{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AXFXIBUGUNOACZWZQQRWM6CBGI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2a9f87b4355222d37db58e3845c9874efe6034e212c627898e016e2c43ad1e39","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T16:47:20Z","title_canon_sha256":"7e195b6066a4c39ca97e8f798e1d594223349ac062f79c33cd7d7f535dbeb671"},"schema_version":"1.0","source":{"id":"2504.00954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00954","created_at":"2026-07-05T10:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00954v1","created_at":"2026-07-05T10:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00954","created_at":"2026-07-05T10:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"AXFXIBUGUNOA","created_at":"2026-07-05T10:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"AXFXIBUGUNOACZWZ","created_at":"2026-07-05T10:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"AXFXIBUG","created_at":"2026-07-05T10:42:53Z"}],"graph_snapshots":[{"event_id":"sha256:71e2086d1fd091d9aebfebb92d24ccf1294a368e5afa5c7f7797717fc84afb5e","target":"graph","created_at":"2026-07-05T10:42:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.00954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bangwei Liu, Chaochao Lu, Shaohui Lin, Xin Tan, Xuhong Wang, Yicheng Bao, Yingchun Wang, Yuan Xie","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T16:47:20Z","title":"IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00954","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ceb7428f7daeef299e154f1a65794b772b69ad40235869f0bf9633e66c93b210","target":"record","created_at":"2026-07-05T10:42:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2a9f87b4355222d37db58e3845c9874efe6034e212c627898e016e2c43ad1e39","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T16:47:20Z","title_canon_sha256":"7e195b6066a4c39ca97e8f798e1d594223349ac062f79c33cd7d7f535dbeb671"},"schema_version":"1.0","source":{"id":"2504.00954","kind":"arxiv","version":1}},"canonical_sha256":"05cb740686a35c0166d98423667841323cbfe42bcc9911d804bbea1f1da363dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05cb740686a35c0166d98423667841323cbfe42bcc9911d804bbea1f1da363dd","first_computed_at":"2026-07-05T10:42:53.730322Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:53.730322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hMjr6NE3CNQ+S6CDD3DE5nI/fqdcVOgd5b/JwgjMa7nBwZ9GK0j9ql4pLZlViOSF7muelEn4VaXusBwWHmhfDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:53.730860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ceb7428f7daeef299e154f1a65794b772b69ad40235869f0bf9633e66c93b210","sha256:71e2086d1fd091d9aebfebb92d24ccf1294a368e5afa5c7f7797717fc84afb5e"],"state_sha256":"5ce7449ec2afc3e765ff75277a1d0e198e4892ded546f11fee424c48b0bc3463"}