{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P6ZCM4XNE53IDPMURO67JP7DOJ","short_pith_number":"pith:P6ZCM4XN","schema_version":"1.0","canonical_sha256":"7fb22672ed277681bd948bbdf4bfe372669779e92f74488c9d192c2da0cfc64f","source":{"kind":"arxiv","id":"2307.00524","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models Enable Few-Shot Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carolin Lawrence, Graham Neubig, Kiril Gashteovski, Tongshuang Wu, Vijay Viswanathan","submitted_at":"2023-07-02T09:17:11Z","abstract_excerpt":"Unlike traditional unsupervised clustering, semi-supervised clustering allows users to provide meaningful structure to the data, which helps the clustering algorithm to match the user's intent. Existing approaches to semi-supervised clustering require a significant amount of feedback from an expert to improve the clusters. In this paper, we ask whether a large language model can amplify an expert's guidance to enable query-efficient, few-shot semi-supervised text clustering. We show that LLMs are surprisingly effective at improving clustering. We explore three stages where LLMs can be incorpor"},"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":"2307.00524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-02T09:17:11Z","cross_cats_sorted":[],"title_canon_sha256":"ded5660dba8e715567a946d3e67e91f0eaf115be49a66068e9c2ff81a4145f80","abstract_canon_sha256":"9881df56b3c72ffacdb683a0416cfa3133a1d7a8cb3f9550a0fa23acfe8acadd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:57.071390Z","signature_b64":"lOCx7V0n69fM5g+KOvSBqQKfN71W/MVVx5m5Dt4q2BT0zw3b07/5gO078VFpUiIL+jyr6PkBkUoKMtdJPCnFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fb22672ed277681bd948bbdf4bfe372669779e92f74488c9d192c2da0cfc64f","last_reissued_at":"2026-07-05T06:26:57.070950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:57.070950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Enable Few-Shot Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carolin Lawrence, Graham Neubig, Kiril Gashteovski, Tongshuang Wu, Vijay Viswanathan","submitted_at":"2023-07-02T09:17:11Z","abstract_excerpt":"Unlike traditional unsupervised clustering, semi-supervised clustering allows users to provide meaningful structure to the data, which helps the clustering algorithm to match the user's intent. Existing approaches to semi-supervised clustering require a significant amount of feedback from an expert to improve the clusters. In this paper, we ask whether a large language model can amplify an expert's guidance to enable query-efficient, few-shot semi-supervised text clustering. We show that LLMs are surprisingly effective at improving clustering. We explore three stages where LLMs can be incorpor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00524","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/2307.00524/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":"2307.00524","created_at":"2026-07-05T06:26:57.071005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00524v1","created_at":"2026-07-05T06:26:57.071005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00524","created_at":"2026-07-05T06:26:57.071005+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6ZCM4XNE53I","created_at":"2026-07-05T06:26:57.071005+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6ZCM4XNE53IDPMU","created_at":"2026-07-05T06:26:57.071005+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6ZCM4XN","created_at":"2026-07-05T06:26:57.071005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10737","citing_title":"TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ","json":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ.json","graph_json":"https://pith.science/api/pith-number/P6ZCM4XNE53IDPMURO67JP7DOJ/graph.json","events_json":"https://pith.science/api/pith-number/P6ZCM4XNE53IDPMURO67JP7DOJ/events.json","paper":"https://pith.science/paper/P6ZCM4XN"},"agent_actions":{"view_html":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ","download_json":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ.json","view_paper":"https://pith.science/paper/P6ZCM4XN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00524&json=true","fetch_graph":"https://pith.science/api/pith-number/P6ZCM4XNE53IDPMURO67JP7DOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/P6ZCM4XNE53IDPMURO67JP7DOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ/action/storage_attestation","attest_author":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ/action/author_attestation","sign_citation":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ/action/citation_signature","submit_replication":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ/action/replication_record"}},"created_at":"2026-07-05T06:26:57.071005+00:00","updated_at":"2026-07-05T06:26:57.071005+00:00"}