{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ITO7YU2I4B7JBY4A4QA2URUCMN","short_pith_number":"pith:ITO7YU2I","schema_version":"1.0","canonical_sha256":"44ddfc5348e07e90e380e401aa4682636770353c3936a7bfc404361b620e69d0","source":{"kind":"arxiv","id":"2306.07111","version":1},"attestation_state":"computed","paper":{"title":"Linear Classifier: An Often-Forgotten Baseline for Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chih-Jen Lin, Jie-Jyun Liu, Si-An Chen, Yu-Chen Lin","submitted_at":"2023-06-12T13:39:54Z","abstract_excerpt":"Large-scale pre-trained language models such as BERT are popular solutions for text classification. Due to the superior performance of these advanced methods, nowadays, people often directly train them for a few epochs and deploy the obtained model. In this opinion paper, we point out that this way may only sometimes get satisfactory results. We argue the importance of running a simple baseline like linear classifiers on bag-of-words features along with advanced methods. First, for many text data, linear methods show competitive performance, high efficiency, and robustness. Second, advanced mo"},"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":"2306.07111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T13:39:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"03ec758826ccadf36e2f0d87a4b0f2f8f5ebdc136a20cfa5eaeb55534892aad2","abstract_canon_sha256":"3ae4fdab05b02b0ada72dd4acb9a89fef1b08f23c124695d4004ca5fd0b94ec6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:47.798732Z","signature_b64":"y6fh8LRp7AU2QCuCrYHmAVIX8qii3ZCJF2Buc2bEspJFvZUyAHkY7Ne6oOVPsCc8I0r12mjUH2yN4XJW+SHyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44ddfc5348e07e90e380e401aa4682636770353c3936a7bfc404361b620e69d0","last_reissued_at":"2026-07-05T06:19:47.798359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:47.798359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear Classifier: An Often-Forgotten Baseline for Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chih-Jen Lin, Jie-Jyun Liu, Si-An Chen, Yu-Chen Lin","submitted_at":"2023-06-12T13:39:54Z","abstract_excerpt":"Large-scale pre-trained language models such as BERT are popular solutions for text classification. Due to the superior performance of these advanced methods, nowadays, people often directly train them for a few epochs and deploy the obtained model. In this opinion paper, we point out that this way may only sometimes get satisfactory results. We argue the importance of running a simple baseline like linear classifiers on bag-of-words features along with advanced methods. First, for many text data, linear methods show competitive performance, high efficiency, and robustness. Second, advanced mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07111","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.07111/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2306.07111","created_at":"2026-07-05T06:19:47.798417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07111v1","created_at":"2026-07-05T06:19:47.798417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07111","created_at":"2026-07-05T06:19:47.798417+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITO7YU2I4B7J","created_at":"2026-07-05T06:19:47.798417+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITO7YU2I4B7JBY4A","created_at":"2026-07-05T06:19:47.798417+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITO7YU2I","created_at":"2026-07-05T06:19:47.798417+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/ITO7YU2I4B7JBY4A4QA2URUCMN","json":"https://pith.science/pith/ITO7YU2I4B7JBY4A4QA2URUCMN.json","graph_json":"https://pith.science/api/pith-number/ITO7YU2I4B7JBY4A4QA2URUCMN/graph.json","events_json":"https://pith.science/api/pith-number/ITO7YU2I4B7JBY4A4QA2URUCMN/events.json","paper":"https://pith.science/paper/ITO7YU2I"},"agent_actions":{"view_html":"https://pith.science/pith/ITO7YU2I4B7JBY4A4QA2URUCMN","download_json":"https://pith.science/pith/ITO7YU2I4B7JBY4A4QA2URUCMN.json","view_paper":"https://pith.science/paper/ITO7YU2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07111&json=true","fetch_graph":"https://pith.science/api/pith-number/ITO7YU2I4B7JBY4A4QA2URUCMN/graph.json","fetch_events":"https://pith.science/api/pith-number/ITO7YU2I4B7JBY4A4QA2URUCMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITO7YU2I4B7JBY4A4QA2URUCMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITO7YU2I4B7JBY4A4QA2URUCMN/action/storage_attestation","attest_author":"https://pith.science/pith/ITO7YU2I4B7JBY4A4QA2URUCMN/action/author_attestation","sign_citation":"https://pith.science/pith/ITO7YU2I4B7JBY4A4QA2URUCMN/action/citation_signature","submit_replication":"https://pith.science/pith/ITO7YU2I4B7JBY4A4QA2URUCMN/action/replication_record"}},"created_at":"2026-07-05T06:19:47.798417+00:00","updated_at":"2026-07-05T06:19:47.798417+00:00"}