{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:NTMSMZJVWQPPWVY6X7VHVCMXO7","short_pith_number":"pith:NTMSMZJV","schema_version":"1.0","canonical_sha256":"6cd9266535b41efb571ebfea7a899777feaf411f772aa612b30d6db2d43f635a","source":{"kind":"arxiv","id":"1305.0638","version":1},"attestation_state":"computed","paper":{"title":"Feature Selection Based on Term Frequency and T-Test for Text Categorization","license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Deqing Wang, Hui Zhang, Rui Liu, Weifeng Lv","submitted_at":"2013-05-03T08:26:05Z","abstract_excerpt":"Much work has been done on feature selection. Existing methods are based on document frequency, such as Chi-Square Statistic, Information Gain etc. However, these methods have two shortcomings: one is that they are not reliable for low-frequency terms, and the other is that they only count whether one term occurs in a document and ignore the term frequency. Actually, high-frequency terms within a specific category are often regards as discriminators.\n  This paper focuses on how to construct the feature selection function based on term frequency, and proposes a new approach based on $t$-test, 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":"1305.0638","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.LG","submitted_at":"2013-05-03T08:26:05Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"b77c7a2ec29d2a8b8c50228ba9ed9a8142b122a9b9992eaf666d325c429eb16e","abstract_canon_sha256":"557041a20da19b58bb6c4fd963fb5dc9a9c09611da0fb084da01cf7fc25f398c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:26:33.147447Z","signature_b64":"CWddQWXn3PbTYLMRjyp4No0IYpgndWpzYrO4nTTHW7vNGsIjC3F56SOvmhktlyhP1x+DwXLgZ1GXEabjYGclAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cd9266535b41efb571ebfea7a899777feaf411f772aa612b30d6db2d43f635a","last_reissued_at":"2026-05-18T03:26:33.147071Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:26:33.147071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Selection Based on Term Frequency and T-Test for Text Categorization","license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Deqing Wang, Hui Zhang, Rui Liu, Weifeng Lv","submitted_at":"2013-05-03T08:26:05Z","abstract_excerpt":"Much work has been done on feature selection. Existing methods are based on document frequency, such as Chi-Square Statistic, Information Gain etc. However, these methods have two shortcomings: one is that they are not reliable for low-frequency terms, and the other is that they only count whether one term occurs in a document and ignore the term frequency. Actually, high-frequency terms within a specific category are often regards as discriminators.\n  This paper focuses on how to construct the feature selection function based on term frequency, and proposes a new approach based on $t$-test, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.0638","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":"1305.0638","created_at":"2026-05-18T03:26:33.147127+00:00"},{"alias_kind":"arxiv_version","alias_value":"1305.0638v1","created_at":"2026-05-18T03:26:33.147127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.0638","created_at":"2026-05-18T03:26:33.147127+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTMSMZJVWQPP","created_at":"2026-05-18T12:27:52.871228+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTMSMZJVWQPPWVY6","created_at":"2026-05-18T12:27:52.871228+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTMSMZJV","created_at":"2026-05-18T12:27:52.871228+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/NTMSMZJVWQPPWVY6X7VHVCMXO7","json":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7.json","graph_json":"https://pith.science/api/pith-number/NTMSMZJVWQPPWVY6X7VHVCMXO7/graph.json","events_json":"https://pith.science/api/pith-number/NTMSMZJVWQPPWVY6X7VHVCMXO7/events.json","paper":"https://pith.science/paper/NTMSMZJV"},"agent_actions":{"view_html":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7","download_json":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7.json","view_paper":"https://pith.science/paper/NTMSMZJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1305.0638&json=true","fetch_graph":"https://pith.science/api/pith-number/NTMSMZJVWQPPWVY6X7VHVCMXO7/graph.json","fetch_events":"https://pith.science/api/pith-number/NTMSMZJVWQPPWVY6X7VHVCMXO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7/action/storage_attestation","attest_author":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7/action/author_attestation","sign_citation":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7/action/citation_signature","submit_replication":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7/action/replication_record"}},"created_at":"2026-05-18T03:26:33.147127+00:00","updated_at":"2026-05-18T03:26:33.147127+00:00"}