{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O5EJMYI6XSICGJVPCIWOV6TW7L","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":"c578a028fd06088cff70c417ad7b8c7a0a7893af514c16d210c801bbd29348db","cross_cats_sorted":["cs.CL","cs.IR","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T06:21:21Z","title_canon_sha256":"12724426dea3d81d1dce0538b59513383d5b03149a64a230372133bf5df7dbbd"},"schema_version":"1.0","source":{"id":"2412.13534","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13534","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13534v1","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13534","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_12","alias_value":"O5EJMYI6XSIC","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_16","alias_value":"O5EJMYI6XSICGJVP","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_8","alias_value":"O5EJMYI6","created_at":"2026-07-05T09:51:03Z"}],"graph_snapshots":[{"event_id":"sha256:0c38ab56a9b421507658524e56361b4d9eb434f4b07b6ffee6b4ba91007c83b1","target":"graph","created_at":"2026-07-05T09:51:03Z","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/2412.13534/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present {\\em generative clustering} (GC) for clustering a set of documents, $\\mathrm{X}$, by using texts $\\mathrm{Y}$ generated by large language models (LLMs) instead of by clustering the original documents $\\mathrm{X}$. Because LLMs provide probability distributions, the similarity between two documents can be rigorously defined in an information-theoretic manner by the KL divergence. We also propose a natural, novel clustering algorithm by using importance sampling. We show that GC achieves the state-of-the-art performance, outperforming any previous clustering method often by a large ma","authors_text":"Kumiko Tanaka-Ishii, Xin Du","cross_cats":["cs.CL","cs.IR","cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T06:21:21Z","title":"Information-Theoretic Generative Clustering of Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13534","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":"sha256:04621598f7686792b6b35b99037f8d12e198b98079372f971367d652757d1d5e","target":"record","created_at":"2026-07-05T09:51:03Z","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":"c578a028fd06088cff70c417ad7b8c7a0a7893af514c16d210c801bbd29348db","cross_cats_sorted":["cs.CL","cs.IR","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T06:21:21Z","title_canon_sha256":"12724426dea3d81d1dce0538b59513383d5b03149a64a230372133bf5df7dbbd"},"schema_version":"1.0","source":{"id":"2412.13534","kind":"arxiv","version":1}},"canonical_sha256":"774896611ebc902326af122ceafa76fad0000b49062ad36fb339901c417f2d99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"774896611ebc902326af122ceafa76fad0000b49062ad36fb339901c417f2d99","first_computed_at":"2026-07-05T09:51:03.532451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:03.532451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QTaJYps64FcfPHkqyr+Cc3KHYKgJMr12B9vN2PT6XbbnsaGhWty3tKN4+Y0vDOWxPl/D3T8OGrv3LipmaHFlDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:03.532936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13534","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04621598f7686792b6b35b99037f8d12e198b98079372f971367d652757d1d5e","sha256:0c38ab56a9b421507658524e56361b4d9eb434f4b07b6ffee6b4ba91007c83b1"],"state_sha256":"3d776ec18c6b5820d205e3015b8eb9826372d3fcc75d85a303e84c4bca732d82"}