{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6AESUCV3Y4TZPLW4FRNJOIK3YR","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":"514e8570592994e1fc3843c241ce1ef8725664b8b04d4ddfb426ddf521e1e630","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T12:26:54Z","title_canon_sha256":"1cd378b574a3790c8589463a5027a113a4b81cdfe8162749e3974e087031094d"},"schema_version":"1.0","source":{"id":"2606.09409","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09409","created_at":"2026-06-09T02:08:46Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09409v1","created_at":"2026-06-09T02:08:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09409","created_at":"2026-06-09T02:08:46Z"},{"alias_kind":"pith_short_12","alias_value":"6AESUCV3Y4TZ","created_at":"2026-06-09T02:08:46Z"},{"alias_kind":"pith_short_16","alias_value":"6AESUCV3Y4TZPLW4","created_at":"2026-06-09T02:08:46Z"},{"alias_kind":"pith_short_8","alias_value":"6AESUCV3","created_at":"2026-06-09T02:08:46Z"}],"graph_snapshots":[{"event_id":"sha256:4df2c5defc4030ded01d28277713cbab0b94444b5d6b203a58a2b0afeed40287","target":"graph","created_at":"2026-06-09T02:08:46Z","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/2606.09409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pairwise comparisons combined with aggregation methods like Elo have become central to evaluating generative models, yet concerns remain that they reward superficial stylistic cues or display judge biases. In a more positive turn, we show that model rankings from pairwise comparisons strongly agree with ground-truth-based accuracy rankings when such ground truth is available for comparison. By converting five well-known benchmarks into free-form generative evaluations, we find that Elo rankings achieve a Spearman correlation above 0.9 with accuracy rankings and substantially outperform direct ","authors_text":"Mina Remeli, Moritz Hardt","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T12:26:54Z","title":"Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09409","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":"sha256:4f3c4fc7a2b0e6d5e06358affaf0614946f5126e517c1ef8fe2aa07d6934c09f","target":"record","created_at":"2026-06-09T02:08:46Z","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":"514e8570592994e1fc3843c241ce1ef8725664b8b04d4ddfb426ddf521e1e630","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T12:26:54Z","title_canon_sha256":"1cd378b574a3790c8589463a5027a113a4b81cdfe8162749e3974e087031094d"},"schema_version":"1.0","source":{"id":"2606.09409","kind":"arxiv","version":1}},"canonical_sha256":"f0092a0abbc72797aedc2c5a97215bc46c3b69b4bb1e4093fc8b8ba7bdadb267","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0092a0abbc72797aedc2c5a97215bc46c3b69b4bb1e4093fc8b8ba7bdadb267","first_computed_at":"2026-06-09T02:08:46.644504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:46.644504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6d2twoYt9ZKGZ6zDTlDp9/0/iCEDuGWHOVy5xYNK9F4EJiBe/Gs5s+dS0C1ghVxGKkP4AGMl0EdAuDg5Ma8qDg==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:46.645561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09409","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f3c4fc7a2b0e6d5e06358affaf0614946f5126e517c1ef8fe2aa07d6934c09f","sha256:4df2c5defc4030ded01d28277713cbab0b94444b5d6b203a58a2b0afeed40287"],"state_sha256":"58d7310e42e173bcdde39a701aeafb9dc7bd62b36ce642d61565791a6cabebe1"}