{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:75KFZUZRTBPR7W6O5BI65ZQ4A4","short_pith_number":"pith:75KFZUZR","schema_version":"1.0","canonical_sha256":"ff545cd331985f1fdbcee851eee61c071ef3cfd83b27adb15d82fc5d618fab3a","source":{"kind":"arxiv","id":"2204.03954","version":6},"attestation_state":"computed","paper":{"title":"Are We Really Making Much Progress in Text Classification? A Comparative Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andor Diera, Ansgar Scherp, Bao Xin Lin, Bhakti Khera, Fabian Karl, Lukas Galke, Tim Meuser, Tushar Singhal","submitted_at":"2022-04-08T09:28:20Z","abstract_excerpt":"We analyze various methods for single-label and multi-label text classification across well-known datasets, categorizing them into bag-of-words, sequence-based, graph-based, and hierarchical approaches. Despite the surge in methods like graph-based models, encoder-only pre-trained language models, notably BERT, remain state-of-the-art. However, recent findings suggest simpler models like logistic regression and trigram-based SVMs outperform newer techniques. While decoder-only generative language models show promise in learning with limited data, they lag behind encoder-only models in performa"},"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":"2204.03954","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T09:28:20Z","cross_cats_sorted":[],"title_canon_sha256":"dd5c7bb8dbb82ee4bfd2bca7872d6beecd9ce7d78de6f2e09457206e6627dd8b","abstract_canon_sha256":"16383b3b999d2a49e9ca65c7485b9d8d1d155c69b7424ba0bfbf1ebdcbb76ecf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:39.205191Z","signature_b64":"rDpUGXVfnziHqgBwlb0V6+OYgFqElX3dC1GC1mXntK7Utk5quy4EloHOD+KWuqbfQ2N8FSO/FiipJnyAHqM8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff545cd331985f1fdbcee851eee61c071ef3cfd83b27adb15d82fc5d618fab3a","last_reissued_at":"2026-07-05T10:02:39.204753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:39.204753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are We Really Making Much Progress in Text Classification? A Comparative Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andor Diera, Ansgar Scherp, Bao Xin Lin, Bhakti Khera, Fabian Karl, Lukas Galke, Tim Meuser, Tushar Singhal","submitted_at":"2022-04-08T09:28:20Z","abstract_excerpt":"We analyze various methods for single-label and multi-label text classification across well-known datasets, categorizing them into bag-of-words, sequence-based, graph-based, and hierarchical approaches. Despite the surge in methods like graph-based models, encoder-only pre-trained language models, notably BERT, remain state-of-the-art. However, recent findings suggest simpler models like logistic regression and trigram-based SVMs outperform newer techniques. While decoder-only generative language models show promise in learning with limited data, they lag behind encoder-only models in performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03954","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/2204.03954/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":"2204.03954","created_at":"2026-07-05T10:02:39.204817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03954v6","created_at":"2026-07-05T10:02:39.204817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03954","created_at":"2026-07-05T10:02:39.204817+00:00"},{"alias_kind":"pith_short_12","alias_value":"75KFZUZRTBPR","created_at":"2026-07-05T10:02:39.204817+00:00"},{"alias_kind":"pith_short_16","alias_value":"75KFZUZRTBPR7W6O","created_at":"2026-07-05T10:02:39.204817+00:00"},{"alias_kind":"pith_short_8","alias_value":"75KFZUZR","created_at":"2026-07-05T10:02:39.204817+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26489","citing_title":"Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09722","citing_title":"ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4","json":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4.json","graph_json":"https://pith.science/api/pith-number/75KFZUZRTBPR7W6O5BI65ZQ4A4/graph.json","events_json":"https://pith.science/api/pith-number/75KFZUZRTBPR7W6O5BI65ZQ4A4/events.json","paper":"https://pith.science/paper/75KFZUZR"},"agent_actions":{"view_html":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4","download_json":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4.json","view_paper":"https://pith.science/paper/75KFZUZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03954&json=true","fetch_graph":"https://pith.science/api/pith-number/75KFZUZRTBPR7W6O5BI65ZQ4A4/graph.json","fetch_events":"https://pith.science/api/pith-number/75KFZUZRTBPR7W6O5BI65ZQ4A4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4/action/storage_attestation","attest_author":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4/action/author_attestation","sign_citation":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4/action/citation_signature","submit_replication":"https://pith.science/pith/75KFZUZRTBPR7W6O5BI65ZQ4A4/action/replication_record"}},"created_at":"2026-07-05T10:02:39.204817+00:00","updated_at":"2026-07-05T10:02:39.204817+00:00"}