{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IMQ376G5T5HR3GERD3XNHGCPU2","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":"d04c4241441e5626c22cc1e5e9a1bede6f389b5fdbeadc045f54713781f0dbee","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-08T03:24:53Z","title_canon_sha256":"9add44f4691eb2781444beffd7af66c1256835e7f7b07de7023f719fcb7b41c2"},"schema_version":"1.0","source":{"id":"1907.04905","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.04905","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"arxiv_version","alias_value":"1907.04905v1","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04905","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"pith_short_12","alias_value":"IMQ376G5T5HR","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IMQ376G5T5HR3GER","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IMQ376G5","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:323a5228f8ffdc4e6e2113f4956e10aa237e00f05705da93975963f6bc764c2c","target":"graph","created_at":"2026-05-17T23:40:54Z","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":"Automatic email categorization is an important application of text classification. We study the automatic reply of email business messages in Brazilian Portuguese. We present a novel corpus containing messages from a real application, and baseline categorization experiments using Naive Bayes and support Vector Machines. We then discuss the effect of lemmatization and the role of part-of-speech tagging filtering on precision and recall. Support Vector Machines classification coupled with nonlemmatized selection of verbs, nouns and adjectives was the best approach, with 87.3% maximum accuracy. S","authors_text":"Arthur Gola de Paula, Rogerio Bonatti","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-08T03:24:53Z","title":"Development of email classifier in Brazilian Portuguese using feature selection for automatic response"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04905","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":"sha256:2166dc9b34b1d9bece531e08361d6606ed7bd46d1812780b10b30ba6310228eb","target":"record","created_at":"2026-05-17T23:40:54Z","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":"d04c4241441e5626c22cc1e5e9a1bede6f389b5fdbeadc045f54713781f0dbee","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-08T03:24:53Z","title_canon_sha256":"9add44f4691eb2781444beffd7af66c1256835e7f7b07de7023f719fcb7b41c2"},"schema_version":"1.0","source":{"id":"1907.04905","kind":"arxiv","version":1}},"canonical_sha256":"4321bff8dd9f4f1d98911eeed3984fa69f9ca620d48c86660104c1b9591dfa20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4321bff8dd9f4f1d98911eeed3984fa69f9ca620d48c86660104c1b9591dfa20","first_computed_at":"2026-05-17T23:40:54.586803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:54.586803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0EOvkeGF0KF7F1dBj+oEbKaSl9ahOODKBNxztHd2OiNtIGDnhLzdfUbGcg7FESKui8ou/+dtaYCjlH62js8sCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:54.587535Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.04905","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2166dc9b34b1d9bece531e08361d6606ed7bd46d1812780b10b30ba6310228eb","sha256:323a5228f8ffdc4e6e2113f4956e10aa237e00f05705da93975963f6bc764c2c"],"state_sha256":"8fce52dcea1fd004fd0fe724467bea6bb3cf8d2dbef1cfeea515157c7a8a56ce"}