{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6SQWDUGSIV3DFWH3CU2KVO55UV","short_pith_number":"pith:6SQWDUGS","schema_version":"1.0","canonical_sha256":"f4a161d0d2457632d8fb1534aabbbda55690695b3b3a6aed8067eb4e188c4923","source":{"kind":"arxiv","id":"2209.11055","version":1},"attestation_state":"computed","paper":{"title":"Efficient Few-Shot Learning Without Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Korat, Lewis Tunstall, Luke Bates, Moshe Wasserblat, Nils Reimers, Oren Pereg, Unso Eun Seo Jo","submitted_at":"2022-09-22T14:48:11Z","abstract_excerpt":"Recent few-shot methods, such as parameter-efficient fine-tuning (PEFT) and pattern exploiting training (PET), have achieved impressive results in label-scarce settings. However, they are difficult to employ since they are subject to high variability from manually crafted prompts, and typically require billion-parameter language models to achieve high accuracy. To address these shortcomings, we propose SetFit (Sentence Transformer Fine-tuning), an efficient and prompt-free framework for few-shot fine-tuning of Sentence Transformers (ST). SetFit works by first fine-tuning a pretrained ST on a s"},"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":"2209.11055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-22T14:48:11Z","cross_cats_sorted":[],"title_canon_sha256":"ec5437690aeb9e5f298dec6076b139ba787dfe1874a385b86a947ded5bbde8c3","abstract_canon_sha256":"65caee85fa4edc2e03f87806200013714f3d4a586772a918c5495f44b6407109"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:09.733494Z","signature_b64":"gUSjxmSWD+HeyZ0+6Bh9WtRIL43HyY5GlpfKehI/dG+kDcbubKcrBDwLIlze5ihQBJKd7UaiA9AlVh6BCdUJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4a161d0d2457632d8fb1534aabbbda55690695b3b3a6aed8067eb4e188c4923","last_reissued_at":"2026-07-05T05:00:09.733090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:09.733090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Few-Shot Learning Without Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Korat, Lewis Tunstall, Luke Bates, Moshe Wasserblat, Nils Reimers, Oren Pereg, Unso Eun Seo Jo","submitted_at":"2022-09-22T14:48:11Z","abstract_excerpt":"Recent few-shot methods, such as parameter-efficient fine-tuning (PEFT) and pattern exploiting training (PET), have achieved impressive results in label-scarce settings. However, they are difficult to employ since they are subject to high variability from manually crafted prompts, and typically require billion-parameter language models to achieve high accuracy. To address these shortcomings, we propose SetFit (Sentence Transformer Fine-tuning), an efficient and prompt-free framework for few-shot fine-tuning of Sentence Transformers (ST). SetFit works by first fine-tuning a pretrained ST on a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11055","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/2209.11055/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":"2209.11055","created_at":"2026-07-05T05:00:09.733147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.11055v1","created_at":"2026-07-05T05:00:09.733147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11055","created_at":"2026-07-05T05:00:09.733147+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SQWDUGSIV3D","created_at":"2026-07-05T05:00:09.733147+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SQWDUGSIV3DFWH3","created_at":"2026-07-05T05:00:09.733147+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SQWDUGS","created_at":"2026-07-05T05:00:09.733147+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10736","citing_title":"Detecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphs","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08605","citing_title":"Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11336","citing_title":"Much of Geospatial Web Search Is Beyond Traditional GIS","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29659","citing_title":"Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21609","citing_title":"CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13353","citing_title":"Cross-Domain Query Translation for Network Troubleshooting: A Multi-Agent LLM Framework with Privacy Preservation and Self-Reflection","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2412.13663","citing_title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","ref_index":190,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16301","citing_title":"Domain-Specific Query Understanding for Automotive Applications: A Modular and Scalable Approach","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22264","citing_title":"Predicting Intermittent Job Failure Categories for Diagnosis Using Few-Shot Fine-Tuned Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03959","citing_title":"LoRA-MME: Multi-Model Ensemble of LoRA-Tuned Encoders for Code Comment Classification","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11213","citing_title":"Quantum Parity Representations: Learnable Basis Discovery, Encoders, and Shadow Deployment","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11336","citing_title":"Much of Geospatial Web Search Is Beyond Traditional GIS","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03450","citing_title":"Retrieving Floods without Floodlights: Topic Models as Binary Classifiers for Extreme Climate Events in German News","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12190","citing_title":"Characterizing Resource Sharing Practices on Underground Internet Forum Synthetic Non-Consensual Intimate Image Content Creation Communities","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13353","citing_title":"Cross-Domain Query Translation for Network Troubleshooting: A Multi-Agent LLM Framework with Privacy Preservation and Self-Reflection","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02798","citing_title":"Measuring Accuracy and Energy-to-Solution of Quantum Fine-Tuning of Foundational AI Models","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SQWDUGSIV3DFWH3CU2KVO55UV","json":"https://pith.science/pith/6SQWDUGSIV3DFWH3CU2KVO55UV.json","graph_json":"https://pith.science/api/pith-number/6SQWDUGSIV3DFWH3CU2KVO55UV/graph.json","events_json":"https://pith.science/api/pith-number/6SQWDUGSIV3DFWH3CU2KVO55UV/events.json","paper":"https://pith.science/paper/6SQWDUGS"},"agent_actions":{"view_html":"https://pith.science/pith/6SQWDUGSIV3DFWH3CU2KVO55UV","download_json":"https://pith.science/pith/6SQWDUGSIV3DFWH3CU2KVO55UV.json","view_paper":"https://pith.science/paper/6SQWDUGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.11055&json=true","fetch_graph":"https://pith.science/api/pith-number/6SQWDUGSIV3DFWH3CU2KVO55UV/graph.json","fetch_events":"https://pith.science/api/pith-number/6SQWDUGSIV3DFWH3CU2KVO55UV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SQWDUGSIV3DFWH3CU2KVO55UV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SQWDUGSIV3DFWH3CU2KVO55UV/action/storage_attestation","attest_author":"https://pith.science/pith/6SQWDUGSIV3DFWH3CU2KVO55UV/action/author_attestation","sign_citation":"https://pith.science/pith/6SQWDUGSIV3DFWH3CU2KVO55UV/action/citation_signature","submit_replication":"https://pith.science/pith/6SQWDUGSIV3DFWH3CU2KVO55UV/action/replication_record"}},"created_at":"2026-07-05T05:00:09.733147+00:00","updated_at":"2026-07-05T05:00:09.733147+00:00"}