith.science/pith/K6WOUAJX7NGUKSFDAJMBMQ6KS7/action/citation_signature","submit_replication":"https://pith.science/pith/K6WOUAJX7NGUKSFDAJMBMQ6KS7/action/replication_record"}},"created_at":"2026-07-05T08:44:08.526181+00:00","updated_at":"2026-07-05T08:44:08.526181+00:00"}