{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OMZ3LIVNZKRQIIHCOTBRFOGEP6","short_pith_number":"pith:OMZ3LIVN","schema_version":"1.0","canonical_sha256":"7333b5a2adcaa30420e274c312b8c47fa7dbd37b4f37feb3c1185ab521242e52","source":{"kind":"arxiv","id":"2503.21309","version":1},"attestation_state":"computed","paper":{"title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haokun Wen, Liqiang Nie, Yupeng Hu, Zhiheng Fu, Zhiwei Chen, Zixu Li","submitted_at":"2025-03-27T09:34:21Z","abstract_excerpt":"Composed Image Retrieval (CIR) facilitates image retrieval through a multimodal query consisting of a reference image and modification text. The reference image defines the retrieval context, while the modification text specifies desired alterations. However, existing CIR datasets predominantly employ coarse-grained modification text (CoarseMT), which inadequately captures fine-grained retrieval intents. This limitation introduces two key challenges: (1) ignoring detailed differences leads to imprecise positive samples, and (2) greater ambiguity arises when retrieving visually similar images. "},"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":"2503.21309","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T09:34:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a3b60219b9b6f79bb1ea07390fcc2a1401d5952c97d0f855bc0fe6df719c6e1","abstract_canon_sha256":"45b0926c5601a8a8ffc1afe344a2acc1629d9213c4cb8f80e66810f5775e9b95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:22.990538Z","signature_b64":"644ctSP5uqNidkaXtq6avLQkUpn4nuY9KrrV4IEwXRZHpi2EDPkp+UMQA40TzKKC5irEsv1Fs6P08SQLlYRABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7333b5a2adcaa30420e274c312b8c47fa7dbd37b4f37feb3c1185ab521242e52","last_reissued_at":"2026-07-05T10:40:22.990071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:22.990071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haokun Wen, Liqiang Nie, Yupeng Hu, Zhiheng Fu, Zhiwei Chen, Zixu Li","submitted_at":"2025-03-27T09:34:21Z","abstract_excerpt":"Composed Image Retrieval (CIR) facilitates image retrieval through a multimodal query consisting of a reference image and modification text. The reference image defines the retrieval context, while the modification text specifies desired alterations. However, existing CIR datasets predominantly employ coarse-grained modification text (CoarseMT), which inadequately captures fine-grained retrieval intents. This limitation introduces two key challenges: (1) ignoring detailed differences leads to imprecise positive samples, and (2) greater ambiguity arises when retrieving visually similar images. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21309","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/2503.21309/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":"2503.21309","created_at":"2026-07-05T10:40:22.990122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.21309v1","created_at":"2026-07-05T10:40:22.990122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21309","created_at":"2026-07-05T10:40:22.990122+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMZ3LIVNZKRQ","created_at":"2026-07-05T10:40:22.990122+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMZ3LIVNZKRQIIHC","created_at":"2026-07-05T10:40:22.990122+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMZ3LIVN","created_at":"2026-07-05T10:40:22.990122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11689","citing_title":"RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11257","citing_title":"Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09253","citing_title":"Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08144","citing_title":"IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09901","citing_title":"On the Controllability-Fidelity Frontier in Diffusion Editing","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04604","citing_title":"COMBINER: Composed Image Retrieval Guided by Attribute-based Neighbor Relations","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00305","citing_title":"Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09253","citing_title":"Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21190","citing_title":"Semantic Granularity Navigation in Image Editing","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24470","citing_title":"TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24481","citing_title":"OmniEgo-R$^2$: A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24500","citing_title":"EgoAdapt: A Multi-Scene Egocentric Adaptation Method for CVPR 2026 HD-EPIC VQA Challenge","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24496","citing_title":"EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00305","citing_title":"Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01113","citing_title":"R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16464","citing_title":"MHMamba: Multi-Head Mamba for 3D Brain Tumor Segmentation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23668","citing_title":"Hermes: A Multi-Scale Spatial-Temporal Hypergraph Network for Stock Time Series Forecasting","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13671","citing_title":"AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27253","citing_title":"Mitigating Hallucination on Hallucination in RAG via Ensemble Voting","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19386","citing_title":"Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10297","citing_title":"FashionMV: Product-Level Composed Image Retrieval with Multi-View Fashion Data","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17898","citing_title":"ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20358","citing_title":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","ref_index":122,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OMZ3LIVNZKRQIIHCOTBRFOGEP6","json":"https://pith.science/pith/OMZ3LIVNZKRQIIHCOTBRFOGEP6.json","graph_json":"https://pith.science/api/pith-number/OMZ3LIVNZKRQIIHCOTBRFOGEP6/graph.json","events_json":"https://pith.science/api/pith-number/OMZ3LIVNZKRQIIHCOTBRFOGEP6/events.json","paper":"https://pith.science/paper/OMZ3LIVN"},"agent_actions":{"view_html":"https://pith.science/pith/OMZ3LIVNZKRQIIHCOTBRFOGEP6","download_json":"https://pith.science/pith/OMZ3LIVNZKRQIIHCOTBRFOGEP6.json","view_paper":"https://pith.science/paper/OMZ3LIVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.21309&json=true","fetch_graph":"https://pith.science/api/pith-number/OMZ3LIVNZKRQIIHCOTBRFOGEP6/graph.json","fetch_events":"https://pith.science/api/pith-number/OMZ3LIVNZKRQIIHCOTBRFOGEP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMZ3LIVNZKRQIIHCOTBRFOGEP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMZ3LIVNZKRQIIHCOTBRFOGEP6/action/storage_attestation","attest_author":"https://pith.science/pith/OMZ3LIVNZKRQIIHCOTBRFOGEP6/action/author_attestation","sign_citation":"https://pith.science/pith/OMZ3LIVNZKRQIIHCOTBRFOGEP6/action/citation_signature","submit_replication":"https://pith.science/pith/OMZ3LIVNZKRQIIHCOTBRFOGEP6/action/replication_record"}},"created_at":"2026-07-05T10:40:22.990122+00:00","updated_at":"2026-07-05T10:40:22.990122+00:00"}