{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:DOSRDFGFZA4SJUYIBN5VDRT6A6","short_pith_number":"pith:DOSRDFGF","schema_version":"1.0","canonical_sha256":"1ba51194c5c83924d3080b7b51c67e07ab7a2090cad2a7a72cbe9f5e5b5553b0","source":{"kind":"arxiv","id":"1602.02850","version":1},"attestation_state":"computed","paper":{"title":"Toward Optimal Feature Selection in Naive Bayes for Text Categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Tang, Haibo He, Steven Kay","submitted_at":"2016-02-09T03:43:21Z","abstract_excerpt":"Automated feature selection is important for text categorization to reduce the feature size and to speed up the learning process of classifiers. In this paper, we present a novel and efficient feature selection framework based on the Information Theory, which aims to rank the features with their discriminative capacity for classification. We first revisit two information measures: Kullback-Leibler divergence and Jeffreys divergence for binary hypothesis testing, and analyze their asymptotic properties relating to type I and type II errors of a Bayesian classifier. We then introduce a new diver"},"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":"1602.02850","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-09T03:43:21Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"815c793bca42c5212dc59a220ca0fcc18b8e24662fe864dbb32d069365a8ead3","abstract_canon_sha256":"4868f3e93c7dc50f6783eca40b571342106a8e405ddb41bf7367a8e4d888d440"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:57.229929Z","signature_b64":"owoNW7qnVbBnnjcTMxN9pbnSMvidG3JChATLuuMW7FQ72NxCfanbZu3T9vfzYCdASyrdnswtNz8c6AWibBJODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ba51194c5c83924d3080b7b51c67e07ab7a2090cad2a7a72cbe9f5e5b5553b0","last_reissued_at":"2026-05-18T00:58:57.229374Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:57.229374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Optimal Feature Selection in Naive Bayes for Text Categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Tang, Haibo He, Steven Kay","submitted_at":"2016-02-09T03:43:21Z","abstract_excerpt":"Automated feature selection is important for text categorization to reduce the feature size and to speed up the learning process of classifiers. In this paper, we present a novel and efficient feature selection framework based on the Information Theory, which aims to rank the features with their discriminative capacity for classification. We first revisit two information measures: Kullback-Leibler divergence and Jeffreys divergence for binary hypothesis testing, and analyze their asymptotic properties relating to type I and type II errors of a Bayesian classifier. We then introduce a new diver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02850","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":"1602.02850","created_at":"2026-05-18T00:58:57.229466+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.02850v1","created_at":"2026-05-18T00:58:57.229466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02850","created_at":"2026-05-18T00:58:57.229466+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOSRDFGFZA4S","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOSRDFGFZA4SJUYI","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOSRDFGF","created_at":"2026-05-18T12:30:12.583610+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/DOSRDFGFZA4SJUYIBN5VDRT6A6","json":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6.json","graph_json":"https://pith.science/api/pith-number/DOSRDFGFZA4SJUYIBN5VDRT6A6/graph.json","events_json":"https://pith.science/api/pith-number/DOSRDFGFZA4SJUYIBN5VDRT6A6/events.json","paper":"https://pith.science/paper/DOSRDFGF"},"agent_actions":{"view_html":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6","download_json":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6.json","view_paper":"https://pith.science/paper/DOSRDFGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.02850&json=true","fetch_graph":"https://pith.science/api/pith-number/DOSRDFGFZA4SJUYIBN5VDRT6A6/graph.json","fetch_events":"https://pith.science/api/pith-number/DOSRDFGFZA4SJUYIBN5VDRT6A6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6/action/storage_attestation","attest_author":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6/action/author_attestation","sign_citation":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6/action/citation_signature","submit_replication":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6/action/replication_record"}},"created_at":"2026-05-18T00:58:57.229466+00:00","updated_at":"2026-05-18T00:58:57.229466+00:00"}