{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FXHJX5JWPM6DA2ESNGWXYEZ4G4","short_pith_number":"pith:FXHJX5JW","schema_version":"1.0","canonical_sha256":"2dce9bf5367b3c30689269ad7c133c371e1e94620c623c43f57c79b3be51d954","source":{"kind":"arxiv","id":"2509.08570","version":1},"attestation_state":"computed","paper":{"title":"Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia-Xuan Jiang, Shubin Zeng, Wenjun Yu, Yinchen Zhou, Yuee Li, Zhong Wang","submitted_at":"2025-09-10T13:16:30Z","abstract_excerpt":"Multimodal models have achieved remarkable success in natural image segmentation, yet they often underperform when applied to the medical domain. Through extensive study, we attribute this performance gap to the challenges of multimodal fusion, primarily the significant semantic gap between abstract textual prompts and fine-grained medical visual features, as well as the resulting feature dispersion. To address these issues, we revisit the problem from the perspective of semantic aggregation. Specifically, we propose an Expectation-Maximization (EM) Aggregation mechanism and a Text-Guided Pixe"},"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":"2509.08570","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T13:16:30Z","cross_cats_sorted":[],"title_canon_sha256":"f57126e19848a9c3482ac69f621fddbf4115ddd266ded24f3063c1a8a79b46bd","abstract_canon_sha256":"ada697fe275bf34cf919b78b663b42eefba8183fc6b211b8242b608a7b4f110a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:32.343203Z","signature_b64":"LpLBzYjMlSMWqBPoZeZguclnw0QQ+ZSI9J3mtFMFPzHMrm8S+6h/MmEHcMoNPx7duXrr1EaZQglmV+fxFNKOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dce9bf5367b3c30689269ad7c133c371e1e94620c623c43f57c79b3be51d954","last_reissued_at":"2026-07-05T12:08:32.342685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:32.342685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia-Xuan Jiang, Shubin Zeng, Wenjun Yu, Yinchen Zhou, Yuee Li, Zhong Wang","submitted_at":"2025-09-10T13:16:30Z","abstract_excerpt":"Multimodal models have achieved remarkable success in natural image segmentation, yet they often underperform when applied to the medical domain. Through extensive study, we attribute this performance gap to the challenges of multimodal fusion, primarily the significant semantic gap between abstract textual prompts and fine-grained medical visual features, as well as the resulting feature dispersion. To address these issues, we revisit the problem from the perspective of semantic aggregation. Specifically, we propose an Expectation-Maximization (EM) Aggregation mechanism and a Text-Guided Pixe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08570","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/2509.08570/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":"2509.08570","created_at":"2026-07-05T12:08:32.342739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08570v1","created_at":"2026-07-05T12:08:32.342739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08570","created_at":"2026-07-05T12:08:32.342739+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXHJX5JWPM6D","created_at":"2026-07-05T12:08:32.342739+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXHJX5JWPM6DA2ES","created_at":"2026-07-05T12:08:32.342739+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXHJX5JW","created_at":"2026-07-05T12:08:32.342739+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/FXHJX5JWPM6DA2ESNGWXYEZ4G4","json":"https://pith.science/pith/FXHJX5JWPM6DA2ESNGWXYEZ4G4.json","graph_json":"https://pith.science/api/pith-number/FXHJX5JWPM6DA2ESNGWXYEZ4G4/graph.json","events_json":"https://pith.science/api/pith-number/FXHJX5JWPM6DA2ESNGWXYEZ4G4/events.json","paper":"https://pith.science/paper/FXHJX5JW"},"agent_actions":{"view_html":"https://pith.science/pith/FXHJX5JWPM6DA2ESNGWXYEZ4G4","download_json":"https://pith.science/pith/FXHJX5JWPM6DA2ESNGWXYEZ4G4.json","view_paper":"https://pith.science/paper/FXHJX5JW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08570&json=true","fetch_graph":"https://pith.science/api/pith-number/FXHJX5JWPM6DA2ESNGWXYEZ4G4/graph.json","fetch_events":"https://pith.science/api/pith-number/FXHJX5JWPM6DA2ESNGWXYEZ4G4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXHJX5JWPM6DA2ESNGWXYEZ4G4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXHJX5JWPM6DA2ESNGWXYEZ4G4/action/storage_attestation","attest_author":"https://pith.science/pith/FXHJX5JWPM6DA2ESNGWXYEZ4G4/action/author_attestation","sign_citation":"https://pith.science/pith/FXHJX5JWPM6DA2ESNGWXYEZ4G4/action/citation_signature","submit_replication":"https://pith.science/pith/FXHJX5JWPM6DA2ESNGWXYEZ4G4/action/replication_record"}},"created_at":"2026-07-05T12:08:32.342739+00:00","updated_at":"2026-07-05T12:08:32.342739+00:00"}