{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:J22BDJ7UG6OUQU7F3ZPGU23YUT","short_pith_number":"pith:J22BDJ7U","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"},"canonical_sha256":"4eb411a7f4379d4853e5de5e6a6b78a4d5da4cc44ea3e91807d4862bb73af167","source":{"kind":"arxiv","id":"2305.14871","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14871","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14871v2","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14871","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"J22BDJ7UG6OU","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_16","alias_value":"J22BDJ7UG6OUQU7F","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_8","alias_value":"J22BDJ7U","created_at":"2026-07-05T07:08:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:J22BDJ7UG6OUQU7F3ZPGU23YUT","target":"record","payload":{"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"},"canonical_sha256":"4eb411a7f4379d4853e5de5e6a6b78a4d5da4cc44ea3e91807d4862bb73af167","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"},"source_kind":"arxiv","source_id":"2305.14871","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+X2B7Bb5rroyxrrfTRMqMgk1lQaPyIdnRLFtdzDxB8wlFldi7KVMSTMRN5xXENVNwVyZpFMy7034BxVGWRUJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:56:28.565726Z"},"content_sha256":"053d0ee6a0fe353825f3f450005f9d1ace28c240ae254747b7546aafb5194f13","schema_version":"1.0","event_id":"sha256:053d0ee6a0fe353825f3f450005f9d1ace28c240ae254747b7546aafb5194f13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:J22BDJ7UG6OUQU7F3ZPGU23YUT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iIhDAI/v7ZY7aojaor4EzoO3R+563CaRvRhVmwap8X6H39hkmwgaGUkBWBdffrZ6cdgmlE1YUCFCNHCRw+FsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:56:28.566243Z"},"content_sha256":"bb83e60497a1f06e7b3599a02f37cbbab11a62b8536b0b2e6fda88c64dd48b85","schema_version":"1.0","event_id":"sha256:bb83e60497a1f06e7b3599a02f37cbbab11a62b8536b0b2e6fda88c64dd48b85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT/bundle.json","state_url":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT/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":"2026-08-09T05:56:28Z","links":{"resolver":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT","bundle":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT/bundle.json","state":"https://pith.science/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J22BDJ7UG6OUQU7F3ZPGU23YUT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J22BDJ7UG6OUQU7F3ZPGU23YUT","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":"d6ecad01fb737d2080da78b1084d22a9961e004f65e3b889493423276ee56137","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:24:25Z","title_canon_sha256":"016d8cb2ccdd7a9277a5dc91e50d3bca6affac68c2e37b8564f75dd99f646a6e"},"schema_version":"1.0","source":{"id":"2305.14871","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14871","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14871v2","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14871","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"J22BDJ7UG6OU","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_16","alias_value":"J22BDJ7UG6OUQU7F","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_8","alias_value":"J22BDJ7U","created_at":"2026-07-05T07:08:58Z"}],"graph_snapshots":[{"event_id":"sha256:bb83e60497a1f06e7b3599a02f37cbbab11a62b8536b0b2e6fda88c64dd48b85","target":"graph","created_at":"2026-07-05T07:08:58Z","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/2305.14871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jingbo Shang, Yuwei Zhang, Zihan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:24:25Z","title":"ClusterLLM: Large Language Models as a Guide for Text Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14871","kind":"arxiv","version":2},"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":"sha256:053d0ee6a0fe353825f3f450005f9d1ace28c240ae254747b7546aafb5194f13","target":"record","created_at":"2026-07-05T07:08:58Z","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":"d6ecad01fb737d2080da78b1084d22a9961e004f65e3b889493423276ee56137","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:24:25Z","title_canon_sha256":"016d8cb2ccdd7a9277a5dc91e50d3bca6affac68c2e37b8564f75dd99f646a6e"},"schema_version":"1.0","source":{"id":"2305.14871","kind":"arxiv","version":2}},"canonical_sha256":"4eb411a7f4379d4853e5de5e6a6b78a4d5da4cc44ea3e91807d4862bb73af167","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4eb411a7f4379d4853e5de5e6a6b78a4d5da4cc44ea3e91807d4862bb73af167","first_computed_at":"2026-07-05T07:08:58.024391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:58.024391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gvcH6F1I150JFcdLBc6MyBVdacnivkttOHU6cBlc9tamFv5swuZ3H364HAkI6FI6g5YXK7KKMCjiL9Mr90BxCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:58.024869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14871","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:053d0ee6a0fe353825f3f450005f9d1ace28c240ae254747b7546aafb5194f13","sha256:bb83e60497a1f06e7b3599a02f37cbbab11a62b8536b0b2e6fda88c64dd48b85"],"state_sha256":"4b9c3afd16c348b3fb6f273494a6e1000b7422fb232957d9af7d76663642de64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hQOCOFH3sGBNcKfyJfmyadjuVJR/HqqPobXI7TDLdieansvr+pVQ++T2uQYDkOOWwaE8czU/Sva5FxWkSQgCDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:56:28.571179Z","bundle_sha256":"ef7b14c270af531b87a2850dd2f93760b6730e3955debf1ada97283caf185556"}}