{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T65WQ7P3OLE4DPXEYHY4PFZSWI","short_pith_number":"pith:T65WQ7P3","schema_version":"1.0","canonical_sha256":"9fbb687dfb72c9c1bee4c1f1c79732b2109ebd99e04fbed56420a2126e39b702","source":{"kind":"arxiv","id":"2605.15720","version":1},"attestation_state":"computed","paper":{"title":"Semi-MedRef: Semi-Supervised Medical Referring Image Segmentation with Cross-Modal Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Luping Zhou, Yi Liu, Yuchen Li, Zhen Zhao","submitted_at":"2026-05-15T08:15:45Z","abstract_excerpt":"Medical referring image segmentation (MRIS) requires pixel-level masks aligned with textual descriptions of anatomical locations, making annotation costly in low-label regimes. Semi-supervised learning (SSL) can mitigate this burden by leveraging unlabeled data, but its success hinges on maintaining reliable image-text alignment under perturbations. Most existing SSL-based referred segmentation methods use either independent or simplistic multi-modal perturbations (e.g., left-right flips), without fully addressing cross-modal alignment under strong augmentation, while CutMix, highly effective "},"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":"2605.15720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T08:15:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c475e262294adbaa1ecd22524471e01055245a6acbb84583523aad36f1ab57ce","abstract_canon_sha256":"5ebe911f97914842c3e785da75ba481b90f6bf141a1857a38cee31ec3dee8836"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:14.575979Z","signature_b64":"GGYgf0ZGUhtT506NoCF4NzeyOYgoXbNxOHHj+gSXGv+MaYjy8h2ynWasbkjIXkVPI5MR3RrMSEjQ+VwQM+rFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fbb687dfb72c9c1bee4c1f1c79732b2109ebd99e04fbed56420a2126e39b702","last_reissued_at":"2026-05-20T00:01:14.575198Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:14.575198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-MedRef: Semi-Supervised Medical Referring Image Segmentation with Cross-Modal Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Luping Zhou, Yi Liu, Yuchen Li, Zhen Zhao","submitted_at":"2026-05-15T08:15:45Z","abstract_excerpt":"Medical referring image segmentation (MRIS) requires pixel-level masks aligned with textual descriptions of anatomical locations, making annotation costly in low-label regimes. Semi-supervised learning (SSL) can mitigate this burden by leveraging unlabeled data, but its success hinges on maintaining reliable image-text alignment under perturbations. Most existing SSL-based referred segmentation methods use either independent or simplistic multi-modal perturbations (e.g., left-right flips), without fully addressing cross-modal alignment under strong augmentation, while CutMix, highly effective "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15720","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/2605.15720/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:25.155892Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.007860Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"49262053c12dd9c0aac27f6378ce6c2c94ca2601faad67558142d771d29137e1"},"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":"2605.15720","created_at":"2026-05-20T00:01:14.575306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15720v1","created_at":"2026-05-20T00:01:14.575306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15720","created_at":"2026-05-20T00:01:14.575306+00:00"},{"alias_kind":"pith_short_12","alias_value":"T65WQ7P3OLE4","created_at":"2026-05-20T00:01:14.575306+00:00"},{"alias_kind":"pith_short_16","alias_value":"T65WQ7P3OLE4DPXE","created_at":"2026-05-20T00:01:14.575306+00:00"},{"alias_kind":"pith_short_8","alias_value":"T65WQ7P3","created_at":"2026-05-20T00:01:14.575306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T65WQ7P3OLE4DPXEYHY4PFZSWI","json":"https://pith.science/pith/T65WQ7P3OLE4DPXEYHY4PFZSWI.json","graph_json":"https://pith.science/api/pith-number/T65WQ7P3OLE4DPXEYHY4PFZSWI/graph.json","events_json":"https://pith.science/api/pith-number/T65WQ7P3OLE4DPXEYHY4PFZSWI/events.json","paper":"https://pith.science/paper/T65WQ7P3"},"agent_actions":{"view_html":"https://pith.science/pith/T65WQ7P3OLE4DPXEYHY4PFZSWI","download_json":"https://pith.science/pith/T65WQ7P3OLE4DPXEYHY4PFZSWI.json","view_paper":"https://pith.science/paper/T65WQ7P3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15720&json=true","fetch_graph":"https://pith.science/api/pith-number/T65WQ7P3OLE4DPXEYHY4PFZSWI/graph.json","fetch_events":"https://pith.science/api/pith-number/T65WQ7P3OLE4DPXEYHY4PFZSWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T65WQ7P3OLE4DPXEYHY4PFZSWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T65WQ7P3OLE4DPXEYHY4PFZSWI/action/storage_attestation","attest_author":"https://pith.science/pith/T65WQ7P3OLE4DPXEYHY4PFZSWI/action/author_attestation","sign_citation":"https://pith.science/pith/T65WQ7P3OLE4DPXEYHY4PFZSWI/action/citation_signature","submit_replication":"https://pith.science/pith/T65WQ7P3OLE4DPXEYHY4PFZSWI/action/replication_record"}},"created_at":"2026-05-20T00:01:14.575306+00:00","updated_at":"2026-05-20T00:01:14.575306+00:00"}