{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PGUZPTQCDFDBFSFHQ66AU2O2ZE","short_pith_number":"pith:PGUZPTQC","schema_version":"1.0","canonical_sha256":"79a997ce02194612c8a787bc0a69dac9151a7dbc20b983a7c236f8ed1851a674","source":{"kind":"arxiv","id":"2008.00364","version":6},"attestation_state":"computed","paper":{"title":"A Survey on Text Classification: From Shallow to Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Congying Xia, Hao Peng, Jianxin Li, Lichao Sun, Lifang He, Philip S. Yu, Qian Li, Renyu Yang","submitted_at":"2020-08-02T00:09:03Z","abstract_excerpt":"Text classification is the most fundamental and essential task in natural language processing. The last decade has seen a surge of research in this area due to the unprecedented success of deep learning. Numerous methods, datasets, and evaluation metrics have been proposed in the literature, raising the need for a comprehensive and updated survey. This paper fills the gap by reviewing the state-of-the-art approaches from 1961 to 2021, focusing on models from traditional models to deep learning. We create a taxonomy for text classification according to the text involved and the models used for "},"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":"2008.00364","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-02T00:09:03Z","cross_cats_sorted":[],"title_canon_sha256":"f0f951f3e8bec9e0b22ac26bdbe7f8df9eb0f4da55d1218117a0b85d77698f80","abstract_canon_sha256":"0c70f782fbd7de1f63c0fc6a622cf3d4ef0c0d162566d4aa16f346f0be1efac6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:00.107551Z","signature_b64":"7721tryGcvS6axdbk5KBAQTk1a4q3dHGkr+kHqWcgfdZ8+nvH5K1s4oHiV5+34050ttT2xM8fqeJwKUVgaxhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79a997ce02194612c8a787bc0a69dac9151a7dbc20b983a7c236f8ed1851a674","last_reissued_at":"2026-07-05T03:43:00.107010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:00.107010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Text Classification: From Shallow to Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Congying Xia, Hao Peng, Jianxin Li, Lichao Sun, Lifang He, Philip S. Yu, Qian Li, Renyu Yang","submitted_at":"2020-08-02T00:09:03Z","abstract_excerpt":"Text classification is the most fundamental and essential task in natural language processing. The last decade has seen a surge of research in this area due to the unprecedented success of deep learning. Numerous methods, datasets, and evaluation metrics have been proposed in the literature, raising the need for a comprehensive and updated survey. This paper fills the gap by reviewing the state-of-the-art approaches from 1961 to 2021, focusing on models from traditional models to deep learning. We create a taxonomy for text classification according to the text involved and the models used for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.00364","kind":"arxiv","version":6},"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/2008.00364/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":"2008.00364","created_at":"2026-07-05T03:43:00.107069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.00364v6","created_at":"2026-07-05T03:43:00.107069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.00364","created_at":"2026-07-05T03:43:00.107069+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGUZPTQCDFDB","created_at":"2026-07-05T03:43:00.107069+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGUZPTQCDFDBFSFH","created_at":"2026-07-05T03:43:00.107069+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGUZPTQC","created_at":"2026-07-05T03:43:00.107069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.02138","citing_title":"Topic-Based Watermarks for Large Language Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PGUZPTQCDFDBFSFHQ66AU2O2ZE","json":"https://pith.science/pith/PGUZPTQCDFDBFSFHQ66AU2O2ZE.json","graph_json":"https://pith.science/api/pith-number/PGUZPTQCDFDBFSFHQ66AU2O2ZE/graph.json","events_json":"https://pith.science/api/pith-number/PGUZPTQCDFDBFSFHQ66AU2O2ZE/events.json","paper":"https://pith.science/paper/PGUZPTQC"},"agent_actions":{"view_html":"https://pith.science/pith/PGUZPTQCDFDBFSFHQ66AU2O2ZE","download_json":"https://pith.science/pith/PGUZPTQCDFDBFSFHQ66AU2O2ZE.json","view_paper":"https://pith.science/paper/PGUZPTQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.00364&json=true","fetch_graph":"https://pith.science/api/pith-number/PGUZPTQCDFDBFSFHQ66AU2O2ZE/graph.json","fetch_events":"https://pith.science/api/pith-number/PGUZPTQCDFDBFSFHQ66AU2O2ZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGUZPTQCDFDBFSFHQ66AU2O2ZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGUZPTQCDFDBFSFHQ66AU2O2ZE/action/storage_attestation","attest_author":"https://pith.science/pith/PGUZPTQCDFDBFSFHQ66AU2O2ZE/action/author_attestation","sign_citation":"https://pith.science/pith/PGUZPTQCDFDBFSFHQ66AU2O2ZE/action/citation_signature","submit_replication":"https://pith.science/pith/PGUZPTQCDFDBFSFHQ66AU2O2ZE/action/replication_record"}},"created_at":"2026-07-05T03:43:00.107069+00:00","updated_at":"2026-07-05T03:43:00.107069+00:00"}