{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JJ3IE2SIDBXMOII4P5QITYRTK3","short_pith_number":"pith:JJ3IE2SI","schema_version":"1.0","canonical_sha256":"4a76826a48186ec7211c7f6089e23356f6431125b1c83a6a992d94d5908ec2dc","source":{"kind":"arxiv","id":"2503.14619","version":1},"attestation_state":"computed","paper":{"title":"The broken sample problem revisited: Proof of a conjecture by Bai-Hsing and high-dimensional extensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.TH"],"primary_cat":"math.ST","authors_text":"Jiaming Xu, Simiao Jiao, Yihong Wu","submitted_at":"2025-03-18T18:15:13Z","abstract_excerpt":"We revisit the classical broken sample problem: Two samples of i.i.d. data points $\\mathbf{X}=\\{X_1,\\cdots, X_n\\}$ and $\\mathbf{Y}=\\{Y_1,\\cdots,Y_m\\}$ are observed without correspondence with $m\\leq n$. Under the null hypothesis, $\\mathbf{X}$ and $\\mathbf{Y}$ are independent. Under the alternative hypothesis, $\\mathbf{Y}$ is correlated with a random subsample of $\\mathbf{X}$, in the sense that $(X_{\\pi(i)},Y_i)$'s are drawn independently from some bivariate distribution for some latent injection $\\pi:[m] \\to [n]$. Originally introduced by DeGroot, Feder, and Goel (1971) to model matching recor"},"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":"2503.14619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-03-18T18:15:13Z","cross_cats_sorted":["cs.IT","math.IT","stat.TH"],"title_canon_sha256":"33c1f7da1962837806c9d18e96e57e7873cf8bd3b307ef196a9c72644e749082","abstract_canon_sha256":"52d2f1e01e1daa904cedf16581b61e220f05a11a4236192f7f6c6b599e2d5fce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:21.485497Z","signature_b64":"6Z6lz1Vb3QDwHlR+S1b03dc1gWxEcGzGy+JJ1IrhESmOZ1ZcCpRpf1MzDQGww6PmYzf7cUoS//2jZptetJNECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a76826a48186ec7211c7f6089e23356f6431125b1c83a6a992d94d5908ec2dc","last_reissued_at":"2026-07-05T10:34:21.484987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:21.484987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The broken sample problem revisited: Proof of a conjecture by Bai-Hsing and high-dimensional extensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.TH"],"primary_cat":"math.ST","authors_text":"Jiaming Xu, Simiao Jiao, Yihong Wu","submitted_at":"2025-03-18T18:15:13Z","abstract_excerpt":"We revisit the classical broken sample problem: Two samples of i.i.d. data points $\\mathbf{X}=\\{X_1,\\cdots, X_n\\}$ and $\\mathbf{Y}=\\{Y_1,\\cdots,Y_m\\}$ are observed without correspondence with $m\\leq n$. Under the null hypothesis, $\\mathbf{X}$ and $\\mathbf{Y}$ are independent. Under the alternative hypothesis, $\\mathbf{Y}$ is correlated with a random subsample of $\\mathbf{X}$, in the sense that $(X_{\\pi(i)},Y_i)$'s are drawn independently from some bivariate distribution for some latent injection $\\pi:[m] \\to [n]$. Originally introduced by DeGroot, Feder, and Goel (1971) to model matching recor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14619","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/2503.14619/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":"2503.14619","created_at":"2026-07-05T10:34:21.485049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14619v1","created_at":"2026-07-05T10:34:21.485049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14619","created_at":"2026-07-05T10:34:21.485049+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJ3IE2SIDBXM","created_at":"2026-07-05T10:34:21.485049+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJ3IE2SIDBXMOII4","created_at":"2026-07-05T10:34:21.485049+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJ3IE2SI","created_at":"2026-07-05T10:34:21.485049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16279","citing_title":"Sharp Detection Threshold for Correlation among Multiple Unlabeled Gaussian Networks","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJ3IE2SIDBXMOII4P5QITYRTK3","json":"https://pith.science/pith/JJ3IE2SIDBXMOII4P5QITYRTK3.json","graph_json":"https://pith.science/api/pith-number/JJ3IE2SIDBXMOII4P5QITYRTK3/graph.json","events_json":"https://pith.science/api/pith-number/JJ3IE2SIDBXMOII4P5QITYRTK3/events.json","paper":"https://pith.science/paper/JJ3IE2SI"},"agent_actions":{"view_html":"https://pith.science/pith/JJ3IE2SIDBXMOII4P5QITYRTK3","download_json":"https://pith.science/pith/JJ3IE2SIDBXMOII4P5QITYRTK3.json","view_paper":"https://pith.science/paper/JJ3IE2SI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14619&json=true","fetch_graph":"https://pith.science/api/pith-number/JJ3IE2SIDBXMOII4P5QITYRTK3/graph.json","fetch_events":"https://pith.science/api/pith-number/JJ3IE2SIDBXMOII4P5QITYRTK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJ3IE2SIDBXMOII4P5QITYRTK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJ3IE2SIDBXMOII4P5QITYRTK3/action/storage_attestation","attest_author":"https://pith.science/pith/JJ3IE2SIDBXMOII4P5QITYRTK3/action/author_attestation","sign_citation":"https://pith.science/pith/JJ3IE2SIDBXMOII4P5QITYRTK3/action/citation_signature","submit_replication":"https://pith.science/pith/JJ3IE2SIDBXMOII4P5QITYRTK3/action/replication_record"}},"created_at":"2026-07-05T10:34:21.485049+00:00","updated_at":"2026-07-05T10:34:21.485049+00:00"}