{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:DOSRDFGFZA4SJUYIBN5VDRT6A6","short_pith_number":"pith:DOSRDFGF","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"},"canonical_sha256":"1ba51194c5c83924d3080b7b51c67e07ab7a2090cad2a7a72cbe9f5e5b5553b0","source":{"kind":"arxiv","id":"1602.02850","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.02850","created_at":"2026-05-18T00:58:57Z"},{"alias_kind":"arxiv_version","alias_value":"1602.02850v1","created_at":"2026-05-18T00:58:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02850","created_at":"2026-05-18T00:58:57Z"},{"alias_kind":"pith_short_12","alias_value":"DOSRDFGFZA4S","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DOSRDFGFZA4SJUYI","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DOSRDFGF","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:DOSRDFGFZA4SJUYIBN5VDRT6A6","target":"record","payload":{"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"},"canonical_sha256":"1ba51194c5c83924d3080b7b51c67e07ab7a2090cad2a7a72cbe9f5e5b5553b0","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"},"source_kind":"arxiv","source_id":"1602.02850","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:58:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pbDa9133rQ6T2gucSdX/cbD9CkwNNGgkXECzA7+UZjthTQQhev4LxD1hAD4D3GiZgMWc4Lx2XBXHnKHfoObGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:26:34.713481Z"},"content_sha256":"fac787b61dbf19ee3ed4be88efafa4df3372bfd0c9e6906fe000fc891962edb7","schema_version":"1.0","event_id":"sha256:fac787b61dbf19ee3ed4be88efafa4df3372bfd0c9e6906fe000fc891962edb7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:DOSRDFGFZA4SJUYIBN5VDRT6A6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:58:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O3bqElZAMpgSlKB69reoxRaKLAdt+ZST833ZKB3A7g6Ff0YTnuoD128YrtgzwV95oEWvpwljPeJtbbgLqq4VAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:26:34.713835Z"},"content_sha256":"80e08da2e2bd48ea85f0acb3f9162005e62581c289f0fef0ac6a3512cdd639b0","schema_version":"1.0","event_id":"sha256:80e08da2e2bd48ea85f0acb3f9162005e62581c289f0fef0ac6a3512cdd639b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6/bundle.json","state_url":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T15:26:34Z","links":{"resolver":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6","bundle":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6/bundle.json","state":"https://pith.science/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DOSRDFGFZA4SJUYIBN5VDRT6A6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:DOSRDFGFZA4SJUYIBN5VDRT6A6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4868f3e93c7dc50f6783eca40b571342106a8e405ddb41bf7367a8e4d888d440","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-09T03:43:21Z","title_canon_sha256":"815c793bca42c5212dc59a220ca0fcc18b8e24662fe864dbb32d069365a8ead3"},"schema_version":"1.0","source":{"id":"1602.02850","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.02850","created_at":"2026-05-18T00:58:57Z"},{"alias_kind":"arxiv_version","alias_value":"1602.02850v1","created_at":"2026-05-18T00:58:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02850","created_at":"2026-05-18T00:58:57Z"},{"alias_kind":"pith_short_12","alias_value":"DOSRDFGFZA4S","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DOSRDFGFZA4SJUYI","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DOSRDFGF","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:80e08da2e2bd48ea85f0acb3f9162005e62581c289f0fef0ac6a3512cdd639b0","target":"graph","created_at":"2026-05-18T00:58:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Bo Tang, Haibo He, Steven Kay","cross_cats":["cs.CL","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-09T03:43:21Z","title":"Toward Optimal Feature Selection in Naive Bayes for Text Categorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02850","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fac787b61dbf19ee3ed4be88efafa4df3372bfd0c9e6906fe000fc891962edb7","target":"record","created_at":"2026-05-18T00:58:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4868f3e93c7dc50f6783eca40b571342106a8e405ddb41bf7367a8e4d888d440","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-09T03:43:21Z","title_canon_sha256":"815c793bca42c5212dc59a220ca0fcc18b8e24662fe864dbb32d069365a8ead3"},"schema_version":"1.0","source":{"id":"1602.02850","kind":"arxiv","version":1}},"canonical_sha256":"1ba51194c5c83924d3080b7b51c67e07ab7a2090cad2a7a72cbe9f5e5b5553b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ba51194c5c83924d3080b7b51c67e07ab7a2090cad2a7a72cbe9f5e5b5553b0","first_computed_at":"2026-05-18T00:58:57.229374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:58:57.229374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"owoNW7qnVbBnnjcTMxN9pbnSMvidG3JChATLuuMW7FQ72NxCfanbZu3T9vfzYCdASyrdnswtNz8c6AWibBJODA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:58:57.229929Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.02850","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fac787b61dbf19ee3ed4be88efafa4df3372bfd0c9e6906fe000fc891962edb7","sha256:80e08da2e2bd48ea85f0acb3f9162005e62581c289f0fef0ac6a3512cdd639b0"],"state_sha256":"344c659455c4a911f6f9dec7a8c0c0f66be42450ef42c7ab04a5b25f859d8592"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U4sc8MCYJ8RGdhZF+rB1NMADXrt4U9Rwe2LoVJf4AOONyBng4YtHrCFrvQsK8HmMSQk17hkjG0i1UPfGo/5ICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T15:26:34.715990Z","bundle_sha256":"e2237060da712130fded88f48d93409115dbeb8563f91e7815d850ae926463e0"}}