{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XA7KCQW26WH3PM64NPN4ZA3LLE","short_pith_number":"pith:XA7KCQW2","schema_version":"1.0","canonical_sha256":"b83ea142daf58fb7b3dc6bdbcc836b5912e493857d193a8a5c85b338fd7cc118","source":{"kind":"arxiv","id":"1810.09942","version":1},"attestation_state":"computed","paper":{"title":"Preprocessor Selection for Machine Learning Pipelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Brandon Schoenfeld, Christophe Giraud-Carrier, Jarom Christensen, Kevin Seppi, Mason Poggemann","submitted_at":"2018-10-23T16:14:11Z","abstract_excerpt":"Much of the work in metalearning has focused on classifier selection, combined more recently with hyperparameter optimization, with little concern for data preprocessing. Yet, it is generally well accepted that machine learning applications require not only model building, but also data preprocessing. In other words, practical solutions consist of pipelines of machine learning operators rather than single algorithms. Interestingly, our experiments suggest that, on average, data preprocessing hinders accuracy, while the best performing pipelines do actually make use of preprocessors. Here, we c"},"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":"1810.09942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-23T16:14:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f1c5778c2496ad4955d8f77ca3194e822f96927d58aa5381123da024c698508d","abstract_canon_sha256":"5276bc71b13d73b54a74ed3dc8a54dccb86d6ec173bb5ef0a63113e0dbe89130"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:28.869201Z","signature_b64":"CeBnXjI8U51grL3cm+QWIXq89Z02KRb2/Z/SYCIYS9FFzj6s0rJ7PUufcag1AWx2/v+RMx+B8bJTAGginyv3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b83ea142daf58fb7b3dc6bdbcc836b5912e493857d193a8a5c85b338fd7cc118","last_reissued_at":"2026-05-18T00:02:28.868553Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:28.868553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preprocessor Selection for Machine Learning Pipelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Brandon Schoenfeld, Christophe Giraud-Carrier, Jarom Christensen, Kevin Seppi, Mason Poggemann","submitted_at":"2018-10-23T16:14:11Z","abstract_excerpt":"Much of the work in metalearning has focused on classifier selection, combined more recently with hyperparameter optimization, with little concern for data preprocessing. Yet, it is generally well accepted that machine learning applications require not only model building, but also data preprocessing. In other words, practical solutions consist of pipelines of machine learning operators rather than single algorithms. Interestingly, our experiments suggest that, on average, data preprocessing hinders accuracy, while the best performing pipelines do actually make use of preprocessors. Here, we c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09942","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":""},"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":"1810.09942","created_at":"2026-05-18T00:02:28.868668+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.09942v1","created_at":"2026-05-18T00:02:28.868668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09942","created_at":"2026-05-18T00:02:28.868668+00:00"},{"alias_kind":"pith_short_12","alias_value":"XA7KCQW26WH3","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XA7KCQW26WH3PM64","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XA7KCQW2","created_at":"2026-05-18T12:33:01.666342+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/XA7KCQW26WH3PM64NPN4ZA3LLE","json":"https://pith.science/pith/XA7KCQW26WH3PM64NPN4ZA3LLE.json","graph_json":"https://pith.science/api/pith-number/XA7KCQW26WH3PM64NPN4ZA3LLE/graph.json","events_json":"https://pith.science/api/pith-number/XA7KCQW26WH3PM64NPN4ZA3LLE/events.json","paper":"https://pith.science/paper/XA7KCQW2"},"agent_actions":{"view_html":"https://pith.science/pith/XA7KCQW26WH3PM64NPN4ZA3LLE","download_json":"https://pith.science/pith/XA7KCQW26WH3PM64NPN4ZA3LLE.json","view_paper":"https://pith.science/paper/XA7KCQW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.09942&json=true","fetch_graph":"https://pith.science/api/pith-number/XA7KCQW26WH3PM64NPN4ZA3LLE/graph.json","fetch_events":"https://pith.science/api/pith-number/XA7KCQW26WH3PM64NPN4ZA3LLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XA7KCQW26WH3PM64NPN4ZA3LLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XA7KCQW26WH3PM64NPN4ZA3LLE/action/storage_attestation","attest_author":"https://pith.science/pith/XA7KCQW26WH3PM64NPN4ZA3LLE/action/author_attestation","sign_citation":"https://pith.science/pith/XA7KCQW26WH3PM64NPN4ZA3LLE/action/citation_signature","submit_replication":"https://pith.science/pith/XA7KCQW26WH3PM64NPN4ZA3LLE/action/replication_record"}},"created_at":"2026-05-18T00:02:28.868668+00:00","updated_at":"2026-05-18T00:02:28.868668+00:00"}