{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QOIIWP474LDM3A76SXUSXXLYTJ","short_pith_number":"pith:QOIIWP47","canonical_record":{"source":{"id":"2103.14931","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2021-03-27T15:34:58Z","cross_cats_sorted":[],"title_canon_sha256":"0e9fc620606ad5792bfb6104f9eb43538efb0945664a5df5ad2eebf646bc7a6d","abstract_canon_sha256":"7f64eea7aa09dca83c7d35419b2704afa8685edd7fffb2afe67df49336cfc245"},"schema_version":"1.0"},"canonical_sha256":"83908b3f9fe2c6cd83fe95e92bdd789a5da255948666adf09d992f0f9caf635f","source":{"kind":"arxiv","id":"2103.14931","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.14931","created_at":"2026-07-05T03:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2103.14931v2","created_at":"2026-07-05T03:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14931","created_at":"2026-07-05T03:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"QOIIWP474LDM","created_at":"2026-07-05T03:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"QOIIWP474LDM3A76","created_at":"2026-07-05T03:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"QOIIWP47","created_at":"2026-07-05T03:09:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QOIIWP474LDM3A76SXUSXXLYTJ","target":"record","payload":{"canonical_record":{"source":{"id":"2103.14931","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2021-03-27T15:34:58Z","cross_cats_sorted":[],"title_canon_sha256":"0e9fc620606ad5792bfb6104f9eb43538efb0945664a5df5ad2eebf646bc7a6d","abstract_canon_sha256":"7f64eea7aa09dca83c7d35419b2704afa8685edd7fffb2afe67df49336cfc245"},"schema_version":"1.0"},"canonical_sha256":"83908b3f9fe2c6cd83fe95e92bdd789a5da255948666adf09d992f0f9caf635f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:29.545828Z","signature_b64":"5dBsDTCnyW1v7CdHGWnO5qwXjr/XbJWMW15t0eSig425YdYseqQvfVpFfeOSVfqdMZ0D0xJJyHXUv6BDHF+0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83908b3f9fe2c6cd83fe95e92bdd789a5da255948666adf09d992f0f9caf635f","last_reissued_at":"2026-07-05T03:09:29.545346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:29.545346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.14931","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":"2026-07-05T03:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GcoPM5fIZdeD0c1mh9tcvkBFyFdYmRTgNL9XLiB+5XYEXwdNbcR2Hbw5swMZSniQ0DvDYEdiwyNtdtzMevZYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:00:14.944596Z"},"content_sha256":"952ad0ee58f86ea72eee8b5c373d1994ed77a48d94c65c992dd77631ee84d6ce","schema_version":"1.0","event_id":"sha256:952ad0ee58f86ea72eee8b5c373d1994ed77a48d94c65c992dd77631ee84d6ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QOIIWP474LDM3A76SXUSXXLYTJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NesPrInDT: Nested undersampling in PrInDT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Claus Weihs, Sarah Buschfeld","submitted_at":"2021-03-27T15:34:58Z","abstract_excerpt":"In this paper, we extend our PrInDT method (Weihs, Buschfeld 2021) towards additional undersampling of one of the predictors. This helps us to handle multiple unbalanced data sets, i.e. data sets that are not only unbalanced with respect to the class variable but also in one of the predictor variables. Beyond the advantages of such an approach, our study reveals that the balanced accuracy in the full data set can be much lower than in the predictor undersamples. We discuss potential reasons for this problem and draw methodological conclusions for linguistic studies."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14931","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/2103.14931/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":"2026-07-05T03:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PyCaWZb7cJUEHR2H2jkSxSajfDEknREvaPpg2hYIHqm3MXtre4cE7BoYO0IBX8RRat14sYa1LPhPrTSDsskyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:00:14.944971Z"},"content_sha256":"e33248d35615c54a7087699057c1514af0e704037dabec30c507e9325b8c9e7b","schema_version":"1.0","event_id":"sha256:e33248d35615c54a7087699057c1514af0e704037dabec30c507e9325b8c9e7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QOIIWP474LDM3A76SXUSXXLYTJ/bundle.json","state_url":"https://pith.science/pith/QOIIWP474LDM3A76SXUSXXLYTJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QOIIWP474LDM3A76SXUSXXLYTJ/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":"2026-07-07T08:00:14Z","links":{"resolver":"https://pith.science/pith/QOIIWP474LDM3A76SXUSXXLYTJ","bundle":"https://pith.science/pith/QOIIWP474LDM3A76SXUSXXLYTJ/bundle.json","state":"https://pith.science/pith/QOIIWP474LDM3A76SXUSXXLYTJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QOIIWP474LDM3A76SXUSXXLYTJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QOIIWP474LDM3A76SXUSXXLYTJ","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":"7f64eea7aa09dca83c7d35419b2704afa8685edd7fffb2afe67df49336cfc245","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2021-03-27T15:34:58Z","title_canon_sha256":"0e9fc620606ad5792bfb6104f9eb43538efb0945664a5df5ad2eebf646bc7a6d"},"schema_version":"1.0","source":{"id":"2103.14931","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.14931","created_at":"2026-07-05T03:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2103.14931v2","created_at":"2026-07-05T03:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14931","created_at":"2026-07-05T03:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"QOIIWP474LDM","created_at":"2026-07-05T03:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"QOIIWP474LDM3A76","created_at":"2026-07-05T03:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"QOIIWP47","created_at":"2026-07-05T03:09:29Z"}],"graph_snapshots":[{"event_id":"sha256:e33248d35615c54a7087699057c1514af0e704037dabec30c507e9325b8c9e7b","target":"graph","created_at":"2026-07-05T03:09:29Z","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/2103.14931/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 2021) towards additional undersampling of one of the predictors. This helps us to handle multiple unbalanced data sets, i.e. data sets that are not only unbalanced with respect to the class variable but also in one of the predictor variables. Beyond the advantages of such an approach, our study reveals that the balanced accuracy in the full data set can be much lower than in the predictor undersamples. We discuss potential reasons for this problem and draw methodological conclusions for linguistic studies.","authors_text":"Claus Weihs, Sarah Buschfeld","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2021-03-27T15:34:58Z","title":"NesPrInDT: Nested undersampling in PrInDT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14931","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":"sha256:952ad0ee58f86ea72eee8b5c373d1994ed77a48d94c65c992dd77631ee84d6ce","target":"record","created_at":"2026-07-05T03:09:29Z","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":"7f64eea7aa09dca83c7d35419b2704afa8685edd7fffb2afe67df49336cfc245","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2021-03-27T15:34:58Z","title_canon_sha256":"0e9fc620606ad5792bfb6104f9eb43538efb0945664a5df5ad2eebf646bc7a6d"},"schema_version":"1.0","source":{"id":"2103.14931","kind":"arxiv","version":2}},"canonical_sha256":"83908b3f9fe2c6cd83fe95e92bdd789a5da255948666adf09d992f0f9caf635f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83908b3f9fe2c6cd83fe95e92bdd789a5da255948666adf09d992f0f9caf635f","first_computed_at":"2026-07-05T03:09:29.545346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:09:29.545346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5dBsDTCnyW1v7CdHGWnO5qwXjr/XbJWMW15t0eSig425YdYseqQvfVpFfeOSVfqdMZ0D0xJJyHXUv6BDHF+0Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T03:09:29.545828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.14931","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:952ad0ee58f86ea72eee8b5c373d1994ed77a48d94c65c992dd77631ee84d6ce","sha256:e33248d35615c54a7087699057c1514af0e704037dabec30c507e9325b8c9e7b"],"state_sha256":"933745fb92b78ea9c375d6a8627878242a099bea079ebc01fadaecf0d9a467f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4z4SPEL1kdClk5Z3JrkgO6fBXe7TZnnQPEPF0wx6x7D9v86HhBkhHOxRwnssmrErwNvKxdYWYjkgkp2YkhxKBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:00:14.946867Z","bundle_sha256":"bcb33d3a3c88e12c395f952d9e05296b18391a977d848a301945f536ef2395fb"}}