{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RUT5HFCLG7ZHSAHMDKXLT4QKNV","short_pith_number":"pith:RUT5HFCL","schema_version":"1.0","canonical_sha256":"8d27d3944b37f27900ec1aaeb9f20a6d7e162ddba69b2a48d9903b47cfaaab9a","source":{"kind":"arxiv","id":"2608.16268","version":1},"attestation_state":"computed","paper":{"title":"CoM$^3$eT: A foundation model for medical image analysis through federated, multidimensional context integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Annika Gerken, Antje Prasse, Chiara Tappermann, Eike Petersen, Fabian Kiessling, Felix Peisen, Habib Mergan, Heinrich von Busch, Isabel Dahm, Isil Dogan O, Jan Hendrik Moltz, Johannes Lotz, J. Raphael Sch\\\"afer, Kai Geissler, Karoline Heber, Lars Ole Schwen, Lisa Siegler, Matthias Stefan May, Nadine Flinner, Natalia Artysh, Nick Weiss, Norman Zerbe, Peter Wild, Robert Grimm, Robin S. Mayer, Sebastian Arndt, Sefer Elezkurtaj, Till Nicke, Tim-Rasmus Kiehl, Tom Bisson","submitted_at":"2026-08-17T08:42:41Z","abstract_excerpt":"Medical foundation models improve generalization when training AI models with limited labeled data, but remain confined to a single specialty, such as pathology or radiology, and to either sparse or dense outputs, such as classification or segmentation. Here, we present CoM$^3$eT (Co-representation Multidimensional Multitask Medical Transformer), a medical vision foundation model that unifies pathology and radiology, sparse and dense predictions, and two- and higher-dimensional inputs by modeling multidimensional context with attention. CoM$^3$eT outperformed other medical foundation models in"},"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":"2608.16268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-17T08:42:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c2517dbaff1ee8d319a7ce0564f029e6120063c39f5f310ab18c789a361cabc4","abstract_canon_sha256":"9fa2a650122e67292fa65060f344339d75a705a05d3313ffe5da97eb65e73c28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-18T02:17:38.472002Z","signature_b64":"SrQwuAJmD6nvwg3eIQkUCnqgWFZ5P1w9c2dyLtqpb6qOdVxmtyNAv126OYuR9P9XfZVsDfpauTWsmsNx7NetAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d27d3944b37f27900ec1aaeb9f20a6d7e162ddba69b2a48d9903b47cfaaab9a","last_reissued_at":"2026-08-18T02:17:38.470220Z","signature_status":"signed_v1","first_computed_at":"2026-08-18T02:17:38.470220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoM$^3$eT: A foundation model for medical image analysis through federated, multidimensional context integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Annika Gerken, Antje Prasse, Chiara Tappermann, Eike Petersen, Fabian Kiessling, Felix Peisen, Habib Mergan, Heinrich von Busch, Isabel Dahm, Isil Dogan O, Jan Hendrik Moltz, Johannes Lotz, J. Raphael Sch\\\"afer, Kai Geissler, Karoline Heber, Lars Ole Schwen, Lisa Siegler, Matthias Stefan May, Nadine Flinner, Natalia Artysh, Nick Weiss, Norman Zerbe, Peter Wild, Robert Grimm, Robin S. Mayer, Sebastian Arndt, Sefer Elezkurtaj, Till Nicke, Tim-Rasmus Kiehl, Tom Bisson","submitted_at":"2026-08-17T08:42:41Z","abstract_excerpt":"Medical foundation models improve generalization when training AI models with limited labeled data, but remain confined to a single specialty, such as pathology or radiology, and to either sparse or dense outputs, such as classification or segmentation. Here, we present CoM$^3$eT (Co-representation Multidimensional Multitask Medical Transformer), a medical vision foundation model that unifies pathology and radiology, sparse and dense predictions, and two- and higher-dimensional inputs by modeling multidimensional context with attention. CoM$^3$eT outperformed other medical foundation models in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.16268","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/2608.16268/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":"2608.16268","created_at":"2026-08-18T02:17:38.469909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.16268v1","created_at":"2026-08-18T02:17:38.469909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.16268","created_at":"2026-08-18T02:17:38.469909+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUT5HFCLG7ZH","created_at":"2026-08-18T02:17:38.469909+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUT5HFCLG7ZHSAHM","created_at":"2026-08-18T02:17:38.469909+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUT5HFCL","created_at":"2026-08-18T02:17:38.469909+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/RUT5HFCLG7ZHSAHMDKXLT4QKNV","json":"https://pith.science/pith/RUT5HFCLG7ZHSAHMDKXLT4QKNV.json","graph_json":"https://pith.science/api/pith-number/RUT5HFCLG7ZHSAHMDKXLT4QKNV/graph.json","events_json":"https://pith.science/api/pith-number/RUT5HFCLG7ZHSAHMDKXLT4QKNV/events.json","paper":"https://pith.science/paper/RUT5HFCL"},"agent_actions":{"view_html":"https://pith.science/pith/RUT5HFCLG7ZHSAHMDKXLT4QKNV","download_json":"https://pith.science/pith/RUT5HFCLG7ZHSAHMDKXLT4QKNV.json","view_paper":"https://pith.science/paper/RUT5HFCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.16268&json=true","fetch_graph":"https://pith.science/api/pith-number/RUT5HFCLG7ZHSAHMDKXLT4QKNV/graph.json","fetch_events":"https://pith.science/api/pith-number/RUT5HFCLG7ZHSAHMDKXLT4QKNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUT5HFCLG7ZHSAHMDKXLT4QKNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUT5HFCLG7ZHSAHMDKXLT4QKNV/action/storage_attestation","attest_author":"https://pith.science/pith/RUT5HFCLG7ZHSAHMDKXLT4QKNV/action/author_attestation","sign_citation":"https://pith.science/pith/RUT5HFCLG7ZHSAHMDKXLT4QKNV/action/citation_signature","submit_replication":"https://pith.science/pith/RUT5HFCLG7ZHSAHMDKXLT4QKNV/action/replication_record"}},"created_at":"2026-08-18T02:17:38.469909+00:00","updated_at":"2026-08-18T02:17:38.469909+00:00"}