{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PLE5O22TSEM6XV7KQ4P7CKUGLI","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":"6552c682343723db4dafff03c4620231edbbe8a29f4f2f586ffb9fc9361582ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T06:30:41Z","title_canon_sha256":"be0e41d54ad48ed2632a0cb141cbb83e1ef4ac4f335d4fa4f612fc7f1e52683e"},"schema_version":"1.0","source":{"id":"2507.12823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12823","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12823v1","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12823","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"pith_short_12","alias_value":"PLE5O22TSEM6","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"pith_short_16","alias_value":"PLE5O22TSEM6XV7K","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"pith_short_8","alias_value":"PLE5O22T","created_at":"2026-07-05T11:38:39Z"}],"graph_snapshots":[{"event_id":"sha256:f43a3f4c9d27806bd66322526f82a185bfeeb22e225e29e9b5b0d1940b0f9e1d","target":"graph","created_at":"2026-07-05T11:38:39Z","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/2507.12823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Composed image retrieval (CIR) is a vision language task that retrieves a target image using a reference image and modification text, enabling intuitive specification of desired changes. While effectively fusing visual and textual modalities is crucial, existing methods typically adopt either early or late fusion. Early fusion tends to excessively focus on explicitly mentioned textual details and neglect visual context, whereas late fusion struggles to capture fine-grained semantic alignments between image regions and textual tokens. To address these issues, we propose FAR-Net, a multi-stage f","authors_text":"Jeong-Woo Park, Seong-Whan Lee, Young-Eun Kim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T06:30:41Z","title":"FAR-Net: Multi-Stage Fusion Network with Enhanced Semantic Alignment and Adaptive Reconciliation for Composed Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12823","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":"sha256:67409bec9082112ff5570d5a9fc42ef620a0713ae41b0182564972338643dc45","target":"record","created_at":"2026-07-05T11:38:39Z","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":"6552c682343723db4dafff03c4620231edbbe8a29f4f2f586ffb9fc9361582ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T06:30:41Z","title_canon_sha256":"be0e41d54ad48ed2632a0cb141cbb83e1ef4ac4f335d4fa4f612fc7f1e52683e"},"schema_version":"1.0","source":{"id":"2507.12823","kind":"arxiv","version":1}},"canonical_sha256":"7ac9d76b539119ebd7ea871ff12a865a23c16054efb5639b24d0db3f24d63f96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ac9d76b539119ebd7ea871ff12a865a23c16054efb5639b24d0db3f24d63f96","first_computed_at":"2026-07-05T11:38:39.908019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:39.908019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7z297vE7ANS72hfNL/DpBxU/PzY9fOpJMWeculDGzXEW0zsYfpbJbHc8P6f5EIYmzdVU0TZFBXB6MtqCu+TvCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:39.908505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67409bec9082112ff5570d5a9fc42ef620a0713ae41b0182564972338643dc45","sha256:f43a3f4c9d27806bd66322526f82a185bfeeb22e225e29e9b5b0d1940b0f9e1d"],"state_sha256":"9bc28a70acf4ace0e9d4195c4248c351062caf26a616b1e396bc7e680445df14"}