{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:A5EN7KRLJW23Q3M7HVOWHMDYF3","short_pith_number":"pith:A5EN7KRL","schema_version":"1.0","canonical_sha256":"0748dfaa2b4db5b86d9f3d5d63b0782edec515cc593355a432681c548edea7c4","source":{"kind":"arxiv","id":"1208.5755","version":3},"attestation_state":"computed","paper":{"title":"Graph-Based Tests for Two-Sample Comparisons of Categorical Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Hao Chen, Nancy R. Zhang","submitted_at":"2012-08-28T19:25:39Z","abstract_excerpt":"We study the problem of two-sample comparison with categorical data when the contingency table is sparsely populated. In modern applications, the number of categories is often comparable to the sample size, causing existing methods to have low power. When the number of categories is large, there is often underlying structure on the sample space that can be exploited. We propose a general non-parametric approach that utilizes similarity information on the space of all categories in two sample tests. Our approach extends the graph-based tests of Friedman and Rafsky (1979) and Rosenbaum (2005), w"},"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":"1208.5755","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2012-08-28T19:25:39Z","cross_cats_sorted":[],"title_canon_sha256":"44653a6c6c403f674c262cd8b3e9a330ca8502429c411b0d6bc4e9b07c40a44c","abstract_canon_sha256":"edaba2de99dc561fb584f7e0367c8243fb4c2509b55813bdedd9b1d85f5d36d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:21.733829Z","signature_b64":"eLlmywEYmfn/dSb3a1k/HaolfXW4M4QcUKVS4aLhUcVO5hvOe3tC9teVEnrPah0wYyft/JE5ltqFz2mo3owODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0748dfaa2b4db5b86d9f3d5d63b0782edec515cc593355a432681c548edea7c4","last_reissued_at":"2026-05-18T02:45:21.733387Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:21.733387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-Based Tests for Two-Sample Comparisons of Categorical Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Hao Chen, Nancy R. Zhang","submitted_at":"2012-08-28T19:25:39Z","abstract_excerpt":"We study the problem of two-sample comparison with categorical data when the contingency table is sparsely populated. In modern applications, the number of categories is often comparable to the sample size, causing existing methods to have low power. When the number of categories is large, there is often underlying structure on the sample space that can be exploited. We propose a general non-parametric approach that utilizes similarity information on the space of all categories in two sample tests. Our approach extends the graph-based tests of Friedman and Rafsky (1979) and Rosenbaum (2005), w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.5755","kind":"arxiv","version":3},"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":"1208.5755","created_at":"2026-05-18T02:45:21.733441+00:00"},{"alias_kind":"arxiv_version","alias_value":"1208.5755v3","created_at":"2026-05-18T02:45:21.733441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.5755","created_at":"2026-05-18T02:45:21.733441+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5EN7KRLJW23","created_at":"2026-05-18T12:26:58.693483+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5EN7KRLJW23Q3M7","created_at":"2026-05-18T12:26:58.693483+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5EN7KRL","created_at":"2026-05-18T12:26:58.693483+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/A5EN7KRLJW23Q3M7HVOWHMDYF3","json":"https://pith.science/pith/A5EN7KRLJW23Q3M7HVOWHMDYF3.json","graph_json":"https://pith.science/api/pith-number/A5EN7KRLJW23Q3M7HVOWHMDYF3/graph.json","events_json":"https://pith.science/api/pith-number/A5EN7KRLJW23Q3M7HVOWHMDYF3/events.json","paper":"https://pith.science/paper/A5EN7KRL"},"agent_actions":{"view_html":"https://pith.science/pith/A5EN7KRLJW23Q3M7HVOWHMDYF3","download_json":"https://pith.science/pith/A5EN7KRLJW23Q3M7HVOWHMDYF3.json","view_paper":"https://pith.science/paper/A5EN7KRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1208.5755&json=true","fetch_graph":"https://pith.science/api/pith-number/A5EN7KRLJW23Q3M7HVOWHMDYF3/graph.json","fetch_events":"https://pith.science/api/pith-number/A5EN7KRLJW23Q3M7HVOWHMDYF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5EN7KRLJW23Q3M7HVOWHMDYF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5EN7KRLJW23Q3M7HVOWHMDYF3/action/storage_attestation","attest_author":"https://pith.science/pith/A5EN7KRLJW23Q3M7HVOWHMDYF3/action/author_attestation","sign_citation":"https://pith.science/pith/A5EN7KRLJW23Q3M7HVOWHMDYF3/action/citation_signature","submit_replication":"https://pith.science/pith/A5EN7KRLJW23Q3M7HVOWHMDYF3/action/replication_record"}},"created_at":"2026-05-18T02:45:21.733441+00:00","updated_at":"2026-05-18T02:45:21.733441+00:00"}