{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GT36XKKJIGG473A2LHPUGV5E6X","short_pith_number":"pith:GT36XKKJ","schema_version":"1.0","canonical_sha256":"34f7eba949418dcfec1a59df4357a4f5db81508f10fc29b33ec4ca1048f9c415","source":{"kind":"arxiv","id":"2408.09629","version":1},"attestation_state":"computed","paper":{"title":"A Strategy to Combine 1stGen Transformers and Open LLMs for Automatic Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adriana Silvina Pagano, Claudio M. V. de Andrade, Davi Reis, Leonardo Rocha, Marcos Andr\\'e Gon\\c{c}alves, Washington Cunha","submitted_at":"2024-08-19T01:22:21Z","abstract_excerpt":"Transformer models have achieved state-of-the-art results, with Large Language Models (LLMs), an evolution of first-generation transformers (1stTR), being considered the cutting edge in several NLP tasks. However, the literature has yet to conclusively demonstrate that LLMs consistently outperform 1stTRs across all NLP tasks. This study compares three 1stTRs (BERT, RoBERTa, and BART) with two open LLMs (Llama 2 and Bloom) across 11 sentiment analysis datasets. The results indicate that open LLMs may moderately outperform or match 1stTRs in 8 out of 11 datasets but only when fine-tuned. Given t"},"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":"2408.09629","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T01:22:21Z","cross_cats_sorted":[],"title_canon_sha256":"5ac6a4094b3c605d59fd97759593b8c63490b73a9579de19cc46ff52e87afaea","abstract_canon_sha256":"1e9b9aed8c460fc470a90b282183a21be33080287d0833fef645acaaee5499b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:34.866229Z","signature_b64":"TL3/eP+sCOqzECN5Gm7KkDWjfnPAPVORN07XU1Xysf9/cEgQ2orrjSzHhMy8XELvX7+GrWVwO6364TkTTTLBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34f7eba949418dcfec1a59df4357a4f5db81508f10fc29b33ec4ca1048f9c415","last_reissued_at":"2026-07-05T08:56:34.865762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:34.865762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Strategy to Combine 1stGen Transformers and Open LLMs for Automatic Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adriana Silvina Pagano, Claudio M. V. de Andrade, Davi Reis, Leonardo Rocha, Marcos Andr\\'e Gon\\c{c}alves, Washington Cunha","submitted_at":"2024-08-19T01:22:21Z","abstract_excerpt":"Transformer models have achieved state-of-the-art results, with Large Language Models (LLMs), an evolution of first-generation transformers (1stTR), being considered the cutting edge in several NLP tasks. However, the literature has yet to conclusively demonstrate that LLMs consistently outperform 1stTRs across all NLP tasks. This study compares three 1stTRs (BERT, RoBERTa, and BART) with two open LLMs (Llama 2 and Bloom) across 11 sentiment analysis datasets. The results indicate that open LLMs may moderately outperform or match 1stTRs in 8 out of 11 datasets but only when fine-tuned. Given t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09629","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/2408.09629/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":"2408.09629","created_at":"2026-07-05T08:56:34.865827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09629v1","created_at":"2026-07-05T08:56:34.865827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09629","created_at":"2026-07-05T08:56:34.865827+00:00"},{"alias_kind":"pith_short_12","alias_value":"GT36XKKJIGG4","created_at":"2026-07-05T08:56:34.865827+00:00"},{"alias_kind":"pith_short_16","alias_value":"GT36XKKJIGG473A2","created_at":"2026-07-05T08:56:34.865827+00:00"},{"alias_kind":"pith_short_8","alias_value":"GT36XKKJ","created_at":"2026-07-05T08:56:34.865827+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/GT36XKKJIGG473A2LHPUGV5E6X","json":"https://pith.science/pith/GT36XKKJIGG473A2LHPUGV5E6X.json","graph_json":"https://pith.science/api/pith-number/GT36XKKJIGG473A2LHPUGV5E6X/graph.json","events_json":"https://pith.science/api/pith-number/GT36XKKJIGG473A2LHPUGV5E6X/events.json","paper":"https://pith.science/paper/GT36XKKJ"},"agent_actions":{"view_html":"https://pith.science/pith/GT36XKKJIGG473A2LHPUGV5E6X","download_json":"https://pith.science/pith/GT36XKKJIGG473A2LHPUGV5E6X.json","view_paper":"https://pith.science/paper/GT36XKKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09629&json=true","fetch_graph":"https://pith.science/api/pith-number/GT36XKKJIGG473A2LHPUGV5E6X/graph.json","fetch_events":"https://pith.science/api/pith-number/GT36XKKJIGG473A2LHPUGV5E6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GT36XKKJIGG473A2LHPUGV5E6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GT36XKKJIGG473A2LHPUGV5E6X/action/storage_attestation","attest_author":"https://pith.science/pith/GT36XKKJIGG473A2LHPUGV5E6X/action/author_attestation","sign_citation":"https://pith.science/pith/GT36XKKJIGG473A2LHPUGV5E6X/action/citation_signature","submit_replication":"https://pith.science/pith/GT36XKKJIGG473A2LHPUGV5E6X/action/replication_record"}},"created_at":"2026-07-05T08:56:34.865827+00:00","updated_at":"2026-07-05T08:56:34.865827+00:00"}