{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3AKXF7PXHHCZFAJYOZMYVA5YWN","short_pith_number":"pith:3AKXF7PX","canonical_record":{"source":{"id":"2505.10823","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T03:39:46Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"993b045a96fcea09f151fe9d4f7af55c476ac5e2aecf8b8cdd3d18c4985ea258","abstract_canon_sha256":"1a637f3863eb41ea01f1ac00938bfc16f4544a32ee8876c62e26465565193954"},"schema_version":"1.0"},"canonical_sha256":"d81572fdf739c592813876598a83b8b3435fe2030ddd39c6f1f1c8edff2e6bca","source":{"kind":"arxiv","id":"2505.10823","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10823","created_at":"2026-07-05T12:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10823v2","created_at":"2026-07-05T12:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10823","created_at":"2026-07-05T12:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"3AKXF7PXHHCZ","created_at":"2026-07-05T12:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"3AKXF7PXHHCZFAJY","created_at":"2026-07-05T12:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"3AKXF7PX","created_at":"2026-07-05T12:04:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3AKXF7PXHHCZFAJYOZMYVA5YWN","target":"record","payload":{"canonical_record":{"source":{"id":"2505.10823","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T03:39:46Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"993b045a96fcea09f151fe9d4f7af55c476ac5e2aecf8b8cdd3d18c4985ea258","abstract_canon_sha256":"1a637f3863eb41ea01f1ac00938bfc16f4544a32ee8876c62e26465565193954"},"schema_version":"1.0"},"canonical_sha256":"d81572fdf739c592813876598a83b8b3435fe2030ddd39c6f1f1c8edff2e6bca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:34.883024Z","signature_b64":"1WKPBbPvPIeV7g2im+HVtAAge1ER8XBYj9hCSdgMKEUPutHtp+xkML22X0ZFf1hdqV9BD2DsGYzyo+RE1lclAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d81572fdf739c592813876598a83b8b3435fe2030ddd39c6f1f1c8edff2e6bca","last_reissued_at":"2026-07-05T12:04:34.882486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:34.882486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.10823","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VH4OOHPx0/UyMa7nkFlXPPGCYpcciZGW7cqPjAO5KkMk4q7qHcsqIleJhVvhqShYAme7i+AxDk9l9PidtaXJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:50:34.243826Z"},"content_sha256":"f6345372c6e30e05194f0b535a946496299841c5bab4cca64f660c390f30e40b","schema_version":"1.0","event_id":"sha256:f6345372c6e30e05194f0b535a946496299841c5bab4cca64f660c390f30e40b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3AKXF7PXHHCZFAJYOZMYVA5YWN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Embeddings to Accuracy: Comparing Foundation Models for Radiographic Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Alan B. McMillan, Alberto Santamaria-Pang, Alexander Ersoy, Christopher Burt, Ivan Tarapov, Jameson Merkow, John W. Garrett, Joshua D. Warner, Matthew P. Lungren, Naiteek Sangani, Noel C. F. Codella, Richard J. Bruce, Tyler Bradshaw, Xue Li","submitted_at":"2025-05-16T03:39:46Z","abstract_excerpt":"Foundation models provide robust embeddings for diverse tasks, including medical imaging. We evaluate embeddings from seven general and medical-specific foundation models (e.g., DenseNet121, BiomedCLIP, MedImageInsight, Rad-DINO, CXR-Foundation) for training lightweight adapters in multi-class radiography classification. Using a dataset of 8,842 radiographs across seven classes, we trained adapters with algorithms like K-Nearest Neighbors, logistic regression, SVM, random forest, and MLP. The combination of MedImageInsight embeddings with an SVM or MLP adapter achieved the highest mean area un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10823","kind":"arxiv","version":2},"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/2505.10823/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8g/cSVKFc9d2nXAUGxTpddzmjGdTZj3XHciDMesVjCQUkT5ww6jEfUWL+ICzzy98UMTy/AZ1tTes1MiNMMo/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:50:34.244246Z"},"content_sha256":"ff0bc5ff67028b58caff5cae4174e6cc3b2e3d4e92af2cebcaebd71246049e28","schema_version":"1.0","event_id":"sha256:ff0bc5ff67028b58caff5cae4174e6cc3b2e3d4e92af2cebcaebd71246049e28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3AKXF7PXHHCZFAJYOZMYVA5YWN/bundle.json","state_url":"https://pith.science/pith/3AKXF7PXHHCZFAJYOZMYVA5YWN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3AKXF7PXHHCZFAJYOZMYVA5YWN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T13:50:34Z","links":{"resolver":"https://pith.science/pith/3AKXF7PXHHCZFAJYOZMYVA5YWN","bundle":"https://pith.science/pith/3AKXF7PXHHCZFAJYOZMYVA5YWN/bundle.json","state":"https://pith.science/pith/3AKXF7PXHHCZFAJYOZMYVA5YWN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3AKXF7PXHHCZFAJYOZMYVA5YWN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3AKXF7PXHHCZFAJYOZMYVA5YWN","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":"1a637f3863eb41ea01f1ac00938bfc16f4544a32ee8876c62e26465565193954","cross_cats_sorted":["eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T03:39:46Z","title_canon_sha256":"993b045a96fcea09f151fe9d4f7af55c476ac5e2aecf8b8cdd3d18c4985ea258"},"schema_version":"1.0","source":{"id":"2505.10823","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10823","created_at":"2026-07-05T12:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10823v2","created_at":"2026-07-05T12:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10823","created_at":"2026-07-05T12:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"3AKXF7PXHHCZ","created_at":"2026-07-05T12:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"3AKXF7PXHHCZFAJY","created_at":"2026-07-05T12:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"3AKXF7PX","created_at":"2026-07-05T12:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:ff0bc5ff67028b58caff5cae4174e6cc3b2e3d4e92af2cebcaebd71246049e28","target":"graph","created_at":"2026-07-05T12:04:34Z","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/2505.10823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models provide robust embeddings for diverse tasks, including medical imaging. We evaluate embeddings from seven general and medical-specific foundation models (e.g., DenseNet121, BiomedCLIP, MedImageInsight, Rad-DINO, CXR-Foundation) for training lightweight adapters in multi-class radiography classification. Using a dataset of 8,842 radiographs across seven classes, we trained adapters with algorithms like K-Nearest Neighbors, logistic regression, SVM, random forest, and MLP. The combination of MedImageInsight embeddings with an SVM or MLP adapter achieved the highest mean area un","authors_text":"Alan B. McMillan, Alberto Santamaria-Pang, Alexander Ersoy, Christopher Burt, Ivan Tarapov, Jameson Merkow, John W. Garrett, Joshua D. Warner, Matthew P. Lungren, Naiteek Sangani, Noel C. F. Codella, Richard J. Bruce, Tyler Bradshaw, Xue Li","cross_cats":["eess.IV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T03:39:46Z","title":"From Embeddings to Accuracy: Comparing Foundation Models for Radiographic Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10823","kind":"arxiv","version":2},"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:f6345372c6e30e05194f0b535a946496299841c5bab4cca64f660c390f30e40b","target":"record","created_at":"2026-07-05T12:04:34Z","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":"1a637f3863eb41ea01f1ac00938bfc16f4544a32ee8876c62e26465565193954","cross_cats_sorted":["eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T03:39:46Z","title_canon_sha256":"993b045a96fcea09f151fe9d4f7af55c476ac5e2aecf8b8cdd3d18c4985ea258"},"schema_version":"1.0","source":{"id":"2505.10823","kind":"arxiv","version":2}},"canonical_sha256":"d81572fdf739c592813876598a83b8b3435fe2030ddd39c6f1f1c8edff2e6bca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d81572fdf739c592813876598a83b8b3435fe2030ddd39c6f1f1c8edff2e6bca","first_computed_at":"2026-07-05T12:04:34.882486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:34.882486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1WKPBbPvPIeV7g2im+HVtAAge1ER8XBYj9hCSdgMKEUPutHtp+xkML22X0ZFf1hdqV9BD2DsGYzyo+RE1lclAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:34.883024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10823","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6345372c6e30e05194f0b535a946496299841c5bab4cca64f660c390f30e40b","sha256:ff0bc5ff67028b58caff5cae4174e6cc3b2e3d4e92af2cebcaebd71246049e28"],"state_sha256":"8fccc6de3d813410582a64f3a674d5a456fc3e799314990dd44baf5ef1c643ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5aC4ATwwUg8HR51RLFRFJMTG30RnJBPjX+TGgQnOPZhM5eE4lRW4TJzSBLB24kEew7IKiAtHERzsdGDDSJ76CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:50:34.246341Z","bundle_sha256":"4b06f0ba38e2937074698f654ff7ec20be4c11d812bb9ca23ba27317792a4a06"}}