{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DNA765IEGSFWW3NIYUV5R3RQXU","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":"2ae2962d0313ad938c0b2acf24444cedf5ff95be71ad54972f1043bc0dc855a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T15:00:07Z","title_canon_sha256":"79d3788b2b873538cf0e9ea207a1c6b9368d0d3cd0b1f2540dc561d6d6a96599"},"schema_version":"1.0","source":{"id":"2601.21816","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21816","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21816v2","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21816","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"DNA765IEGSFW","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"DNA765IEGSFWW3NI","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"DNA765IE","created_at":"2026-06-09T01:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:0b029597b38ef6397f88f9bafc43abf1318f39e957462b7176365742a9b6b40f","target":"graph","created_at":"2026-06-09T01:05:13Z","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/2601.21816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the performance of large language models (LLMs) from human preference data is crucial for obtaining LLM leaderboards. However, many existing approaches either rely on restrictive parametric assumptions or lack valid uncertainty quantification when flexible machine learning methods are used. In this paper, we propose a nonparametric statistical framework, called DMLRank, for comparing and ranking LLMs from preference data using debiased machine learning (DML). For this, we introduce generalized average ranking scores (GARS), which generalize commonly used ranking models, including th","authors_text":"Athiya Deviyani, Dennis Frauen, Mihaela van der Schaar, Stefan Feuerriegel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T15:00:07Z","title":"Nonparametric LLM Evaluation from Preference Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21816","kind":"arxiv","version":2},"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:f09f137a75c914c9ea4f93b6359cb7900b37cb27b06c47964f8c7d551d28ecb6","target":"record","created_at":"2026-06-09T01:05:13Z","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":"2ae2962d0313ad938c0b2acf24444cedf5ff95be71ad54972f1043bc0dc855a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T15:00:07Z","title_canon_sha256":"79d3788b2b873538cf0e9ea207a1c6b9368d0d3cd0b1f2540dc561d6d6a96599"},"schema_version":"1.0","source":{"id":"2601.21816","kind":"arxiv","version":2}},"canonical_sha256":"1b41ff7504348b6b6da8c52bd8ee30bd3d80fabce7a1b6f91b31087067c8917d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b41ff7504348b6b6da8c52bd8ee30bd3d80fabce7a1b6f91b31087067c8917d","first_computed_at":"2026-06-09T01:05:13.376927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:13.376927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"98YEAzw8kBjr7NEWcnrmsfgiRbRDlmYfjw5NyuYerUBjXzSOIYpgYuI5IrqeDgQHh6Mj/1vd9o4i+j7K+TDrAQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:13.377491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21816","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f09f137a75c914c9ea4f93b6359cb7900b37cb27b06c47964f8c7d551d28ecb6","sha256:0b029597b38ef6397f88f9bafc43abf1318f39e957462b7176365742a9b6b40f"],"state_sha256":"7dc901e981cb2b1855d93bd1ec8ddff03bd706f6b9bb01e1d39d3b884a5221a3"}