{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3AGUCINCMDFKKW4JOO5NKQ4SM3","short_pith_number":"pith:3AGUCINC","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"},"canonical_sha256":"d80d4121a260caa55b8973bad5439266c0154113a522f14f7ec44a0ee69acbbf","source":{"kind":"arxiv","id":"2605.30315","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30315","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30315v1","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30315","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"3AGUCINCMDFK","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"3AGUCINCMDFKKW4J","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"3AGUCINC","created_at":"2026-05-29T02:06:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3AGUCINCMDFKKW4JOO5NKQ4SM3","target":"record","payload":{"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"},"canonical_sha256":"d80d4121a260caa55b8973bad5439266c0154113a522f14f7ec44a0ee69acbbf","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"},"source_kind":"arxiv","source_id":"2605.30315","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V45B3JofRjh4pQhLu6KEbbKO785i7e8htwRcry/VSr5Yx7BzN5cYVf1Zd7jFVxmEfWVocLG7V+SCZn1Sj+PIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T07:22:55.480833Z"},"content_sha256":"b31f979179cb8d91b36a34c1e735bbaed23d7d6951e14027e3367dfe2ab5d3e8","schema_version":"1.0","event_id":"sha256:b31f979179cb8d91b36a34c1e735bbaed23d7d6951e14027e3367dfe2ab5d3e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3AGUCINCMDFKKW4JOO5NKQ4SM3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FHEJGmzCR+ocwZO3GizFTmRxoOfyC5TfiazdtJ+08UfivCf7LpHdJvMSzN4YgfgljjkTCVh5ncdN/N7+IXwdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T07:22:55.481200Z"},"content_sha256":"123158d1d000ccfbcfd2641877aef6bc37cb77a290421e66465cfbb0895aa46a","schema_version":"1.0","event_id":"sha256:123158d1d000ccfbcfd2641877aef6bc37cb77a290421e66465cfbb0895aa46a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3/bundle.json","state_url":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3/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":"2026-06-30T07:22:55Z","links":{"resolver":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3","bundle":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3/bundle.json","state":"https://pith.science/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3AGUCINCMDFKKW4JOO5NKQ4SM3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3AGUCINCMDFKKW4JOO5NKQ4SM3","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":"928aa7c4e8ccbaafed1ec166f2eba75b5a814c51c7359b3ba395409779712133","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:54:09Z","title_canon_sha256":"6565865ff12c42a195be3d2c7fd65c498ff406a341ad7a05344656e67c4e2459"},"schema_version":"1.0","source":{"id":"2605.30315","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30315","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30315v1","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30315","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"3AGUCINCMDFK","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"3AGUCINCMDFKKW4J","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"3AGUCINC","created_at":"2026-05-29T02:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:123158d1d000ccfbcfd2641877aef6bc37cb77a290421e66465cfbb0895aa46a","target":"graph","created_at":"2026-05-29T02:06:16Z","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/2605.30315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Anany Kotawala","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:54:09Z","title":"Resolution Diagnostics for Paired LLM Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30315","kind":"arxiv","version":1},"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:b31f979179cb8d91b36a34c1e735bbaed23d7d6951e14027e3367dfe2ab5d3e8","target":"record","created_at":"2026-05-29T02:06:16Z","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":"928aa7c4e8ccbaafed1ec166f2eba75b5a814c51c7359b3ba395409779712133","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:54:09Z","title_canon_sha256":"6565865ff12c42a195be3d2c7fd65c498ff406a341ad7a05344656e67c4e2459"},"schema_version":"1.0","source":{"id":"2605.30315","kind":"arxiv","version":1}},"canonical_sha256":"d80d4121a260caa55b8973bad5439266c0154113a522f14f7ec44a0ee69acbbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d80d4121a260caa55b8973bad5439266c0154113a522f14f7ec44a0ee69acbbf","first_computed_at":"2026-05-29T02:06:16.245655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:16.245655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jda5WD3EAjQBwRk5HhQyPi2vy+jDBXFi+LpqhvKDK4+GSnDS0owuyCUOyVbLAaxKATHJT6dwXR66WoGjEtt0DQ==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:16.246020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30315","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b31f979179cb8d91b36a34c1e735bbaed23d7d6951e14027e3367dfe2ab5d3e8","sha256:123158d1d000ccfbcfd2641877aef6bc37cb77a290421e66465cfbb0895aa46a"],"state_sha256":"094c5d8107efb46b7ed1cac08cab0676f9f599e7160cb6bab8c1f234e1187737"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YwJSdRBUgK7dkVUkP6lwmKJFs6xoh79XGVZCYyyGDm/8hjWNj17lFxYLIMoK8ISisOWUOzP9wJz7bDtAsLMFAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T07:22:55.483247Z","bundle_sha256":"94cbf4f01ec07a4de22a7bf4b627dde9560d940096f1e85cd6803c7fd8e47308"}}