{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MI6BZQCDLM5D6ZRL5HSGHISOWT","short_pith_number":"pith:MI6BZQCD","schema_version":"1.0","canonical_sha256":"623c1cc0435b3a3f662be9e463a24eb4e9fa1c7778fe3dd0fc8e56727f14b28b","source":{"kind":"arxiv","id":"2307.02179","version":2},"attestation_state":"computed","paper":{"title":"Open-Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fabrizio Gilardi, Juan Diego Bermeo, Ma\\\"el Kubli, Maria Korobeynikova, Meysam Alizadeh, Mohammadmasiha Zahedivafa, Shirin Dehghani, Zeynab Samei","submitted_at":"2023-07-05T10:15:07Z","abstract_excerpt":"This paper studies the performance of open-source Large Language Models (LLMs) in text classification tasks typical for political science research. By examining tasks like stance, topic, and relevance classification, we aim to guide scholars in making informed decisions about their use of LLMs for text analysis. Specifically, we conduct an assessment of both zero-shot and fine-tuned LLMs across a range of text annotation tasks using news articles and tweets datasets. Our analysis shows that fine-tuning improves the performance of open-source LLMs, allowing them to match or even surpass zero-sh"},"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":"2307.02179","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-05T10:15:07Z","cross_cats_sorted":[],"title_canon_sha256":"74ca7ec933d108dbc462302a5ed1107b2925ac0568996f25e2d199a0ebfe028e","abstract_canon_sha256":"36124925f64d69f240d38f698658b3449bc8b480d4a808fbc450cf4d0a2635fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:36.815949Z","signature_b64":"rdIDeYL3DesCFL2CIHyWSm7GRpqvFLuprLdRIjJczV8xODzEsJQ1KKHoBrLEHSOtkr3RvhdkmDic/CADszagDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"623c1cc0435b3a3f662be9e463a24eb4e9fa1c7778fe3dd0fc8e56727f14b28b","last_reissued_at":"2026-07-05T08:24:36.815492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:36.815492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fabrizio Gilardi, Juan Diego Bermeo, Ma\\\"el Kubli, Maria Korobeynikova, Meysam Alizadeh, Mohammadmasiha Zahedivafa, Shirin Dehghani, Zeynab Samei","submitted_at":"2023-07-05T10:15:07Z","abstract_excerpt":"This paper studies the performance of open-source Large Language Models (LLMs) in text classification tasks typical for political science research. By examining tasks like stance, topic, and relevance classification, we aim to guide scholars in making informed decisions about their use of LLMs for text analysis. Specifically, we conduct an assessment of both zero-shot and fine-tuned LLMs across a range of text annotation tasks using news articles and tweets datasets. Our analysis shows that fine-tuning improves the performance of open-source LLMs, allowing them to match or even surpass zero-sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02179","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/2307.02179/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":"2307.02179","created_at":"2026-07-05T08:24:36.815551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02179v2","created_at":"2026-07-05T08:24:36.815551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02179","created_at":"2026-07-05T08:24:36.815551+00:00"},{"alias_kind":"pith_short_12","alias_value":"MI6BZQCDLM5D","created_at":"2026-07-05T08:24:36.815551+00:00"},{"alias_kind":"pith_short_16","alias_value":"MI6BZQCDLM5D6ZRL","created_at":"2026-07-05T08:24:36.815551+00:00"},{"alias_kind":"pith_short_8","alias_value":"MI6BZQCD","created_at":"2026-07-05T08:24:36.815551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.03825","citing_title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MI6BZQCDLM5D6ZRL5HSGHISOWT","json":"https://pith.science/pith/MI6BZQCDLM5D6ZRL5HSGHISOWT.json","graph_json":"https://pith.science/api/pith-number/MI6BZQCDLM5D6ZRL5HSGHISOWT/graph.json","events_json":"https://pith.science/api/pith-number/MI6BZQCDLM5D6ZRL5HSGHISOWT/events.json","paper":"https://pith.science/paper/MI6BZQCD"},"agent_actions":{"view_html":"https://pith.science/pith/MI6BZQCDLM5D6ZRL5HSGHISOWT","download_json":"https://pith.science/pith/MI6BZQCDLM5D6ZRL5HSGHISOWT.json","view_paper":"https://pith.science/paper/MI6BZQCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02179&json=true","fetch_graph":"https://pith.science/api/pith-number/MI6BZQCDLM5D6ZRL5HSGHISOWT/graph.json","fetch_events":"https://pith.science/api/pith-number/MI6BZQCDLM5D6ZRL5HSGHISOWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MI6BZQCDLM5D6ZRL5HSGHISOWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MI6BZQCDLM5D6ZRL5HSGHISOWT/action/storage_attestation","attest_author":"https://pith.science/pith/MI6BZQCDLM5D6ZRL5HSGHISOWT/action/author_attestation","sign_citation":"https://pith.science/pith/MI6BZQCDLM5D6ZRL5HSGHISOWT/action/citation_signature","submit_replication":"https://pith.science/pith/MI6BZQCDLM5D6ZRL5HSGHISOWT/action/replication_record"}},"created_at":"2026-07-05T08:24:36.815551+00:00","updated_at":"2026-07-05T08:24:36.815551+00:00"}