{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IBLB6OVXAHCPMZFLNSUXSXDKJW","short_pith_number":"pith:IBLB6OVX","schema_version":"1.0","canonical_sha256":"40561f3ab701c4f664ab6ca9795c6a4dadf6630f5a1ca1a35b275960088ed0b7","source":{"kind":"arxiv","id":"2304.14660","version":7},"attestation_state":"computed","paper":{"title":"Segment Anything Model for Medical Images?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Ao Chang, Chaoyu Chen, Deng-Ping Fan, Dong Ni, Fajin Dong, Han Zhou, Haozhe Chi, Jiongquan Chen, Junxuan Yu, Kejuan Yue, Lei Li, Lian Liu, Rusi Chen, Sijing Liu, Vicente Grau, Xindi Hu, Xinrui Zhou, Xin Yang, Yuhao Huang","submitted_at":"2023-04-28T07:23:31Z","abstract_excerpt":"The Segment Anything Model (SAM) is the first foundation model for general image segmentation. It has achieved impressive results on various natural image segmentation tasks. However, medical image segmentation (MIS) is more challenging because of the complex modalities, fine anatomical structures, uncertain and complex object boundaries, and wide-range object scales. To fully validate SAM's performance on medical data, we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D imag"},"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":"2304.14660","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2023-04-28T07:23:31Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"d1c1d798ff79d8778ddffe5d1222d1d0d554b3286569f2a0deb1e55028d30768","abstract_canon_sha256":"aefc6faa875929f5c06a56a81b34f78c6ba9b27adf04d96cddece2aeb9a67ab2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:32.793546Z","signature_b64":"iZtlMrf9gENFnHdUFtMOGhEdnh193k5peG2gKRj88vZPhacGVcDjt/Mf4IsZKaiQZSIugxatAGs17WsspgssCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40561f3ab701c4f664ab6ca9795c6a4dadf6630f5a1ca1a35b275960088ed0b7","last_reissued_at":"2026-07-05T07:34:32.792947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:32.792947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segment Anything Model for Medical Images?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Ao Chang, Chaoyu Chen, Deng-Ping Fan, Dong Ni, Fajin Dong, Han Zhou, Haozhe Chi, Jiongquan Chen, Junxuan Yu, Kejuan Yue, Lei Li, Lian Liu, Rusi Chen, Sijing Liu, Vicente Grau, Xindi Hu, Xinrui Zhou, Xin Yang, Yuhao Huang","submitted_at":"2023-04-28T07:23:31Z","abstract_excerpt":"The Segment Anything Model (SAM) is the first foundation model for general image segmentation. It has achieved impressive results on various natural image segmentation tasks. However, medical image segmentation (MIS) is more challenging because of the complex modalities, fine anatomical structures, uncertain and complex object boundaries, and wide-range object scales. To fully validate SAM's performance on medical data, we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D imag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14660","kind":"arxiv","version":7},"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/2304.14660/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":"2304.14660","created_at":"2026-07-05T07:34:32.793011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14660v7","created_at":"2026-07-05T07:34:32.793011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14660","created_at":"2026-07-05T07:34:32.793011+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBLB6OVXAHCP","created_at":"2026-07-05T07:34:32.793011+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBLB6OVXAHCPMZFL","created_at":"2026-07-05T07:34:32.793011+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBLB6OVX","created_at":"2026-07-05T07:34:32.793011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13376","citing_title":"Clinical utility of foundation models in musculoskeletal MRI for biomarker fidelity and predictive outcomes","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03313","citing_title":"CardioSAM: Topology-Aware Decoder Design for High-Precision Cardiac MRI Segmentation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBLB6OVXAHCPMZFLNSUXSXDKJW","json":"https://pith.science/pith/IBLB6OVXAHCPMZFLNSUXSXDKJW.json","graph_json":"https://pith.science/api/pith-number/IBLB6OVXAHCPMZFLNSUXSXDKJW/graph.json","events_json":"https://pith.science/api/pith-number/IBLB6OVXAHCPMZFLNSUXSXDKJW/events.json","paper":"https://pith.science/paper/IBLB6OVX"},"agent_actions":{"view_html":"https://pith.science/pith/IBLB6OVXAHCPMZFLNSUXSXDKJW","download_json":"https://pith.science/pith/IBLB6OVXAHCPMZFLNSUXSXDKJW.json","view_paper":"https://pith.science/paper/IBLB6OVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14660&json=true","fetch_graph":"https://pith.science/api/pith-number/IBLB6OVXAHCPMZFLNSUXSXDKJW/graph.json","fetch_events":"https://pith.science/api/pith-number/IBLB6OVXAHCPMZFLNSUXSXDKJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBLB6OVXAHCPMZFLNSUXSXDKJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBLB6OVXAHCPMZFLNSUXSXDKJW/action/storage_attestation","attest_author":"https://pith.science/pith/IBLB6OVXAHCPMZFLNSUXSXDKJW/action/author_attestation","sign_citation":"https://pith.science/pith/IBLB6OVXAHCPMZFLNSUXSXDKJW/action/citation_signature","submit_replication":"https://pith.science/pith/IBLB6OVXAHCPMZFLNSUXSXDKJW/action/replication_record"}},"created_at":"2026-07-05T07:34:32.793011+00:00","updated_at":"2026-07-05T07:34:32.793011+00:00"}