{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GRBCPNEQWQKWKJN42BNK32BUGW","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":"21a3d294b3714b967b957d8f25e5bebc3e980faec09a661d7b259ee2eeab6ddb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T09:56:44Z","title_canon_sha256":"53d78474cd0aee1340f65261ed639b04300c3302b7365868aacbd6422849168f"},"schema_version":"1.0","source":{"id":"2312.16930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16930","created_at":"2026-07-05T07:28:37Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16930v1","created_at":"2026-07-05T07:28:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16930","created_at":"2026-07-05T07:28:37Z"},{"alias_kind":"pith_short_12","alias_value":"GRBCPNEQWQKW","created_at":"2026-07-05T07:28:37Z"},{"alias_kind":"pith_short_16","alias_value":"GRBCPNEQWQKWKJN4","created_at":"2026-07-05T07:28:37Z"},{"alias_kind":"pith_short_8","alias_value":"GRBCPNEQ","created_at":"2026-07-05T07:28:37Z"}],"graph_snapshots":[{"event_id":"sha256:12a2d44dcfa568c49350e435a5ce450b75ecb73a8b384c56c5cb16e7eb62c9a1","target":"graph","created_at":"2026-07-05T07:28:37Z","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/2312.16930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Categorical features are present in about 40% of real world problems, highlighting the crucial role of encoding as a preprocessing component. Some recent studies have reported benefits of the various target-based encoders over classical target-agnostic approaches. However, these claims are not supported by any statistical analysis, and are based on a single dataset or a very small and heterogeneous sample of datasets. The present study explores the encoding effects in an exhaustive sample of classification problems from OpenML repository. We fitted linear mixed-effects models to the experiment","authors_text":"Alexey Korolev, Ekaterina Poslavskaya","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T09:56:44Z","title":"Encoding categorical data: Is there yet anything 'hotter' than one-hot encoding?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16930","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:d80d7ee897b535fd2434b6d062d7002ee278f23225f959832e0c60aa66d74f25","target":"record","created_at":"2026-07-05T07:28:37Z","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":"21a3d294b3714b967b957d8f25e5bebc3e980faec09a661d7b259ee2eeab6ddb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T09:56:44Z","title_canon_sha256":"53d78474cd0aee1340f65261ed639b04300c3302b7365868aacbd6422849168f"},"schema_version":"1.0","source":{"id":"2312.16930","kind":"arxiv","version":1}},"canonical_sha256":"344227b490b4156525bcd05aade8343591aa01e0c6f1163a546e846049cca373","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"344227b490b4156525bcd05aade8343591aa01e0c6f1163a546e846049cca373","first_computed_at":"2026-07-05T07:28:37.147116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:37.147116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G5Lk/hIzEwT0FCIyaHmdReAiIAz0d7uIHZ5DwBLsmjjHtvLuHLs8ZhRFseumfhsPq0tBOU1N/90ISMRwPnqnAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:37.147574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.16930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d80d7ee897b535fd2434b6d062d7002ee278f23225f959832e0c60aa66d74f25","sha256:12a2d44dcfa568c49350e435a5ce450b75ecb73a8b384c56c5cb16e7eb62c9a1"],"state_sha256":"e851deb39f0b3aaff740bf0234d9bda67b075e8282446e8e47eeea13e6d1e9d4"}