{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AXFXIBUGUNOACZWZQQRWM6CBGI","short_pith_number":"pith:AXFXIBUG","schema_version":"1.0","canonical_sha256":"05cb740686a35c0166d98423667841323cbfe42bcc9911d804bbea1f1da363dd","source":{"kind":"arxiv","id":"2504.00954","version":1},"attestation_state":"computed","paper":{"title":"IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bangwei Liu, Chaochao Lu, Shaohui Lin, Xin Tan, Xuhong Wang, Yicheng Bao, Yingchun Wang, Yuan Xie","submitted_at":"2025-04-01T16:47:20Z","abstract_excerpt":"Multimodal retrieval systems are becoming increasingly vital for cutting-edge AI technologies, such as embodied AI and AI-driven digital content industries. However, current multimodal retrieval tasks lack sufficient complexity and demonstrate limited practical application value. It spires us to design Instance-Driven Multimodal Image Retrieval (IDMR), a novel task that requires models to retrieve images containing the same instance as a query image while matching a text-described scenario. Unlike existing retrieval tasks focused on global image similarity or category-level matching, IDMR dema"},"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":"2504.00954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T16:47:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e195b6066a4c39ca97e8f798e1d594223349ac062f79c33cd7d7f535dbeb671","abstract_canon_sha256":"2a9f87b4355222d37db58e3845c9874efe6034e212c627898e016e2c43ad1e39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:53.730860Z","signature_b64":"hMjr6NE3CNQ+S6CDD3DE5nI/fqdcVOgd5b/JwgjMa7nBwZ9GK0j9ql4pLZlViOSF7muelEn4VaXusBwWHmhfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05cb740686a35c0166d98423667841323cbfe42bcc9911d804bbea1f1da363dd","last_reissued_at":"2026-07-05T10:42:53.730322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:53.730322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bangwei Liu, Chaochao Lu, Shaohui Lin, Xin Tan, Xuhong Wang, Yicheng Bao, Yingchun Wang, Yuan Xie","submitted_at":"2025-04-01T16:47:20Z","abstract_excerpt":"Multimodal retrieval systems are becoming increasingly vital for cutting-edge AI technologies, such as embodied AI and AI-driven digital content industries. However, current multimodal retrieval tasks lack sufficient complexity and demonstrate limited practical application value. It spires us to design Instance-Driven Multimodal Image Retrieval (IDMR), a novel task that requires models to retrieve images containing the same instance as a query image while matching a text-described scenario. Unlike existing retrieval tasks focused on global image similarity or category-level matching, IDMR dema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00954","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/2504.00954/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":"2504.00954","created_at":"2026-07-05T10:42:53.730390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00954v1","created_at":"2026-07-05T10:42:53.730390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00954","created_at":"2026-07-05T10:42:53.730390+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXFXIBUGUNOA","created_at":"2026-07-05T10:42:53.730390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXFXIBUGUNOACZWZ","created_at":"2026-07-05T10:42:53.730390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXFXIBUG","created_at":"2026-07-05T10:42:53.730390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.24621","citing_title":"FreeRet: MLLMs as Training-Free Retrievers","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AXFXIBUGUNOACZWZQQRWM6CBGI","json":"https://pith.science/pith/AXFXIBUGUNOACZWZQQRWM6CBGI.json","graph_json":"https://pith.science/api/pith-number/AXFXIBUGUNOACZWZQQRWM6CBGI/graph.json","events_json":"https://pith.science/api/pith-number/AXFXIBUGUNOACZWZQQRWM6CBGI/events.json","paper":"https://pith.science/paper/AXFXIBUG"},"agent_actions":{"view_html":"https://pith.science/pith/AXFXIBUGUNOACZWZQQRWM6CBGI","download_json":"https://pith.science/pith/AXFXIBUGUNOACZWZQQRWM6CBGI.json","view_paper":"https://pith.science/paper/AXFXIBUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00954&json=true","fetch_graph":"https://pith.science/api/pith-number/AXFXIBUGUNOACZWZQQRWM6CBGI/graph.json","fetch_events":"https://pith.science/api/pith-number/AXFXIBUGUNOACZWZQQRWM6CBGI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXFXIBUGUNOACZWZQQRWM6CBGI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXFXIBUGUNOACZWZQQRWM6CBGI/action/storage_attestation","attest_author":"https://pith.science/pith/AXFXIBUGUNOACZWZQQRWM6CBGI/action/author_attestation","sign_citation":"https://pith.science/pith/AXFXIBUGUNOACZWZQQRWM6CBGI/action/citation_signature","submit_replication":"https://pith.science/pith/AXFXIBUGUNOACZWZQQRWM6CBGI/action/replication_record"}},"created_at":"2026-07-05T10:42:53.730390+00:00","updated_at":"2026-07-05T10:42:53.730390+00:00"}