{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7JADUI6FS3LPRTEJYI4OPWW5HP","short_pith_number":"pith:7JADUI6F","canonical_record":{"source":{"id":"2111.04253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-08T03:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"4fb0e083b339658b8bc2e81dc17d51aff37f48e5e3f7215509af5885e754721c","abstract_canon_sha256":"4c5359c71edcc90ba5f71730e7017f57f3129b94477a9cd8aa94b1c80ef3be96"},"schema_version":"1.0"},"canonical_sha256":"fa403a23c596d6f8cc89c238e7dadd3bffbac5dcb767ba082c03217996d2f01b","source":{"kind":"arxiv","id":"2111.04253","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7JADUI6FS3LPRTEJYI4OPWW5HP","target":"record","payload":{"canonical_record":{"source":{"id":"2111.04253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-08T03:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"4fb0e083b339658b8bc2e81dc17d51aff37f48e5e3f7215509af5885e754721c","abstract_canon_sha256":"4c5359c71edcc90ba5f71730e7017f57f3129b94477a9cd8aa94b1c80ef3be96"},"schema_version":"1.0"},"canonical_sha256":"fa403a23c596d6f8cc89c238e7dadd3bffbac5dcb767ba082c03217996d2f01b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:57.109646Z","signature_b64":"mw6ASK3jqMv8mcAd4KbdhERgOpgOx8l51Fc+wGfWSwStK/44LUhkCOZh1seNfYshryJAhUNCyLONBd8NNohYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa403a23c596d6f8cc89c238e7dadd3bffbac5dcb767ba082c03217996d2f01b","last_reissued_at":"2026-07-05T03:29:57.109151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:57.109151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.04253","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:29:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mqHtKgdnsD2muaysUMeAVUj5xDGLks6FAvOiGwE0jm6jYcr9fQmHPMcnT7/mKXuvDJaKf6VdPocDhP4TO1xSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:22:13.062775Z"},"content_sha256":"33ef4a93c9521c56ce8258c96f1a1a18ec3a7b51e135f742a08e32a24242d146","schema_version":"1.0","event_id":"sha256:33ef4a93c9521c56ce8258c96f1a1a18ec3a7b51e135f742a08e32a24242d146"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7JADUI6FS3LPRTEJYI4OPWW5HP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Novel Data Pre-processing Technique: Making Data Mining Robust to Different Units and Scales of Measurement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arbind Agrahari Baniya, Santosh KC, Sunil Aryal","submitted_at":"2021-11-08T03:14:14Z","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 | "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.04253","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.04253/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":"2026-07-05T03:29:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yIDF8CkYe3Ws4r4/QIxh4x+s3S+F0j1V611kB0aK2YzWTgpdkvimMp3BuZ7HnAQ/hhU6geJP9Xk8I9rEyIzcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:22:13.063342Z"},"content_sha256":"c54616a2b5ca743fa8b720befbb1a9a5deb4f8dd6c8745c3398676220b8b8074","schema_version":"1.0","event_id":"sha256:c54616a2b5ca743fa8b720befbb1a9a5deb4f8dd6c8745c3398676220b8b8074"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7JADUI6FS3LPRTEJYI4OPWW5HP/bundle.json","state_url":"https://pith.science/pith/7JADUI6FS3LPRTEJYI4OPWW5HP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7JADUI6FS3LPRTEJYI4OPWW5HP/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":"2026-08-12T20:22:13Z","links":{"resolver":"https://pith.science/pith/7JADUI6FS3LPRTEJYI4OPWW5HP","bundle":"https://pith.science/pith/7JADUI6FS3LPRTEJYI4OPWW5HP/bundle.json","state":"https://pith.science/pith/7JADUI6FS3LPRTEJYI4OPWW5HP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7JADUI6FS3LPRTEJYI4OPWW5HP/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"52yqZZq4mFuwlpfE69B5L0hBB7fzdllFgBlb46c2I/3Fyf07mEPKM8OXh3zUonC0KNKJbJJltb5XFodnVM9iDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T20:22:13.068756Z","bundle_sha256":"ac96a82de21e0f719db7856c01f063cc52210fa6236e36add8bec04519e011f9"}}