{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IBZC7HJI227AZRWVS3YL6T6OWS","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":"82cfe915f9a54da3acd82b346b2c6fd3ffcf3b124acb0f8b994284132ce1c3bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T06:57:49Z","title_canon_sha256":"446b6b025fc21b4f229e2d969e5ccdaee84eb4ed934eeaea05e242e777e21926"},"schema_version":"1.0","source":{"id":"2504.15640","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15640","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15640v2","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15640","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_12","alias_value":"IBZC7HJI227A","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_16","alias_value":"IBZC7HJI227AZRWV","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_8","alias_value":"IBZC7HJI","created_at":"2026-07-05T11:56:56Z"}],"graph_snapshots":[{"event_id":"sha256:ae3a4014c94c9bc3a07e51730988f8141a5d667d4290ff63e3f710a3e2d5348f","target":"graph","created_at":"2026-07-05T11:56:56Z","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/2504.15640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text clustering aims to automatically partition a collection of documents into coherent groups based on their linguistic features. In the literature, this task is formulated either as metric clustering over pre-trained text embeddings or as graph clustering based on pairwise similarities derived from an oracle, e.g., a large machine learning model. Recent advances in large language models (LLMs) have significantly improved this field by providing high-quality contextualized embeddings and accurate semantic similarity estimates. However, leveraging LLMs at scale introduces substantial computati","authors_text":"Hongtao Wang, Jianliang Xu, Renchi Yang, Taiyan Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T06:57:49Z","title":"Cequel: Cost-Effective Querying of Large Language Models for Text Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15640","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:f604082ffdc9cb385e4cac4fdc8a643fd9150df6a59385fe3510edf1211864b7","target":"record","created_at":"2026-07-05T11:56:56Z","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":"82cfe915f9a54da3acd82b346b2c6fd3ffcf3b124acb0f8b994284132ce1c3bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T06:57:49Z","title_canon_sha256":"446b6b025fc21b4f229e2d969e5ccdaee84eb4ed934eeaea05e242e777e21926"},"schema_version":"1.0","source":{"id":"2504.15640","kind":"arxiv","version":2}},"canonical_sha256":"40722f9d28d6be0cc6d596f0bf4fceb48f3e87d814ea534573c80c972e2c0400","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40722f9d28d6be0cc6d596f0bf4fceb48f3e87d814ea534573c80c972e2c0400","first_computed_at":"2026-07-05T11:56:56.259902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:56.259902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5E9IN6a/TXickRk79JrsdpkA+jKDmLgyqap8mc3ns4BvzLCrB/W6SqoS6BUEeTLOG6Pm4rwadLFL7unDcoQ+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:56.260539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15640","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f604082ffdc9cb385e4cac4fdc8a643fd9150df6a59385fe3510edf1211864b7","sha256:ae3a4014c94c9bc3a07e51730988f8141a5d667d4290ff63e3f710a3e2d5348f"],"state_sha256":"77ccd5d9010b8646b4e791fa1822846ba449edd782dcb3c4f42692a6588bfaf7"}