{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UANI5RHBGKA7GNQERKVDAZ3PPF","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":"dcac68a825c066df66da3aaa7db9798ce3b71be549e045f8bee7276c8a6a2954","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2021-08-11T10:15:06Z","title_canon_sha256":"76253eac3a4f0794900a451eb6c3fe20fb085e19e736ebf4279e2c9f15a581a7"},"schema_version":"1.0","source":{"id":"2108.05129","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05129","created_at":"2026-07-05T03:05:07Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05129v1","created_at":"2026-07-05T03:05:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05129","created_at":"2026-07-05T03:05:07Z"},{"alias_kind":"pith_short_12","alias_value":"UANI5RHBGKA7","created_at":"2026-07-05T03:05:07Z"},{"alias_kind":"pith_short_16","alias_value":"UANI5RHBGKA7GNQE","created_at":"2026-07-05T03:05:07Z"},{"alias_kind":"pith_short_8","alias_value":"UANI5RHB","created_at":"2026-07-05T03:05:07Z"}],"graph_snapshots":[{"event_id":"sha256:828a920d093dcae5712d32aeaa4a0a927ebaaf7f61bb39fc09a20095f5e0e2da","target":"graph","created_at":"2026-07-05T03:05:07Z","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/2108.05129/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we extend our PrInDT method (Weihs & Buschfeld 2021a) towards undersampling with different percentages of the smaller and the larger classes (psmall and plarge), stratification of predictors, varying the prediction threshold, and measuring variable importance in ensembles. An application of these methods to a linguistic example suggests the following: 1. In undersampling, a careful selection of the percentages plarge and psmall is important for building models with high balanced accuracies; 2. Stratification of predictors does not majorly enhance balanced accuracies; 3. Lowering","authors_text":"Claus Weihs, Sarah Buschfeld","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2021-08-11T10:15:06Z","title":"Repeated undersampling in PrInDT (RePrInDT): Variation in undersampling and prediction, and ranking of predictors in ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05129","kind":"arxiv","version":1},"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":"sha256:68faf8e341488a0f8154b48747ef0f133bb77707e1dbb14144349137ed698596","target":"record","created_at":"2026-07-05T03:05:07Z","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":"dcac68a825c066df66da3aaa7db9798ce3b71be549e045f8bee7276c8a6a2954","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2021-08-11T10:15:06Z","title_canon_sha256":"76253eac3a4f0794900a451eb6c3fe20fb085e19e736ebf4279e2c9f15a581a7"},"schema_version":"1.0","source":{"id":"2108.05129","kind":"arxiv","version":1}},"canonical_sha256":"a01a8ec4e13281f336048aaa30676f796fa894e518d2f2b9bae8f051d661c041","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a01a8ec4e13281f336048aaa30676f796fa894e518d2f2b9bae8f051d661c041","first_computed_at":"2026-07-05T03:05:07.035573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:07.035573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I/vYdCiVcYj6ypysZKezIIFCG6zVfYSPxP2Tgu2iOHg/LhCNdMr16GstuCGSjmEn12fQGMlWnkRIXGCOwd9tAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:07.035978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.05129","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68faf8e341488a0f8154b48747ef0f133bb77707e1dbb14144349137ed698596","sha256:828a920d093dcae5712d32aeaa4a0a927ebaaf7f61bb39fc09a20095f5e0e2da"],"state_sha256":"d6e239a79e28f0204cd79bd2e12c1743ad9ebb6c3b6cbcbb45a8c3d577cdff69"}