{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UCPZFAEGIW3PZFSRRWNZ5JKDGB","short_pith_number":"pith:UCPZFAEG","canonical_record":{"source":{"id":"2403.15112","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T11:08:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5585a7ea8e283f7d333b0e5c58ea1fc9d153a58886c89fa45da2d67b551c8129","abstract_canon_sha256":"215b27dca89ad953f889803710f9f129127bf5060fbb73f11e3056d17ee6cbb4"},"schema_version":"1.0"},"canonical_sha256":"a09f92808645b6fc96518d9b9ea5433064b87e59d10118a2fac39c94f04a5058","source":{"kind":"arxiv","id":"2403.15112","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.15112","created_at":"2026-07-05T09:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.15112v5","created_at":"2026-07-05T09:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15112","created_at":"2026-07-05T09:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"UCPZFAEGIW3P","created_at":"2026-07-05T09:44:50Z"},{"alias_kind":"pith_short_16","alias_value":"UCPZFAEGIW3PZFSR","created_at":"2026-07-05T09:44:50Z"},{"alias_kind":"pith_short_8","alias_value":"UCPZFAEG","created_at":"2026-07-05T09:44:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UCPZFAEGIW3PZFSRRWNZ5JKDGB","target":"record","payload":{"canonical_record":{"source":{"id":"2403.15112","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T11:08:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5585a7ea8e283f7d333b0e5c58ea1fc9d153a58886c89fa45da2d67b551c8129","abstract_canon_sha256":"215b27dca89ad953f889803710f9f129127bf5060fbb73f11e3056d17ee6cbb4"},"schema_version":"1.0"},"canonical_sha256":"a09f92808645b6fc96518d9b9ea5433064b87e59d10118a2fac39c94f04a5058","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:50.002849Z","signature_b64":"nTTybaL9L9MzGYLJ/Smc9RLcV8lEFPI5sGGr1CdhyaxxiiGfRyn/osmRRhPQW5ErzZOg/ZCBv/R1FVTORoQpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a09f92808645b6fc96518d9b9ea5433064b87e59d10118a2fac39c94f04a5058","last_reissued_at":"2026-07-05T09:44:50.002385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:50.002385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.15112","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gNKylMw7EvcIe6inDkmeQ3VdmnfHVaLPAOyIu//7Yc9GIP3EjFlYkCUevVaZyo6Tidj6dz1OTUKcL2cbE51UCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:46:03.487882Z"},"content_sha256":"dcc1d51615e4f488a281f41d48f0f6c4536a79a5fa392fb677238988833ec282","schema_version":"1.0","event_id":"sha256:dcc1d51615e4f488a281f41d48f0f6c4536a79a5fa392fb677238988833ec282"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UCPZFAEGIW3PZFSRRWNZ5JKDGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Clustering with Large Language Model Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alina Petukhova, Jo\\~ao P. Matos-Carvalho, Nuno Fachada","submitted_at":"2024-03-22T11:08:48Z","abstract_excerpt":"Text clustering is an important method for organising the increasing volume of digital content, aiding in the structuring and discovery of hidden patterns in uncategorised data. The effectiveness of text clustering largely depends on the selection of textual embeddings and clustering algorithms. This study argues that recent advancements in large language models (LLMs) have the potential to enhance this task. The research investigates how different textual embeddings, particularly those utilised in LLMs, and various clustering algorithms influence the clustering of text datasets. A series of e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15112","kind":"arxiv","version":5},"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/2403.15112/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":"2026-07-05T09:44:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s4/sJmcg8oRspU2kU7Z0s/PF3bJBneEZZ/xa35MaRGC4HEkIKucmrBxXXfKZaSlVa1G0zWyEThMt70VrxXNsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:46:03.488811Z"},"content_sha256":"aa30b306f381ba006062b4fa0a8fdb4efb2f9c069f3b235cae81009d0daea549","schema_version":"1.0","event_id":"sha256:aa30b306f381ba006062b4fa0a8fdb4efb2f9c069f3b235cae81009d0daea549"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UCPZFAEGIW3PZFSRRWNZ5JKDGB/bundle.json","state_url":"https://pith.science/pith/UCPZFAEGIW3PZFSRRWNZ5JKDGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UCPZFAEGIW3PZFSRRWNZ5JKDGB/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":"2026-08-09T15:46:03Z","links":{"resolver":"https://pith.science/pith/UCPZFAEGIW3PZFSRRWNZ5JKDGB","bundle":"https://pith.science/pith/UCPZFAEGIW3PZFSRRWNZ5JKDGB/bundle.json","state":"https://pith.science/pith/UCPZFAEGIW3PZFSRRWNZ5JKDGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UCPZFAEGIW3PZFSRRWNZ5JKDGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UCPZFAEGIW3PZFSRRWNZ5JKDGB","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":"215b27dca89ad953f889803710f9f129127bf5060fbb73f11e3056d17ee6cbb4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T11:08:48Z","title_canon_sha256":"5585a7ea8e283f7d333b0e5c58ea1fc9d153a58886c89fa45da2d67b551c8129"},"schema_version":"1.0","source":{"id":"2403.15112","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.15112","created_at":"2026-07-05T09:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.15112v5","created_at":"2026-07-05T09:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15112","created_at":"2026-07-05T09:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"UCPZFAEGIW3P","created_at":"2026-07-05T09:44:50Z"},{"alias_kind":"pith_short_16","alias_value":"UCPZFAEGIW3PZFSR","created_at":"2026-07-05T09:44:50Z"},{"alias_kind":"pith_short_8","alias_value":"UCPZFAEG","created_at":"2026-07-05T09:44:50Z"}],"graph_snapshots":[{"event_id":"sha256:aa30b306f381ba006062b4fa0a8fdb4efb2f9c069f3b235cae81009d0daea549","target":"graph","created_at":"2026-07-05T09:44:50Z","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/2403.15112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text clustering is an important method for organising the increasing volume of digital content, aiding in the structuring and discovery of hidden patterns in uncategorised data. The effectiveness of text clustering largely depends on the selection of textual embeddings and clustering algorithms. This study argues that recent advancements in large language models (LLMs) have the potential to enhance this task. The research investigates how different textual embeddings, particularly those utilised in LLMs, and various clustering algorithms influence the clustering of text datasets. A series of e","authors_text":"Alina Petukhova, Jo\\~ao P. Matos-Carvalho, Nuno Fachada","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T11:08:48Z","title":"Text Clustering with Large Language Model Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15112","kind":"arxiv","version":5},"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:dcc1d51615e4f488a281f41d48f0f6c4536a79a5fa392fb677238988833ec282","target":"record","created_at":"2026-07-05T09:44:50Z","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":"215b27dca89ad953f889803710f9f129127bf5060fbb73f11e3056d17ee6cbb4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T11:08:48Z","title_canon_sha256":"5585a7ea8e283f7d333b0e5c58ea1fc9d153a58886c89fa45da2d67b551c8129"},"schema_version":"1.0","source":{"id":"2403.15112","kind":"arxiv","version":5}},"canonical_sha256":"a09f92808645b6fc96518d9b9ea5433064b87e59d10118a2fac39c94f04a5058","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a09f92808645b6fc96518d9b9ea5433064b87e59d10118a2fac39c94f04a5058","first_computed_at":"2026-07-05T09:44:50.002385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:50.002385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nTTybaL9L9MzGYLJ/Smc9RLcV8lEFPI5sGGr1CdhyaxxiiGfRyn/osmRRhPQW5ErzZOg/ZCBv/R1FVTORoQpDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:50.002849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.15112","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcc1d51615e4f488a281f41d48f0f6c4536a79a5fa392fb677238988833ec282","sha256:aa30b306f381ba006062b4fa0a8fdb4efb2f9c069f3b235cae81009d0daea549"],"state_sha256":"59db2b4444a6c35f88c9e54f6e1ebbedeb1a5050521f379983db519e17940ec7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MTX0cdTDxXAwcn9mwR3dSqBcM7rPUkzFF35YbhDKhL9DN03KmhmuSxmh8bMHniK0XSGOrAyAQlTHl7QexV60DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:46:03.496254Z","bundle_sha256":"8f668345262bf2a3cb62b7ca23376a35e79e370b77f44b089830390f981850bd"}}