{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RTHG62JYLCOPUHJQPBANFHPB5K","short_pith_number":"pith:RTHG62JY","schema_version":"1.0","canonical_sha256":"8cce6f6938589cfa1d307840d29de1eaa1d3a7ac18c051e566b6113258316b2a","source":{"kind":"arxiv","id":"2503.12108","version":1},"attestation_state":"computed","paper":{"title":"RECSIP: REpeated Clustering of Scores Improving the Precision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alois Christian Knoll, Andr\\'e Schamschurko, Nenad Petrovic","submitted_at":"2025-03-15T12:36:32Z","abstract_excerpt":"The latest research on Large Language Models (LLMs) has demonstrated significant advancement in the field of Natural Language Processing (NLP). However, despite this progress, there is still a lack of reliability in these models. This is due to the stochastic architecture of LLMs, which presents a challenge for users attempting to ascertain the reliability of a model's response. These responses may cause serious harm in high-risk environments or expensive failures in industrial contexts. Therefore, we introduce the framework REpeated Clustering of Scores Improving the Precision (RECSIP) which "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.12108","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-15T12:36:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e9d02c6a457c5af57dbf8e8751b2a9d54207d377e9d9a7ce8092ddce51473bc0","abstract_canon_sha256":"8d46500157672f1294b435e7c937beeecf30209c02e96e4cd992ef0062fd8471"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:05.660490Z","signature_b64":"WY2841exwcZRYWZHPyzOAsJlaad3zOZQImfN3Pdksujx1BdyQly0db2o44Bj11fbIW7azpcoSizf8am9bfq/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cce6f6938589cfa1d307840d29de1eaa1d3a7ac18c051e566b6113258316b2a","last_reissued_at":"2026-07-05T10:32:05.659989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:05.659989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RECSIP: REpeated Clustering of Scores Improving the Precision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alois Christian Knoll, Andr\\'e Schamschurko, Nenad Petrovic","submitted_at":"2025-03-15T12:36:32Z","abstract_excerpt":"The latest research on Large Language Models (LLMs) has demonstrated significant advancement in the field of Natural Language Processing (NLP). However, despite this progress, there is still a lack of reliability in these models. This is due to the stochastic architecture of LLMs, which presents a challenge for users attempting to ascertain the reliability of a model's response. These responses may cause serious harm in high-risk environments or expensive failures in industrial contexts. Therefore, we introduce the framework REpeated Clustering of Scores Improving the Precision (RECSIP) which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12108","kind":"arxiv","version":1},"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/2503.12108/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.12108","created_at":"2026-07-05T10:32:05.660046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12108v1","created_at":"2026-07-05T10:32:05.660046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12108","created_at":"2026-07-05T10:32:05.660046+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTHG62JYLCOP","created_at":"2026-07-05T10:32:05.660046+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTHG62JYLCOPUHJQ","created_at":"2026-07-05T10:32:05.660046+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTHG62JY","created_at":"2026-07-05T10:32:05.660046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18223","citing_title":"GenAI for Automotive Software Development: From Requirements to Wheels","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTHG62JYLCOPUHJQPBANFHPB5K","json":"https://pith.science/pith/RTHG62JYLCOPUHJQPBANFHPB5K.json","graph_json":"https://pith.science/api/pith-number/RTHG62JYLCOPUHJQPBANFHPB5K/graph.json","events_json":"https://pith.science/api/pith-number/RTHG62JYLCOPUHJQPBANFHPB5K/events.json","paper":"https://pith.science/paper/RTHG62JY"},"agent_actions":{"view_html":"https://pith.science/pith/RTHG62JYLCOPUHJQPBANFHPB5K","download_json":"https://pith.science/pith/RTHG62JYLCOPUHJQPBANFHPB5K.json","view_paper":"https://pith.science/paper/RTHG62JY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12108&json=true","fetch_graph":"https://pith.science/api/pith-number/RTHG62JYLCOPUHJQPBANFHPB5K/graph.json","fetch_events":"https://pith.science/api/pith-number/RTHG62JYLCOPUHJQPBANFHPB5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTHG62JYLCOPUHJQPBANFHPB5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTHG62JYLCOPUHJQPBANFHPB5K/action/storage_attestation","attest_author":"https://pith.science/pith/RTHG62JYLCOPUHJQPBANFHPB5K/action/author_attestation","sign_citation":"https://pith.science/pith/RTHG62JYLCOPUHJQPBANFHPB5K/action/citation_signature","submit_replication":"https://pith.science/pith/RTHG62JYLCOPUHJQPBANFHPB5K/action/replication_record"}},"created_at":"2026-07-05T10:32:05.660046+00:00","updated_at":"2026-07-05T10:32:05.660046+00:00"}