{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BOUSXS2SP4QUXN3JFQKUC4MQ4M","short_pith_number":"pith:BOUSXS2S","schema_version":"1.0","canonical_sha256":"0ba92bcb527f214bb7692c15417190e30aa97135bd09431ab471cf77e2887cfe","source":{"kind":"arxiv","id":"2506.18082","version":2},"attestation_state":"computed","paper":{"title":"Statistical Multicriteria Evaluation of LLM-Generated Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.CL","authors_text":"Christoph Jansen, Esteban Garces Arias, Hannah Blocher, Julian Rodemann, Matthias A{\\ss}enmacher","submitted_at":"2025-06-22T16:08:44Z","abstract_excerpt":"Assessing the quality of LLM-generated text remains a fundamental challenge in natural language processing. Current evaluation approaches often rely on isolated metrics or simplistic aggregations that fail to capture the nuanced trade-offs between coherence, diversity, fluency, and other relevant indicators of text quality. In this work, we adapt a recently proposed framework for statistical inference based on Generalized Stochastic Dominance (GSD) that addresses three critical limitations in existing benchmarking methodologies: the inadequacy of single-metric evaluation, the incompatibility b"},"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":"2506.18082","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-22T16:08:44Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"437a9e97c6513aab96ed5e2db83eb587dc595f0f556f6826863d742824911608","abstract_canon_sha256":"336b196c1c98f8b3f27e51c7407461a54ccc4626502d1aba01a7f4fe9f8d99ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:06.130644Z","signature_b64":"uKgudZV+OhfWxxDReAJusmL/1OIzZ98lI9lB5V9S0TsL2AjF2InLaPCJKfLNm9AnNbULfMO8p2pSU2KwW6kNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ba92bcb527f214bb7692c15417190e30aa97135bd09431ab471cf77e2887cfe","last_reissued_at":"2026-07-05T11:26:06.130157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:06.130157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Multicriteria Evaluation of LLM-Generated Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.CL","authors_text":"Christoph Jansen, Esteban Garces Arias, Hannah Blocher, Julian Rodemann, Matthias A{\\ss}enmacher","submitted_at":"2025-06-22T16:08:44Z","abstract_excerpt":"Assessing the quality of LLM-generated text remains a fundamental challenge in natural language processing. Current evaluation approaches often rely on isolated metrics or simplistic aggregations that fail to capture the nuanced trade-offs between coherence, diversity, fluency, and other relevant indicators of text quality. In this work, we adapt a recently proposed framework for statistical inference based on Generalized Stochastic Dominance (GSD) that addresses three critical limitations in existing benchmarking methodologies: the inadequacy of single-metric evaluation, the incompatibility b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18082","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/2506.18082/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":"2506.18082","created_at":"2026-07-05T11:26:06.130215+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18082v2","created_at":"2026-07-05T11:26:06.130215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18082","created_at":"2026-07-05T11:26:06.130215+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOUSXS2SP4QU","created_at":"2026-07-05T11:26:06.130215+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOUSXS2SP4QUXN3J","created_at":"2026-07-05T11:26:06.130215+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOUSXS2S","created_at":"2026-07-05T11:26:06.130215+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12208","citing_title":"Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BOUSXS2SP4QUXN3JFQKUC4MQ4M","json":"https://pith.science/pith/BOUSXS2SP4QUXN3JFQKUC4MQ4M.json","graph_json":"https://pith.science/api/pith-number/BOUSXS2SP4QUXN3JFQKUC4MQ4M/graph.json","events_json":"https://pith.science/api/pith-number/BOUSXS2SP4QUXN3JFQKUC4MQ4M/events.json","paper":"https://pith.science/paper/BOUSXS2S"},"agent_actions":{"view_html":"https://pith.science/pith/BOUSXS2SP4QUXN3JFQKUC4MQ4M","download_json":"https://pith.science/pith/BOUSXS2SP4QUXN3JFQKUC4MQ4M.json","view_paper":"https://pith.science/paper/BOUSXS2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18082&json=true","fetch_graph":"https://pith.science/api/pith-number/BOUSXS2SP4QUXN3JFQKUC4MQ4M/graph.json","fetch_events":"https://pith.science/api/pith-number/BOUSXS2SP4QUXN3JFQKUC4MQ4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOUSXS2SP4QUXN3JFQKUC4MQ4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOUSXS2SP4QUXN3JFQKUC4MQ4M/action/storage_attestation","attest_author":"https://pith.science/pith/BOUSXS2SP4QUXN3JFQKUC4MQ4M/action/author_attestation","sign_citation":"https://pith.science/pith/BOUSXS2SP4QUXN3JFQKUC4MQ4M/action/citation_signature","submit_replication":"https://pith.science/pith/BOUSXS2SP4QUXN3JFQKUC4MQ4M/action/replication_record"}},"created_at":"2026-07-05T11:26:06.130215+00:00","updated_at":"2026-07-05T11:26:06.130215+00:00"}