{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LWEO7MB3FCIHY4CRLYHQN62DBB","short_pith_number":"pith:LWEO7MB3","schema_version":"1.0","canonical_sha256":"5d88efb03b28907c70515e0f06fb4308643bb07763793c3b5b8132db5fb649a6","source":{"kind":"arxiv","id":"2403.15250","version":2},"attestation_state":"computed","paper":{"title":"Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anders S{\\o}gaard, Kun Sun, Rong Wang","submitted_at":"2024-03-22T14:47:35Z","abstract_excerpt":"Amidst the rapid evolution of LLMs, the significance of evaluation in comprehending and propelling these models forward is increasingly paramount. Evaluations have revealed that factors such as scaling, training types, architectures and other factors profoundly impact the performance of LLMs. However, the extent and nature of these impacts continue to be subjects of debate because most assessments have been restricted to a limited number of models and data points. Clarifying the effects of these factors on performance scores can be more effectively achieved through a statistical lens. Our stud"},"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":"2403.15250","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T14:47:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bdf2cf0369911d15562f5e9e8ea9d9056408a3f6a580b64ec733efae33f93db8","abstract_canon_sha256":"171277538857b152f76088ac437e8ec362a970426dd4fb7455c987a64b65622e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:44.623364Z","signature_b64":"Gpn4lEsv+GYThVmoTUWQ8w97sm3ywqBGJ//QeblCYu4OlsCEOMxMAWm/yo7m96+QnTMT8nJgc61Crm/4dUyJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d88efb03b28907c70515e0f06fb4308643bb07763793c3b5b8132db5fb649a6","last_reissued_at":"2026-07-05T08:35:44.622877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:44.622877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anders S{\\o}gaard, Kun Sun, Rong Wang","submitted_at":"2024-03-22T14:47:35Z","abstract_excerpt":"Amidst the rapid evolution of LLMs, the significance of evaluation in comprehending and propelling these models forward is increasingly paramount. Evaluations have revealed that factors such as scaling, training types, architectures and other factors profoundly impact the performance of LLMs. However, the extent and nature of these impacts continue to be subjects of debate because most assessments have been restricted to a limited number of models and data points. Clarifying the effects of these factors on performance scores can be more effectively achieved through a statistical lens. Our stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15250","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/2403.15250/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":"2403.15250","created_at":"2026-07-05T08:35:44.622936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15250v2","created_at":"2026-07-05T08:35:44.622936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15250","created_at":"2026-07-05T08:35:44.622936+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWEO7MB3FCIH","created_at":"2026-07-05T08:35:44.622936+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWEO7MB3FCIHY4CR","created_at":"2026-07-05T08:35:44.622936+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWEO7MB3","created_at":"2026-07-05T08:35:44.622936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18213","citing_title":"A Conceptual Framework for AI Capability Evaluations","ref_index":86,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWEO7MB3FCIHY4CRLYHQN62DBB","json":"https://pith.science/pith/LWEO7MB3FCIHY4CRLYHQN62DBB.json","graph_json":"https://pith.science/api/pith-number/LWEO7MB3FCIHY4CRLYHQN62DBB/graph.json","events_json":"https://pith.science/api/pith-number/LWEO7MB3FCIHY4CRLYHQN62DBB/events.json","paper":"https://pith.science/paper/LWEO7MB3"},"agent_actions":{"view_html":"https://pith.science/pith/LWEO7MB3FCIHY4CRLYHQN62DBB","download_json":"https://pith.science/pith/LWEO7MB3FCIHY4CRLYHQN62DBB.json","view_paper":"https://pith.science/paper/LWEO7MB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15250&json=true","fetch_graph":"https://pith.science/api/pith-number/LWEO7MB3FCIHY4CRLYHQN62DBB/graph.json","fetch_events":"https://pith.science/api/pith-number/LWEO7MB3FCIHY4CRLYHQN62DBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWEO7MB3FCIHY4CRLYHQN62DBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWEO7MB3FCIHY4CRLYHQN62DBB/action/storage_attestation","attest_author":"https://pith.science/pith/LWEO7MB3FCIHY4CRLYHQN62DBB/action/author_attestation","sign_citation":"https://pith.science/pith/LWEO7MB3FCIHY4CRLYHQN62DBB/action/citation_signature","submit_replication":"https://pith.science/pith/LWEO7MB3FCIHY4CRLYHQN62DBB/action/replication_record"}},"created_at":"2026-07-05T08:35:44.622936+00:00","updated_at":"2026-07-05T08:35:44.622936+00:00"}