{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M6ZINE3YLKO7THQC2HC73WNMUP","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":"181d8918e731084c4a4530451d30c080401076aea62731bcfaa637a50f75b955","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-29T20:55:50Z","title_canon_sha256":"a04d3c3e8f6dac38ef9d28cea9143d10bdeb66636f167bf4130fc31541a4e6df"},"schema_version":"1.0","source":{"id":"2604.27195","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27195","created_at":"2026-05-21T02:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27195v2","created_at":"2026-05-21T02:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27195","created_at":"2026-05-21T02:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"M6ZINE3YLKO7","created_at":"2026-05-21T02:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"M6ZINE3YLKO7THQC","created_at":"2026-05-21T02:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"M6ZINE3Y","created_at":"2026-05-21T02:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:490f4cd20d43adb5f3bf884b82d18bba95401ea091cbc3431a07cc606e7504a0","target":"graph","created_at":"2026-05-21T02:05:03Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"TabPFN achieved one the highest performance (AUC=0.892), outperforming LightGBM (AUC=0.860) and demonstrating advantages in low data settings. At N=50 training samples, TabPFN maintained strong AUC while the traditional machine learning models struggles at small training samples."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That differences in reported AUC arise from model architecture rather than unstated hyperparameter tuning, feature preprocessing choices, or train-test leakage in the TADPOLE splits."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TabPFN reaches AUC 0.892 for 3-year MCI-to-AD conversion on TADPOLE data and holds performance at N=50 training samples where XGBoost, Random Forest, LightGBM, and logistic regression degrade."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"TabPFN outperforms traditional machine learning models when predicting conversion from mild cognitive impairment to Alzheimer's disease in settings with limited training data."}],"snapshot_sha256":"492abc6b2a6cd5dca5c95a6f19e8c1584360fb941649139431709427fcc9f651"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T22:42:38.105708Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T19:31:33.428088Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.27195/integrity.json","findings":[],"snapshot_sha256":"b97128290d20c7f9e26532b6427d4fe51941f9d15403dcbf9c40e6e9a9b2562d","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate prediction of conversion from Mild Cognitive Impairment (MCI) to Alzheimers Diseases (AD) is essential for early intervention, however, developing reliable conversion predictive models is difficult to develop due to limited longitudinal data availability We evaluate TabPFN (Tabular Pre-Trained Foundation Network) against traditional machine learning methods for predicting 3 year MCI to AD conversion using the TADPOLE dataset derived from ADNI. Using multimodal biomarker features extracted from demographics, APOE4, MRI volumes, CSF markers, and PET imaging, we conducted an experimental","authors_text":"Brad Ye, Bulent Soykan, Gulsah Hancerliogullari Koksalmis, Hsin-Hsiung Huang, Laura J. Brattain","cross_cats":[],"headline":"TabPFN outperforms traditional machine learning models when predicting conversion from mild cognitive impairment to Alzheimer's disease in settings with limited training data.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-29T20:55:50Z","title":"Evaluating TabPFN for Mild Cognitive Impairment to Alzheimer's Disease Conversion in Data Limited Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.27195","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T09:32:21.971897Z","id":"85407175-1322-4258-8f0e-c62c5ac14cd8","model_set":{"reader":"grok-4.3"},"one_line_summary":"TabPFN reaches AUC 0.892 for 3-year MCI-to-AD conversion on TADPOLE data and holds performance at N=50 training samples where XGBoost, Random Forest, LightGBM, and logistic regression degrade.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"TabPFN outperforms traditional machine learning models when predicting conversion from mild cognitive impairment to Alzheimer's disease in settings with limited training data.","strongest_claim":"TabPFN achieved one the highest performance (AUC=0.892), outperforming LightGBM (AUC=0.860) and demonstrating advantages in low data settings. At N=50 training samples, TabPFN maintained strong AUC while the traditional machine learning models struggles at small training samples.","weakest_assumption":"That differences in reported AUC arise from model architecture rather than unstated hyperparameter tuning, feature preprocessing choices, or train-test leakage in the TADPOLE splits."}},"verdict_id":"85407175-1322-4258-8f0e-c62c5ac14cd8"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:72e83d030b5109bd334775dc7557d3caf669525627554d23590807abb1c7d9ac","target":"record","created_at":"2026-05-21T02:05:03Z","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":"181d8918e731084c4a4530451d30c080401076aea62731bcfaa637a50f75b955","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-29T20:55:50Z","title_canon_sha256":"a04d3c3e8f6dac38ef9d28cea9143d10bdeb66636f167bf4130fc31541a4e6df"},"schema_version":"1.0","source":{"id":"2604.27195","kind":"arxiv","version":2}},"canonical_sha256":"67b28693785a9df99e02d1c5fdd9aca3c19bf00f54bb6007133073e4c59571e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67b28693785a9df99e02d1c5fdd9aca3c19bf00f54bb6007133073e4c59571e9","first_computed_at":"2026-05-21T02:05:03.656652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T02:05:03.656652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/IVa7j8i9xt5A+/yxr346VkCLG+ozkBTtsBujc+0Alo3LWse8fpxyXvZEZP/W5Mn82mhPfyPSqg8Nrh0iiO1BQ==","signature_status":"signed_v1","signed_at":"2026-05-21T02:05:03.657185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.27195","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72e83d030b5109bd334775dc7557d3caf669525627554d23590807abb1c7d9ac","sha256:490f4cd20d43adb5f3bf884b82d18bba95401ea091cbc3431a07cc606e7504a0"],"state_sha256":"8315944082c7e453dd41e20a3de98d32dd645cf857bbfb857be81bd80b53c990"}