{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IBZC7HJI227AZRWVS3YL6T6OWS","short_pith_number":"pith:IBZC7HJI","canonical_record":{"source":{"id":"2504.15640","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T06:57:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"446b6b025fc21b4f229e2d969e5ccdaee84eb4ed934eeaea05e242e777e21926","abstract_canon_sha256":"82cfe915f9a54da3acd82b346b2c6fd3ffcf3b124acb0f8b994284132ce1c3bc"},"schema_version":"1.0"},"canonical_sha256":"40722f9d28d6be0cc6d596f0bf4fceb48f3e87d814ea534573c80c972e2c0400","source":{"kind":"arxiv","id":"2504.15640","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IBZC7HJI227AZRWVS3YL6T6OWS","target":"record","payload":{"canonical_record":{"source":{"id":"2504.15640","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T06:57:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"446b6b025fc21b4f229e2d969e5ccdaee84eb4ed934eeaea05e242e777e21926","abstract_canon_sha256":"82cfe915f9a54da3acd82b346b2c6fd3ffcf3b124acb0f8b994284132ce1c3bc"},"schema_version":"1.0"},"canonical_sha256":"40722f9d28d6be0cc6d596f0bf4fceb48f3e87d814ea534573c80c972e2c0400","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:56.260539Z","signature_b64":"5E9IN6a/TXickRk79JrsdpkA+jKDmLgyqap8mc3ns4BvzLCrB/W6SqoS6BUEeTLOG6Pm4rwadLFL7unDcoQ+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40722f9d28d6be0cc6d596f0bf4fceb48f3e87d814ea534573c80c972e2c0400","last_reissued_at":"2026-07-05T11:56:56.259902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:56.259902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.15640","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":"2026-07-05T11:56:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vjHnI2Ei6NABP4egTgwtvc0HBiZgx7K2vy2vi1XU0582KGsVi4gafk6djnbQ2wRGS7dkuGV04qBykxkJQcZWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:52:01.897033Z"},"content_sha256":"f604082ffdc9cb385e4cac4fdc8a643fd9150df6a59385fe3510edf1211864b7","schema_version":"1.0","event_id":"sha256:f604082ffdc9cb385e4cac4fdc8a643fd9150df6a59385fe3510edf1211864b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IBZC7HJI227AZRWVS3YL6T6OWS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cequel: Cost-Effective Querying of Large Language Models for Text Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongtao Wang, Jianliang Xu, Renchi Yang, Taiyan Zhang","submitted_at":"2025-04-22T06:57:49Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15640","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/2504.15640/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":"2026-07-05T11:56:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CoabWawgPCOLjflHgCdUDxy26ifKeAC5orhHfXYRyLpV4iKKyo95DwwLjO1bsumMzmeCvfC70F5nsllebZSdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:52:01.897721Z"},"content_sha256":"ae3a4014c94c9bc3a07e51730988f8141a5d667d4290ff63e3f710a3e2d5348f","schema_version":"1.0","event_id":"sha256:ae3a4014c94c9bc3a07e51730988f8141a5d667d4290ff63e3f710a3e2d5348f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBZC7HJI227AZRWVS3YL6T6OWS/bundle.json","state_url":"https://pith.science/pith/IBZC7HJI227AZRWVS3YL6T6OWS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBZC7HJI227AZRWVS3YL6T6OWS/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":"2026-07-07T00:52:01Z","links":{"resolver":"https://pith.science/pith/IBZC7HJI227AZRWVS3YL6T6OWS","bundle":"https://pith.science/pith/IBZC7HJI227AZRWVS3YL6T6OWS/bundle.json","state":"https://pith.science/pith/IBZC7HJI227AZRWVS3YL6T6OWS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBZC7HJI227AZRWVS3YL6T6OWS/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZlCLOh5Lj9ADyh1FRVPi/Rd0m/d5zvYfjtUOVrwS0Lf9S1mYt7QHZXABMe+FPD1RdxwT8JBD/q2vn3kUxQQAAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T00:52:01.901596Z","bundle_sha256":"b890842bb6eb3c067ce071213f6f640a4c5af35c360ba192a35dadd22685f9db"}}