{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XCLZDB545TTOBC6RMHY2CJPOOH","short_pith_number":"pith:XCLZDB54","schema_version":"1.0","canonical_sha256":"b8979187bcece6e08bd161f1a125ee71de607f978e3b9c0e76b3c630e1270156","source":{"kind":"arxiv","id":"2507.13393","version":1},"attestation_state":"computed","paper":{"title":"Improving KAN with CDF normalization to quantiles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jakub Strawa, Jarek Duda","submitted_at":"2025-07-16T09:24:11Z","abstract_excerpt":"Data normalization is crucial in machine learning, usually performed by subtracting the mean and dividing by standard deviation, or by rescaling to a fixed range. In copula theory, popular in finance, there is used normalization to approximately quantiles by transforming x to CDF(x) with estimated CDF (cumulative distribution function) to nearly uniform distribution in [0,1], allowing for simpler representations which are less likely to overfit. It seems nearly unknown in machine learning, therefore, we would like to present some its advantages on example of recently popular Kolmogorov-Arnold "},"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":"2507.13393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T09:24:11Z","cross_cats_sorted":[],"title_canon_sha256":"22668d01fcb0b3078c77601c2211f02fcba25e58e7f6ebdc66123bb5ffeddcd8","abstract_canon_sha256":"67035e57922cd9fb3379235d07c94f78abc8127c7c1bed275a4ba913ef2315e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:16.652182Z","signature_b64":"g7iEFPVy3q3pR6EF7B60DFG5tHbtQMaTle/deT2elVGnAwazeNVV2k4XXcD2lR51iy23Vzcdzs2S6GcIzfkiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8979187bcece6e08bd161f1a125ee71de607f978e3b9c0e76b3c630e1270156","last_reissued_at":"2026-07-05T11:39:16.651717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:16.651717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving KAN with CDF normalization to quantiles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jakub Strawa, Jarek Duda","submitted_at":"2025-07-16T09:24:11Z","abstract_excerpt":"Data normalization is crucial in machine learning, usually performed by subtracting the mean and dividing by standard deviation, or by rescaling to a fixed range. In copula theory, popular in finance, there is used normalization to approximately quantiles by transforming x to CDF(x) with estimated CDF (cumulative distribution function) to nearly uniform distribution in [0,1], allowing for simpler representations which are less likely to overfit. It seems nearly unknown in machine learning, therefore, we would like to present some its advantages on example of recently popular Kolmogorov-Arnold "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13393","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/2507.13393/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.13393","created_at":"2026-07-05T11:39:16.651787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13393v1","created_at":"2026-07-05T11:39:16.651787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13393","created_at":"2026-07-05T11:39:16.651787+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCLZDB545TTO","created_at":"2026-07-05T11:39:16.651787+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCLZDB545TTOBC6R","created_at":"2026-07-05T11:39:16.651787+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCLZDB54","created_at":"2026-07-05T11:39:16.651787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.05097","citing_title":"Biology-inspired joint distribution neurons based on Hierarchical Correlation Reconstruction allowing for multidirectional propagation of values and densities","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCLZDB545TTOBC6RMHY2CJPOOH","json":"https://pith.science/pith/XCLZDB545TTOBC6RMHY2CJPOOH.json","graph_json":"https://pith.science/api/pith-number/XCLZDB545TTOBC6RMHY2CJPOOH/graph.json","events_json":"https://pith.science/api/pith-number/XCLZDB545TTOBC6RMHY2CJPOOH/events.json","paper":"https://pith.science/paper/XCLZDB54"},"agent_actions":{"view_html":"https://pith.science/pith/XCLZDB545TTOBC6RMHY2CJPOOH","download_json":"https://pith.science/pith/XCLZDB545TTOBC6RMHY2CJPOOH.json","view_paper":"https://pith.science/paper/XCLZDB54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13393&json=true","fetch_graph":"https://pith.science/api/pith-number/XCLZDB545TTOBC6RMHY2CJPOOH/graph.json","fetch_events":"https://pith.science/api/pith-number/XCLZDB545TTOBC6RMHY2CJPOOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCLZDB545TTOBC6RMHY2CJPOOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCLZDB545TTOBC6RMHY2CJPOOH/action/storage_attestation","attest_author":"https://pith.science/pith/XCLZDB545TTOBC6RMHY2CJPOOH/action/author_attestation","sign_citation":"https://pith.science/pith/XCLZDB545TTOBC6RMHY2CJPOOH/action/citation_signature","submit_replication":"https://pith.science/pith/XCLZDB545TTOBC6RMHY2CJPOOH/action/replication_record"}},"created_at":"2026-07-05T11:39:16.651787+00:00","updated_at":"2026-07-05T11:39:16.651787+00:00"}