{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:PCNNBF2ZXIK6RYT4RUO6M6W52Y","short_pith_number":"pith:PCNNBF2Z","schema_version":"1.0","canonical_sha256":"789ad09759ba15e8e27c8d1de67addd618fd1a001a970ce682aa0228b925fe25","source":{"kind":"arxiv","id":"1601.06212","version":1},"attestation_state":"computed","paper":{"title":"Nonparametric Heterogeneity Testing For Massive Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Guang Cheng, Han Liu, Junwei Lu","submitted_at":"2016-01-23T00:34:19Z","abstract_excerpt":"A massive dataset often consists of a growing number of (potentially) heterogeneous sub-populations. This paper is concerned about testing various forms of heterogeneity arising from massive data. In a general nonparametric framework, a set of testing procedures are designed to accommodate a growing number of sub-populations, denoted as $s$, with computational feasibility. In theory, their null limit distributions are derived as being nearly Chi-square with diverging degrees of freedom as long as $s$ does not grow too fast. Interestingly, we find that a lower bound on $s$ needs to be set for o"},"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":"1601.06212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2016-01-23T00:34:19Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"767ad1c71b14fc1265bdd8edc440ff925454515675e026a93294062818a2b3ca","abstract_canon_sha256":"742179a9aaaed13044ae3cda52941b1274e0dfca2cdf3890fa47b99e60d512f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:05.099560Z","signature_b64":"viOIP4/sPBcDlEf5iQU+Yi+ussr5/9Nld/dGdsR7jR9te2nRjEnWKaL7xoL46+NbEixb28VHjLffHWWay8C1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"789ad09759ba15e8e27c8d1de67addd618fd1a001a970ce682aa0228b925fe25","last_reissued_at":"2026-05-18T01:22:05.098914Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:05.098914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonparametric Heterogeneity Testing For Massive Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Guang Cheng, Han Liu, Junwei Lu","submitted_at":"2016-01-23T00:34:19Z","abstract_excerpt":"A massive dataset often consists of a growing number of (potentially) heterogeneous sub-populations. This paper is concerned about testing various forms of heterogeneity arising from massive data. In a general nonparametric framework, a set of testing procedures are designed to accommodate a growing number of sub-populations, denoted as $s$, with computational feasibility. In theory, their null limit distributions are derived as being nearly Chi-square with diverging degrees of freedom as long as $s$ does not grow too fast. Interestingly, we find that a lower bound on $s$ needs to be set for o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.06212","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":""},"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":"1601.06212","created_at":"2026-05-18T01:22:05.098984+00:00"},{"alias_kind":"arxiv_version","alias_value":"1601.06212v1","created_at":"2026-05-18T01:22:05.098984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.06212","created_at":"2026-05-18T01:22:05.098984+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCNNBF2ZXIK6","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCNNBF2ZXIK6RYT4","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCNNBF2Z","created_at":"2026-05-18T12:30:39.010887+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/PCNNBF2ZXIK6RYT4RUO6M6W52Y","json":"https://pith.science/pith/PCNNBF2ZXIK6RYT4RUO6M6W52Y.json","graph_json":"https://pith.science/api/pith-number/PCNNBF2ZXIK6RYT4RUO6M6W52Y/graph.json","events_json":"https://pith.science/api/pith-number/PCNNBF2ZXIK6RYT4RUO6M6W52Y/events.json","paper":"https://pith.science/paper/PCNNBF2Z"},"agent_actions":{"view_html":"https://pith.science/pith/PCNNBF2ZXIK6RYT4RUO6M6W52Y","download_json":"https://pith.science/pith/PCNNBF2ZXIK6RYT4RUO6M6W52Y.json","view_paper":"https://pith.science/paper/PCNNBF2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1601.06212&json=true","fetch_graph":"https://pith.science/api/pith-number/PCNNBF2ZXIK6RYT4RUO6M6W52Y/graph.json","fetch_events":"https://pith.science/api/pith-number/PCNNBF2ZXIK6RYT4RUO6M6W52Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCNNBF2ZXIK6RYT4RUO6M6W52Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCNNBF2ZXIK6RYT4RUO6M6W52Y/action/storage_attestation","attest_author":"https://pith.science/pith/PCNNBF2ZXIK6RYT4RUO6M6W52Y/action/author_attestation","sign_citation":"https://pith.science/pith/PCNNBF2ZXIK6RYT4RUO6M6W52Y/action/citation_signature","submit_replication":"https://pith.science/pith/PCNNBF2ZXIK6RYT4RUO6M6W52Y/action/replication_record"}},"created_at":"2026-05-18T01:22:05.098984+00:00","updated_at":"2026-05-18T01:22:05.098984+00:00"}