{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:NTMSMZJVWQPPWVY6X7VHVCMXO7","short_pith_number":"pith:NTMSMZJV","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"},"canonical_sha256":"6cd9266535b41efb571ebfea7a899777feaf411f772aa612b30d6db2d43f635a","source":{"kind":"arxiv","id":"1305.0638","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1305.0638","created_at":"2026-05-18T03:26:33Z"},{"alias_kind":"arxiv_version","alias_value":"1305.0638v1","created_at":"2026-05-18T03:26:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.0638","created_at":"2026-05-18T03:26:33Z"},{"alias_kind":"pith_short_12","alias_value":"NTMSMZJVWQPP","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"NTMSMZJVWQPPWVY6","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"NTMSMZJV","created_at":"2026-05-18T12:27:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:NTMSMZJVWQPPWVY6X7VHVCMXO7","target":"record","payload":{"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"},"canonical_sha256":"6cd9266535b41efb571ebfea7a899777feaf411f772aa612b30d6db2d43f635a","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"},"source_kind":"arxiv","source_id":"1305.0638","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":"2026-05-18T03:26:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LPjRJD6IqhLJmbYZxHFAXAxG+vgKM7jIkXhwo7XbYipdTSmg/UGy2E1apP7nojru0Xh2eq5AzV12MbAwq1f9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:33:34.157291Z"},"content_sha256":"2cbd68438ae76c7205203b16da4fe199473dbd625f1a1dd0e7fcc9de93186f37","schema_version":"1.0","event_id":"sha256:2cbd68438ae76c7205203b16da4fe199473dbd625f1a1dd0e7fcc9de93186f37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:NTMSMZJVWQPPWVY6X7VHVCMXO7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:26:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YbYRtJlN+m96geb9HdNXldi9z+RjUsH+kC0063KT39oj1MixxKKzPTMO/kEE/a/nS5zDwQ5GFansAGLF/5NCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:33:34.157953Z"},"content_sha256":"a34600619565486527140053cab6038f82a49ecd8909031738a09bdc3d8e511f","schema_version":"1.0","event_id":"sha256:a34600619565486527140053cab6038f82a49ecd8909031738a09bdc3d8e511f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7/bundle.json","state_url":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7/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":"2026-05-31T14:33:34Z","links":{"resolver":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7","bundle":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7/bundle.json","state":"https://pith.science/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NTMSMZJVWQPPWVY6X7VHVCMXO7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:NTMSMZJVWQPPWVY6X7VHVCMXO7","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":"557041a20da19b58bb6c4fd963fb5dc9a9c09611da0fb084da01cf7fc25f398c","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.LG","submitted_at":"2013-05-03T08:26:05Z","title_canon_sha256":"b77c7a2ec29d2a8b8c50228ba9ed9a8142b122a9b9992eaf666d325c429eb16e"},"schema_version":"1.0","source":{"id":"1305.0638","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1305.0638","created_at":"2026-05-18T03:26:33Z"},{"alias_kind":"arxiv_version","alias_value":"1305.0638v1","created_at":"2026-05-18T03:26:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.0638","created_at":"2026-05-18T03:26:33Z"},{"alias_kind":"pith_short_12","alias_value":"NTMSMZJVWQPP","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"NTMSMZJVWQPPWVY6","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"NTMSMZJV","created_at":"2026-05-18T12:27:52Z"}],"graph_snapshots":[{"event_id":"sha256:a34600619565486527140053cab6038f82a49ecd8909031738a09bdc3d8e511f","target":"graph","created_at":"2026-05-18T03:26:33Z","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":"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","authors_text":"Deqing Wang, Hui Zhang, Rui Liu, Weifeng Lv","cross_cats":["cs.IR","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.LG","submitted_at":"2013-05-03T08:26:05Z","title":"Feature Selection Based on Term Frequency and T-Test for Text Categorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.0638","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":"sha256:2cbd68438ae76c7205203b16da4fe199473dbd625f1a1dd0e7fcc9de93186f37","target":"record","created_at":"2026-05-18T03:26:33Z","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":"557041a20da19b58bb6c4fd963fb5dc9a9c09611da0fb084da01cf7fc25f398c","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.LG","submitted_at":"2013-05-03T08:26:05Z","title_canon_sha256":"b77c7a2ec29d2a8b8c50228ba9ed9a8142b122a9b9992eaf666d325c429eb16e"},"schema_version":"1.0","source":{"id":"1305.0638","kind":"arxiv","version":1}},"canonical_sha256":"6cd9266535b41efb571ebfea7a899777feaf411f772aa612b30d6db2d43f635a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cd9266535b41efb571ebfea7a899777feaf411f772aa612b30d6db2d43f635a","first_computed_at":"2026-05-18T03:26:33.147071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:26:33.147071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CWddQWXn3PbTYLMRjyp4No0IYpgndWpzYrO4nTTHW7vNGsIjC3F56SOvmhktlyhP1x+DwXLgZ1GXEabjYGclAg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:26:33.147447Z","signed_message":"canonical_sha256_bytes"},"source_id":"1305.0638","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cbd68438ae76c7205203b16da4fe199473dbd625f1a1dd0e7fcc9de93186f37","sha256:a34600619565486527140053cab6038f82a49ecd8909031738a09bdc3d8e511f"],"state_sha256":"d5d608abcec70b505188dd1fe64f4638d23bb641c872141c8249fb3d7d3ba52e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J6dCGcGLtqHUehAOuM58CLLU4oAoqqRiK3cR9Cjz42hj/TA5dw8ZE8/nRf9pNgXSU5we3BEy5ER94FU9+N7OAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T14:33:34.161682Z","bundle_sha256":"d09a80678bde1a5d952e21d80d2f78b01064fa9c797ec5e7966051752342fd09"}}