{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3AGUCINCMDFKKW4JOO5NKQ4SM3","short_pith_number":"pith:3AGUCINC","schema_version":"1.0","canonical_sha256":"d80d4121a260caa55b8973bad5439266c0154113a522f14f7ec44a0ee69acbbf","source":{"kind":"arxiv","id":"2605.30315","version":1},"attestation_state":"computed","paper":{"title":"Resolution Diagnostics for Paired LLM Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anany Kotawala","submitted_at":"2026-05-28T17:54:09Z","abstract_excerpt":"Across two public LLM leaderboards, many displayed pairwise rankings do not meet a conventional paired-test resolution target under the actual paired evaluation design: 11 of 40 Open LLM Leaderboard v1 pairwise comparisons and 4 of 9 MMLU-Pro top-10 adjacent-rank pairs are unresolved at (alpha, 1-beta) = (0.05, 0.8). The MMLU-Pro count rises to 6/9 under real subject-level clustering and stays at 5-6 out of 9 in 99.9% of category-bootstrap resamples. We frame paired LLM evaluation as a hypothesis-testing problem, invert level-alpha, power-(1-beta) tests, and report a per-pair resolution ratio "},"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":"2605.30315","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:54:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6565865ff12c42a195be3d2c7fd65c498ff406a341ad7a05344656e67c4e2459","abstract_canon_sha256":"928aa7c4e8ccbaafed1ec166f2eba75b5a814c51c7359b3ba395409779712133"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:16.246020Z","signature_b64":"Jda5WD3EAjQBwRk5HhQyPi2vy+jDBXFi+LpqhvKDK4+GSnDS0owuyCUOyVbLAaxKATHJT6dwXR66WoGjEtt0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d80d4121a260caa55b8973bad5439266c0154113a522f14f7ec44a0ee69acbbf","last_reissued_at":"2026-05-29T02:06:16.245655Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:16.245655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Resolution Diagnostics for Paired LLM Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anany Kotawala","submitted_at":"2026-05-28T17:54:09Z","abstract_excerpt":"Across two public LLM leaderboards, many displayed pairwise rankings do not meet a conventional paired-test resolution target under the actual paired evaluation design: 11 of 40 Open LLM Leaderboard v1 pairwise comparisons and 4 of 9 MMLU-Pro top-10 adjacent-rank pairs are unresolved at (alpha, 1-beta) = (0.05, 0.8). The MMLU-Pro count rises to 6/9 under real subject-level clustering and stays at 5-6 out of 9 in 99.9% of category-bootstrap resamples. We frame paired LLM evaluation as a hypothesis-testing problem, invert level-alpha, power-(1-beta) tests, and report a per-pair resolution ratio "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30315","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/2605.30315/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":"2605.30315","created_at":"2026-05-29T02:06:16.245721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30315v1","created_at":"2026-05-29T02:06:16.245721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30315","created_at":"2026-05-29T02:06:16.245721+00:00"},{"alias_kind":"pith_short_12","alias_value":"3AGUCINCMDFK","created_at":"2026-05-29T02:06:16.245721+00:00"},{"alias_kind":"pith_short_16","alias_value":"3AGUCINCMDFKKW4J","created_at":"2026-05-29T02:06:16.245721+00:00"},{"alias_kind":"pith_short_8","alias_value":"3AGUCINC","created_at":"2026-05-29T02:06:16.245721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3","json":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3.json","graph_json":"https://pith.science/api/pith-number/3AGUCINCMDFKKW4JOO5NKQ4SM3/graph.json","events_json":"https://pith.science/api/pith-number/3AGUCINCMDFKKW4JOO5NKQ4SM3/events.json","paper":"https://pith.science/paper/3AGUCINC"},"agent_actions":{"view_html":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3","download_json":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3.json","view_paper":"https://pith.science/paper/3AGUCINC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30315&json=true","fetch_graph":"https://pith.science/api/pith-number/3AGUCINCMDFKKW4JOO5NKQ4SM3/graph.json","fetch_events":"https://pith.science/api/pith-number/3AGUCINCMDFKKW4JOO5NKQ4SM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3/action/storage_attestation","attest_author":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3/action/author_attestation","sign_citation":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3/action/citation_signature","submit_replication":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3/action/replication_record"}},"created_at":"2026-05-29T02:06:16.245721+00:00","updated_at":"2026-05-29T02:06:16.245721+00:00"}