{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J22BDJ7UG6OUQU7F3ZPGU23YUT","short_pith_number":"pith:J22BDJ7U","schema_version":"1.0","canonical_sha256":"4eb411a7f4379d4853e5de5e6a6b78a4d5da4cc44ea3e91807d4862bb73af167","source":{"kind":"arxiv","id":"2305.14871","version":2},"attestation_state":"computed","paper":{"title":"ClusterLLM: Large Language Models as a Guide for Text Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingbo Shang, Yuwei Zhang, Zihan Wang","submitted_at":"2023-05-24T08:24:25Z","abstract_excerpt":"We introduce ClusterLLM, a novel text clustering framework that leverages feedback from an instruction-tuned large language model, such as ChatGPT. Compared with traditional unsupervised methods that builds upon \"small\" embedders, ClusterLLM exhibits two intriguing advantages: (1) it enjoys the emergent capability of LLM even if its embeddings are inaccessible; and (2) it understands the user's preference on clustering through textual instruction and/or a few annotated data. First, we prompt ChatGPT for insights on clustering perspective by constructing hard triplet questions <does A better co"},"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":"2305.14871","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:24:25Z","cross_cats_sorted":[],"title_canon_sha256":"016d8cb2ccdd7a9277a5dc91e50d3bca6affac68c2e37b8564f75dd99f646a6e","abstract_canon_sha256":"d6ecad01fb737d2080da78b1084d22a9961e004f65e3b889493423276ee56137"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:58.024869Z","signature_b64":"gvcH6F1I150JFcdLBc6MyBVdacnivkttOHU6cBlc9tamFv5swuZ3H364HAkI6FI6g5YXK7KKMCjiL9Mr90BxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eb411a7f4379d4853e5de5e6a6b78a4d5da4cc44ea3e91807d4862bb73af167","last_reissued_at":"2026-07-05T07:08:58.024391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:58.024391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClusterLLM: Large Language Models as a Guide for Text Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingbo Shang, Yuwei Zhang, Zihan Wang","submitted_at":"2023-05-24T08:24:25Z","abstract_excerpt":"We introduce ClusterLLM, a novel text clustering framework that leverages feedback from an instruction-tuned large language model, such as ChatGPT. Compared with traditional unsupervised methods that builds upon \"small\" embedders, ClusterLLM exhibits two intriguing advantages: (1) it enjoys the emergent capability of LLM even if its embeddings are inaccessible; and (2) it understands the user's preference on clustering through textual instruction and/or a few annotated data. First, we prompt ChatGPT for insights on clustering perspective by constructing hard triplet questions <does A better co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14871","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/2305.14871/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":"2305.14871","created_at":"2026-07-05T07:08:58.024447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14871v2","created_at":"2026-07-05T07:08:58.024447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14871","created_at":"2026-07-05T07:08:58.024447+00:00"},{"alias_kind":"pith_short_12","alias_value":"J22BDJ7UG6OU","created_at":"2026-07-05T07:08:58.024447+00:00"},{"alias_kind":"pith_short_16","alias_value":"J22BDJ7UG6OUQU7F","created_at":"2026-07-05T07:08:58.024447+00:00"},{"alias_kind":"pith_short_8","alias_value":"J22BDJ7U","created_at":"2026-07-05T07:08:58.024447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29182","citing_title":"Evidence-Informed LLM Beliefs for Continual Scientific Discovery","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT","json":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT.json","graph_json":"https://pith.science/api/pith-number/J22BDJ7UG6OUQU7F3ZPGU23YUT/graph.json","events_json":"https://pith.science/api/pith-number/J22BDJ7UG6OUQU7F3ZPGU23YUT/events.json","paper":"https://pith.science/paper/J22BDJ7U"},"agent_actions":{"view_html":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT","download_json":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT.json","view_paper":"https://pith.science/paper/J22BDJ7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14871&json=true","fetch_graph":"https://pith.science/api/pith-number/J22BDJ7UG6OUQU7F3ZPGU23YUT/graph.json","fetch_events":"https://pith.science/api/pith-number/J22BDJ7UG6OUQU7F3ZPGU23YUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT/action/storage_attestation","attest_author":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT/action/author_attestation","sign_citation":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT/action/citation_signature","submit_replication":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT/action/replication_record"}},"created_at":"2026-07-05T07:08:58.024447+00:00","updated_at":"2026-07-05T07:08:58.024447+00:00"}