{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7JADUI6FS3LPRTEJYI4OPWW5HP","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":"4c5359c71edcc90ba5f71730e7017f57f3129b94477a9cd8aa94b1c80ef3be96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-08T03:14:14Z","title_canon_sha256":"4fb0e083b339658b8bc2e81dc17d51aff37f48e5e3f7215509af5885e754721c"},"schema_version":"1.0","source":{"id":"2111.04253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.04253","created_at":"2026-07-05T03:29:57Z"},{"alias_kind":"arxiv_version","alias_value":"2111.04253v1","created_at":"2026-07-05T03:29:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.04253","created_at":"2026-07-05T03:29:57Z"},{"alias_kind":"pith_short_12","alias_value":"7JADUI6FS3LP","created_at":"2026-07-05T03:29:57Z"},{"alias_kind":"pith_short_16","alias_value":"7JADUI6FS3LPRTEJ","created_at":"2026-07-05T03:29:57Z"},{"alias_kind":"pith_short_8","alias_value":"7JADUI6F","created_at":"2026-07-05T03:29:57Z"}],"graph_snapshots":[{"event_id":"sha256:c54616a2b5ca743fa8b720befbb1a9a5deb4f8dd6c8745c3398676220b8b8074","target":"graph","created_at":"2026-07-05T03:29:57Z","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/2111.04253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many existing data mining algorithms use feature values directly in their model, making them sensitive to units/scales used to measure/represent data. Pre-processing of data based on rank transformation has been suggested as a potential solution to overcome this issue. However, the resulting data after pre-processing with rank transformation is uniformly distributed, which may not be very useful in many data mining applications. In this paper, we present a better and effective alternative based on ranks over multiple sub-samples of data. We call the proposed pre-processing technique as ARES | ","authors_text":"Arbind Agrahari Baniya, Santosh KC, Sunil Aryal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-08T03:14:14Z","title":"A Novel Data Pre-processing Technique: Making Data Mining Robust to Different Units and Scales of Measurement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.04253","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":"sha256:33ef4a93c9521c56ce8258c96f1a1a18ec3a7b51e135f742a08e32a24242d146","target":"record","created_at":"2026-07-05T03:29:57Z","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":"4c5359c71edcc90ba5f71730e7017f57f3129b94477a9cd8aa94b1c80ef3be96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-08T03:14:14Z","title_canon_sha256":"4fb0e083b339658b8bc2e81dc17d51aff37f48e5e3f7215509af5885e754721c"},"schema_version":"1.0","source":{"id":"2111.04253","kind":"arxiv","version":1}},"canonical_sha256":"fa403a23c596d6f8cc89c238e7dadd3bffbac5dcb767ba082c03217996d2f01b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa403a23c596d6f8cc89c238e7dadd3bffbac5dcb767ba082c03217996d2f01b","first_computed_at":"2026-07-05T03:29:57.109151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:57.109151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mw6ASK3jqMv8mcAd4KbdhERgOpgOx8l51Fc+wGfWSwStK/44LUhkCOZh1seNfYshryJAhUNCyLONBd8NNohYBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:57.109646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.04253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33ef4a93c9521c56ce8258c96f1a1a18ec3a7b51e135f742a08e32a24242d146","sha256:c54616a2b5ca743fa8b720befbb1a9a5deb4f8dd6c8745c3398676220b8b8074"],"state_sha256":"e514ef11cd1d6150dfd3a394544472d528da3b1124027daf44709b4f3f577e17"}