{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:35CGQBSOZX4DOXYXACWKF3HPBB","short_pith_number":"pith:35CGQBSO","schema_version":"1.0","canonical_sha256":"df4468064ecdf8375f1700aca2ecef0849f1dfaf6083f3ca364ffc4bdd1a6925","source":{"kind":"arxiv","id":"2504.19021","version":2},"attestation_state":"computed","paper":{"title":"Advancing Scientific Text Classification: Fine-Tuned Models with Dataset Expansion and Hard-Voting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"G\\'abor Kert\\'esz, Zhyar Rzgar K Rostam","submitted_at":"2025-04-26T21:06:49Z","abstract_excerpt":"Efficient text classification is essential for handling the increasing volume of academic publications. This study explores the use of pre-trained language models (PLMs), including BERT, SciBERT, BioBERT, and BlueBERT, fine-tuned on the Web of Science (WoS-46985) dataset for scientific text classification. To enhance performance, we augment the dataset by executing seven targeted queries in the WoS database, retrieving 1,000 articles per category aligned with WoS-46985's main classes. PLMs predict labels for this unlabeled data, and a hard-voting strategy combines predictions for improved accu"},"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":"2504.19021","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-26T21:06:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6e9fd092d7c5dd51ef407f61589918d134f41399d03e9b78b3145d5ca1c6596","abstract_canon_sha256":"47c741b366510d9cd24f3d22d28a934d34b441aa2421340033485ff6e3022d6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:09.943638Z","signature_b64":"PEiGQQ1QtgoO5g4CUa7gx+zDN6MdQWNnbKFK2nwTMbnDGh4N4DDMOINbUq2IuE9uEMlt5bV4KpaYVAK4VQYsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df4468064ecdf8375f1700aca2ecef0849f1dfaf6083f3ca364ffc4bdd1a6925","last_reissued_at":"2026-07-05T12:06:09.943052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:09.943052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Scientific Text Classification: Fine-Tuned Models with Dataset Expansion and Hard-Voting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"G\\'abor Kert\\'esz, Zhyar Rzgar K Rostam","submitted_at":"2025-04-26T21:06:49Z","abstract_excerpt":"Efficient text classification is essential for handling the increasing volume of academic publications. This study explores the use of pre-trained language models (PLMs), including BERT, SciBERT, BioBERT, and BlueBERT, fine-tuned on the Web of Science (WoS-46985) dataset for scientific text classification. To enhance performance, we augment the dataset by executing seven targeted queries in the WoS database, retrieving 1,000 articles per category aligned with WoS-46985's main classes. PLMs predict labels for this unlabeled data, and a hard-voting strategy combines predictions for improved accu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19021","kind":"arxiv","version":2},"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/2504.19021/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":"2504.19021","created_at":"2026-07-05T12:06:09.943112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.19021v2","created_at":"2026-07-05T12:06:09.943112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19021","created_at":"2026-07-05T12:06:09.943112+00:00"},{"alias_kind":"pith_short_12","alias_value":"35CGQBSOZX4D","created_at":"2026-07-05T12:06:09.943112+00:00"},{"alias_kind":"pith_short_16","alias_value":"35CGQBSOZX4DOXYX","created_at":"2026-07-05T12:06:09.943112+00:00"},{"alias_kind":"pith_short_8","alias_value":"35CGQBSO","created_at":"2026-07-05T12:06:09.943112+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/35CGQBSOZX4DOXYXACWKF3HPBB","json":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB.json","graph_json":"https://pith.science/api/pith-number/35CGQBSOZX4DOXYXACWKF3HPBB/graph.json","events_json":"https://pith.science/api/pith-number/35CGQBSOZX4DOXYXACWKF3HPBB/events.json","paper":"https://pith.science/paper/35CGQBSO"},"agent_actions":{"view_html":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB","download_json":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB.json","view_paper":"https://pith.science/paper/35CGQBSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.19021&json=true","fetch_graph":"https://pith.science/api/pith-number/35CGQBSOZX4DOXYXACWKF3HPBB/graph.json","fetch_events":"https://pith.science/api/pith-number/35CGQBSOZX4DOXYXACWKF3HPBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB/action/storage_attestation","attest_author":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB/action/author_attestation","sign_citation":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB/action/citation_signature","submit_replication":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB/action/replication_record"}},"created_at":"2026-07-05T12:06:09.943112+00:00","updated_at":"2026-07-05T12:06:09.943112+00:00"}