{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AI55SAI72LZR6H7DLGVQJVYQZ4","short_pith_number":"pith:AI55SAI7","schema_version":"1.0","canonical_sha256":"023bd9011fd2f31f1fe359ab04d710cf2e3f06d064688c3eff3b37620c83ec94","source":{"kind":"arxiv","id":"2312.09380","version":1},"attestation_state":"computed","paper":{"title":"Two-sample KS test with approxQuantile in Apache Spark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Amadou Ba, Bradley Eck, Duygu Kabakci-Zorlu","submitted_at":"2023-12-14T22:30:29Z","abstract_excerpt":"The classical two-sample test of Kolmogorov-Smirnov (KS) is widely used to test whether empirical samples come from the same distribution. Even though most statistical packages provide an implementation, carrying out the test in big data settings can be challenging because it requires a full sort of the data. The popular Apache Spark system for big data processing provides a 1-sample KS test, but not the 2-sample version. Moreover, recent Spark versions provide the approxQuantile method for querying $\\epsilon$-approximate quantiles. We build on approxQuantile to propose a variation of the clas"},"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":"2312.09380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2023-12-14T22:30:29Z","cross_cats_sorted":[],"title_canon_sha256":"31b6284775ef02cca0087773f0c51056c46cb2ab442a9177098d922bfcbde84b","abstract_canon_sha256":"84b96d0e287c40c697dd8d513800f222a2f266b5a11cad5fdcf4b180ca2e7c70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:24.095198Z","signature_b64":"Gvl01eImnfAx8dCM8yZCD8ee5Xsubmn0g/t7ih+3VEiTsHbjji4FprsoSB1Wy7Fvp4JqQxCiJwZfvM+dNfCOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"023bd9011fd2f31f1fe359ab04d710cf2e3f06d064688c3eff3b37620c83ec94","last_reissued_at":"2026-07-05T07:24:24.094792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:24.094792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two-sample KS test with approxQuantile in Apache Spark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Amadou Ba, Bradley Eck, Duygu Kabakci-Zorlu","submitted_at":"2023-12-14T22:30:29Z","abstract_excerpt":"The classical two-sample test of Kolmogorov-Smirnov (KS) is widely used to test whether empirical samples come from the same distribution. Even though most statistical packages provide an implementation, carrying out the test in big data settings can be challenging because it requires a full sort of the data. The popular Apache Spark system for big data processing provides a 1-sample KS test, but not the 2-sample version. Moreover, recent Spark versions provide the approxQuantile method for querying $\\epsilon$-approximate quantiles. We build on approxQuantile to propose a variation of the clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09380","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/2312.09380/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":"2312.09380","created_at":"2026-07-05T07:24:24.094846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09380v1","created_at":"2026-07-05T07:24:24.094846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09380","created_at":"2026-07-05T07:24:24.094846+00:00"},{"alias_kind":"pith_short_12","alias_value":"AI55SAI72LZR","created_at":"2026-07-05T07:24:24.094846+00:00"},{"alias_kind":"pith_short_16","alias_value":"AI55SAI72LZR6H7D","created_at":"2026-07-05T07:24:24.094846+00:00"},{"alias_kind":"pith_short_8","alias_value":"AI55SAI7","created_at":"2026-07-05T07:24:24.094846+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/AI55SAI72LZR6H7DLGVQJVYQZ4","json":"https://pith.science/pith/AI55SAI72LZR6H7DLGVQJVYQZ4.json","graph_json":"https://pith.science/api/pith-number/AI55SAI72LZR6H7DLGVQJVYQZ4/graph.json","events_json":"https://pith.science/api/pith-number/AI55SAI72LZR6H7DLGVQJVYQZ4/events.json","paper":"https://pith.science/paper/AI55SAI7"},"agent_actions":{"view_html":"https://pith.science/pith/AI55SAI72LZR6H7DLGVQJVYQZ4","download_json":"https://pith.science/pith/AI55SAI72LZR6H7DLGVQJVYQZ4.json","view_paper":"https://pith.science/paper/AI55SAI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09380&json=true","fetch_graph":"https://pith.science/api/pith-number/AI55SAI72LZR6H7DLGVQJVYQZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/AI55SAI72LZR6H7DLGVQJVYQZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AI55SAI72LZR6H7DLGVQJVYQZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AI55SAI72LZR6H7DLGVQJVYQZ4/action/storage_attestation","attest_author":"https://pith.science/pith/AI55SAI72LZR6H7DLGVQJVYQZ4/action/author_attestation","sign_citation":"https://pith.science/pith/AI55SAI72LZR6H7DLGVQJVYQZ4/action/citation_signature","submit_replication":"https://pith.science/pith/AI55SAI72LZR6H7DLGVQJVYQZ4/action/replication_record"}},"created_at":"2026-07-05T07:24:24.094846+00:00","updated_at":"2026-07-05T07:24:24.094846+00:00"}