{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:P6ZCM4XNE53IDPMURO67JP7DOJ","short_pith_number":"pith:P6ZCM4XN","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"},"canonical_sha256":"7fb22672ed277681bd948bbdf4bfe372669779e92f74488c9d192c2da0cfc64f","source":{"kind":"arxiv","id":"2307.00524","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00524","created_at":"2026-07-05T06:26:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00524v1","created_at":"2026-07-05T06:26:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00524","created_at":"2026-07-05T06:26:57Z"},{"alias_kind":"pith_short_12","alias_value":"P6ZCM4XNE53I","created_at":"2026-07-05T06:26:57Z"},{"alias_kind":"pith_short_16","alias_value":"P6ZCM4XNE53IDPMU","created_at":"2026-07-05T06:26:57Z"},{"alias_kind":"pith_short_8","alias_value":"P6ZCM4XN","created_at":"2026-07-05T06:26:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:P6ZCM4XNE53IDPMURO67JP7DOJ","target":"record","payload":{"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"},"canonical_sha256":"7fb22672ed277681bd948bbdf4bfe372669779e92f74488c9d192c2da0cfc64f","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"},"source_kind":"arxiv","source_id":"2307.00524","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:26:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s8KsXqZi6GuCS/fyvj33BK1Mi2ke622vWjdJeVe5AastMIANupJ1WIsRBqktXjcPZ+qQ+rTVTntdM5EF1xlgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:58:58.921276Z"},"content_sha256":"a58030cb58136851fa4bb684323fa8cfd0bb82517fbf94dea37e6083c173159e","schema_version":"1.0","event_id":"sha256:a58030cb58136851fa4bb684323fa8cfd0bb82517fbf94dea37e6083c173159e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:P6ZCM4XNE53IDPMURO67JP7DOJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:26:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ASjFrrSZ6RyZMHk8JfNK0V027QEC/DT6lBYlYENuS6F7MdeQjjZmeuZcM9b7XW+yKYuvgVuRUesaHC2qOZstCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:58:58.921801Z"},"content_sha256":"e10b0899c1660e81040dda3e18fb8da3b83dd51c756990557c826565bfe1771d","schema_version":"1.0","event_id":"sha256:e10b0899c1660e81040dda3e18fb8da3b83dd51c756990557c826565bfe1771d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ/bundle.json","state_url":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P6ZCM4XNE53IDPMURO67JP7DOJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T09:58:58Z","links":{"resolver":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ","bundle":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ/bundle.json","state":"https://pith.science/pith/P6ZCM4XNE53IDPMURO67JP7DOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P6ZCM4XNE53IDPMURO67JP7DOJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P6ZCM4XNE53IDPMURO67JP7DOJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9881df56b3c72ffacdb683a0416cfa3133a1d7a8cb3f9550a0fa23acfe8acadd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-02T09:17:11Z","title_canon_sha256":"ded5660dba8e715567a946d3e67e91f0eaf115be49a66068e9c2ff81a4145f80"},"schema_version":"1.0","source":{"id":"2307.00524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00524","created_at":"2026-07-05T06:26:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00524v1","created_at":"2026-07-05T06:26:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00524","created_at":"2026-07-05T06:26:57Z"},{"alias_kind":"pith_short_12","alias_value":"P6ZCM4XNE53I","created_at":"2026-07-05T06:26:57Z"},{"alias_kind":"pith_short_16","alias_value":"P6ZCM4XNE53IDPMU","created_at":"2026-07-05T06:26:57Z"},{"alias_kind":"pith_short_8","alias_value":"P6ZCM4XN","created_at":"2026-07-05T06:26:57Z"}],"graph_snapshots":[{"event_id":"sha256:e10b0899c1660e81040dda3e18fb8da3b83dd51c756990557c826565bfe1771d","target":"graph","created_at":"2026-07-05T06:26:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2307.00524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Carolin Lawrence, Graham Neubig, Kiril Gashteovski, Tongshuang Wu, Vijay Viswanathan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-02T09:17:11Z","title":"Large Language Models Enable Few-Shot Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00524","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a58030cb58136851fa4bb684323fa8cfd0bb82517fbf94dea37e6083c173159e","target":"record","created_at":"2026-07-05T06:26:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9881df56b3c72ffacdb683a0416cfa3133a1d7a8cb3f9550a0fa23acfe8acadd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-02T09:17:11Z","title_canon_sha256":"ded5660dba8e715567a946d3e67e91f0eaf115be49a66068e9c2ff81a4145f80"},"schema_version":"1.0","source":{"id":"2307.00524","kind":"arxiv","version":1}},"canonical_sha256":"7fb22672ed277681bd948bbdf4bfe372669779e92f74488c9d192c2da0cfc64f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fb22672ed277681bd948bbdf4bfe372669779e92f74488c9d192c2da0cfc64f","first_computed_at":"2026-07-05T06:26:57.070950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:57.070950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lOCx7V0n69fM5g+KOvSBqQKfN71W/MVVx5m5Dt4q2BT0zw3b07/5gO078VFpUiIL+jyr6PkBkUoKMtdJPCnFBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:57.071390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.00524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a58030cb58136851fa4bb684323fa8cfd0bb82517fbf94dea37e6083c173159e","sha256:e10b0899c1660e81040dda3e18fb8da3b83dd51c756990557c826565bfe1771d"],"state_sha256":"c4c253969f8f8d9e7cbd901c56ff8387fbe11a983aa5bb3b6997cce18f29177f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jOywpPyYq/xWFNos4npoctgWjNKCUR2K4r29lCj3ocr4YpaocapEESsFQyqgj4zedINfPOXj2Ptua8m3YvNUDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T09:58:58.926306Z","bundle_sha256":"2cd1a38d0819bf2b10ad839dc17088b2c00c4d02c055e6924f7a9d67d0e78397"}}