{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6CGRBTQ3LBR4XPEFBVFEL3QYNR","short_pith_number":"pith:6CGRBTQ3","schema_version":"1.0","canonical_sha256":"f08d10ce1b5863cbbc850d4a45ee186c701c9a3d57fa43057a75c689c24a7718","source":{"kind":"arxiv","id":"2412.08587","version":2},"attestation_state":"computed","paper":{"title":"Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gang Yang, Hang Zhao, Qile P. Chen, Yijing Barry Zhang","submitted_at":"2024-12-11T18:06:44Z","abstract_excerpt":"Both encoder-only models (e.g., BERT, RoBERTa) and large language models (LLMs, e.g., Llama3) have been widely used for text classification tasks. However, there is a lack of systematic studies comparing the performance of encoder-based models and LLMs in text classification, particularly when fine-tuning is involved. This study employed a diverse range of models and methods, varying in size and architecture, and including both fine-tuned and pre-trained approaches. We first assessed the performances of these LLMs on the 20 Newsgroups (20NG) and MASSIVE datasets, comparing them to encoder-only"},"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":"2412.08587","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T18:06:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e70be4612274cd8d548565b005b75297b83d20181df8217d862c688e797d2e8c","abstract_canon_sha256":"5c9e833dd5e75bf3464915af6d879e8654ad19eb0a5b92687071b6cf20dacebb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:29.820759Z","signature_b64":"CxBQgB3nAfj9rWaMKrVn3gyxJhMlg56IATa6PLWkAGyLwSsf0yVbibIVV3JkzJeusNujKAh5GI/f1UDQgRfOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f08d10ce1b5863cbbc850d4a45ee186c701c9a3d57fa43057a75c689c24a7718","last_reissued_at":"2026-07-05T11:01:29.820222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:29.820222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gang Yang, Hang Zhao, Qile P. Chen, Yijing Barry Zhang","submitted_at":"2024-12-11T18:06:44Z","abstract_excerpt":"Both encoder-only models (e.g., BERT, RoBERTa) and large language models (LLMs, e.g., Llama3) have been widely used for text classification tasks. However, there is a lack of systematic studies comparing the performance of encoder-based models and LLMs in text classification, particularly when fine-tuning is involved. This study employed a diverse range of models and methods, varying in size and architecture, and including both fine-tuned and pre-trained approaches. We first assessed the performances of these LLMs on the 20 Newsgroups (20NG) and MASSIVE datasets, comparing them to encoder-only"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08587","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/2412.08587/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":"2412.08587","created_at":"2026-07-05T11:01:29.820292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08587v2","created_at":"2026-07-05T11:01:29.820292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08587","created_at":"2026-07-05T11:01:29.820292+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CGRBTQ3LBR4","created_at":"2026-07-05T11:01:29.820292+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CGRBTQ3LBR4XPEF","created_at":"2026-07-05T11:01:29.820292+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CGRBTQ3","created_at":"2026-07-05T11:01:29.820292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20358","citing_title":"Beyond Binary Moderation: Identifying Fine-Grained Sexist and Misogynistic Behavior on GitHub with Large Language Models","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CGRBTQ3LBR4XPEFBVFEL3QYNR","json":"https://pith.science/pith/6CGRBTQ3LBR4XPEFBVFEL3QYNR.json","graph_json":"https://pith.science/api/pith-number/6CGRBTQ3LBR4XPEFBVFEL3QYNR/graph.json","events_json":"https://pith.science/api/pith-number/6CGRBTQ3LBR4XPEFBVFEL3QYNR/events.json","paper":"https://pith.science/paper/6CGRBTQ3"},"agent_actions":{"view_html":"https://pith.science/pith/6CGRBTQ3LBR4XPEFBVFEL3QYNR","download_json":"https://pith.science/pith/6CGRBTQ3LBR4XPEFBVFEL3QYNR.json","view_paper":"https://pith.science/paper/6CGRBTQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08587&json=true","fetch_graph":"https://pith.science/api/pith-number/6CGRBTQ3LBR4XPEFBVFEL3QYNR/graph.json","fetch_events":"https://pith.science/api/pith-number/6CGRBTQ3LBR4XPEFBVFEL3QYNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CGRBTQ3LBR4XPEFBVFEL3QYNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CGRBTQ3LBR4XPEFBVFEL3QYNR/action/storage_attestation","attest_author":"https://pith.science/pith/6CGRBTQ3LBR4XPEFBVFEL3QYNR/action/author_attestation","sign_citation":"https://pith.science/pith/6CGRBTQ3LBR4XPEFBVFEL3QYNR/action/citation_signature","submit_replication":"https://pith.science/pith/6CGRBTQ3LBR4XPEFBVFEL3QYNR/action/replication_record"}},"created_at":"2026-07-05T11:01:29.820292+00:00","updated_at":"2026-07-05T11:01:29.820292+00:00"}