{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VINKXVPWYYTVVTON7ZCEZZNVAU","short_pith_number":"pith:VINKXVPW","schema_version":"1.0","canonical_sha256":"aa1aabd5f6c6275acdcdfe444ce5b505144f12291d325a049dd8db3a8be2ea48","source":{"kind":"arxiv","id":"2606.25770","version":1},"attestation_state":"computed","paper":{"title":"Re-mixing Embeddings for Patient Augmentation in Data Scarce Multiple Instance Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Anastasia Litinetskaya, Ario Sadafi, Carsten Marr, Fatih Ozlugedik, Muhammed Furkan Dasdelen, Nassir Navab","submitted_at":"2026-06-24T12:45:44Z","abstract_excerpt":"Data scarcity is a major bottleneck in medical Multiple Instance Learning (MIL), especially for rare diseases or expensive modalities. We introduce a statistically grounded patient augmentation approach that generates realistic patients directly in embedding space. Using Gaussian Mixture Models as a probabilistic clustering approach on pooled instance embeddings from all patients, our method learns disease-specific \"recipes\"-statistical distributions of instances across unsupervised clusters. New patients are then generated by sampling embeddings from clusters based on learned recipes. Unlike "},"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":"2606.25770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T12:45:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e919cd58dc2dfbbb9f0720d3c2daf764129e6e6629a21398e671c50761e3b641","abstract_canon_sha256":"059edaaf48da7b543dac988a4217e1815689155a9fe4087be18c89692af14b8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:14.806107Z","signature_b64":"tA0tl606Qb1mp/JRIZb++vhhFWSVMtUSGW8TpmpODwsMb7itliEQDpko38YVDF5PqLwwGzKiUL6bEbjw21YxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa1aabd5f6c6275acdcdfe444ce5b505144f12291d325a049dd8db3a8be2ea48","last_reissued_at":"2026-06-25T01:18:14.805754Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:14.805754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Re-mixing Embeddings for Patient Augmentation in Data Scarce Multiple Instance Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Anastasia Litinetskaya, Ario Sadafi, Carsten Marr, Fatih Ozlugedik, Muhammed Furkan Dasdelen, Nassir Navab","submitted_at":"2026-06-24T12:45:44Z","abstract_excerpt":"Data scarcity is a major bottleneck in medical Multiple Instance Learning (MIL), especially for rare diseases or expensive modalities. We introduce a statistically grounded patient augmentation approach that generates realistic patients directly in embedding space. Using Gaussian Mixture Models as a probabilistic clustering approach on pooled instance embeddings from all patients, our method learns disease-specific \"recipes\"-statistical distributions of instances across unsupervised clusters. New patients are then generated by sampling embeddings from clusters based on learned recipes. Unlike "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25770","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/2606.25770/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":"2606.25770","created_at":"2026-06-25T01:18:14.805820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25770v1","created_at":"2026-06-25T01:18:14.805820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25770","created_at":"2026-06-25T01:18:14.805820+00:00"},{"alias_kind":"pith_short_12","alias_value":"VINKXVPWYYTV","created_at":"2026-06-25T01:18:14.805820+00:00"},{"alias_kind":"pith_short_16","alias_value":"VINKXVPWYYTVVTON","created_at":"2026-06-25T01:18:14.805820+00:00"},{"alias_kind":"pith_short_8","alias_value":"VINKXVPW","created_at":"2026-06-25T01:18:14.805820+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/VINKXVPWYYTVVTON7ZCEZZNVAU","json":"https://pith.science/pith/VINKXVPWYYTVVTON7ZCEZZNVAU.json","graph_json":"https://pith.science/api/pith-number/VINKXVPWYYTVVTON7ZCEZZNVAU/graph.json","events_json":"https://pith.science/api/pith-number/VINKXVPWYYTVVTON7ZCEZZNVAU/events.json","paper":"https://pith.science/paper/VINKXVPW"},"agent_actions":{"view_html":"https://pith.science/pith/VINKXVPWYYTVVTON7ZCEZZNVAU","download_json":"https://pith.science/pith/VINKXVPWYYTVVTON7ZCEZZNVAU.json","view_paper":"https://pith.science/paper/VINKXVPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25770&json=true","fetch_graph":"https://pith.science/api/pith-number/VINKXVPWYYTVVTON7ZCEZZNVAU/graph.json","fetch_events":"https://pith.science/api/pith-number/VINKXVPWYYTVVTON7ZCEZZNVAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VINKXVPWYYTVVTON7ZCEZZNVAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VINKXVPWYYTVVTON7ZCEZZNVAU/action/storage_attestation","attest_author":"https://pith.science/pith/VINKXVPWYYTVVTON7ZCEZZNVAU/action/author_attestation","sign_citation":"https://pith.science/pith/VINKXVPWYYTVVTON7ZCEZZNVAU/action/citation_signature","submit_replication":"https://pith.science/pith/VINKXVPWYYTVVTON7ZCEZZNVAU/action/replication_record"}},"created_at":"2026-06-25T01:18:14.805820+00:00","updated_at":"2026-06-25T01:18:14.805820+00:00"}