{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SG7QGOHJKP43OFU3GF4X5NGFKH","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":"67031cf32f814fbc2341736ffb53d0d4c2c74a22c58ed6082f099380382cc902","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T22:40:46Z","title_canon_sha256":"61f770c219474f290fb25f78844fecee59034d1e65a309b98ec07639d54f8cec"},"schema_version":"1.0","source":{"id":"2606.26429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26429","created_at":"2026-06-26T00:15:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26429v1","created_at":"2026-06-26T00:15:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26429","created_at":"2026-06-26T00:15:40Z"},{"alias_kind":"pith_short_12","alias_value":"SG7QGOHJKP43","created_at":"2026-06-26T00:15:40Z"},{"alias_kind":"pith_short_16","alias_value":"SG7QGOHJKP43OFU3","created_at":"2026-06-26T00:15:40Z"},{"alias_kind":"pith_short_8","alias_value":"SG7QGOHJ","created_at":"2026-06-26T00:15:40Z"}],"graph_snapshots":[{"event_id":"sha256:4483cd295fb9b6a552164696540aeb40572b74cc5fc918ee2483587fe061105d","target":"graph","created_at":"2026-06-26T00:15:40Z","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/2606.26429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current LLM evaluation relies on two complementary but often disconnected signals: static benchmarks with objective correctness labels and arena-style preference data that better reflect open-ended user interactions. We introduce DualEval, a latent model-item calibration framework that represents models and evaluation items in a shared space, jointly estimating model ability together with item difficulty and sharpness. We apply DualEval across four domains: coding, math, miscellaneous domain-knowledge tasks, and generic everyday user queries. Our evaluation uses 18 frontier LLMs, static benchm","authors_text":"Aaron J. Li, Bin Yu, Cho-Jui Hsieh, Hao Huang, Ion Stoica, Li Chen, Wei-Lin Chiang, Yitong Ma, Youngmin Park","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T22:40:46Z","title":"DualEval: Joint Model-Item Calibration for Unified LLM Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26429","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":"sha256:65bb7534113549587c5283a85d583d6f3faef86c791e5d9f220552c2090f716c","target":"record","created_at":"2026-06-26T00:15:40Z","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":"67031cf32f814fbc2341736ffb53d0d4c2c74a22c58ed6082f099380382cc902","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T22:40:46Z","title_canon_sha256":"61f770c219474f290fb25f78844fecee59034d1e65a309b98ec07639d54f8cec"},"schema_version":"1.0","source":{"id":"2606.26429","kind":"arxiv","version":1}},"canonical_sha256":"91bf0338e953f9b7169b31797eb4c551f7e654a637bcef2530e7ca9a4ee68a71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91bf0338e953f9b7169b31797eb4c551f7e654a637bcef2530e7ca9a4ee68a71","first_computed_at":"2026-06-26T00:15:40.689930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T00:15:40.689930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DfhKRSU/0Rcg632QCbwiiHYBxv7QemApwhHIfZpmZ0gXRcbaocUqWfPhoecFZ1yQ8KNViKQMDFlz3/Qt5STzAQ==","signature_status":"signed_v1","signed_at":"2026-06-26T00:15:40.690358Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65bb7534113549587c5283a85d583d6f3faef86c791e5d9f220552c2090f716c","sha256:4483cd295fb9b6a552164696540aeb40572b74cc5fc918ee2483587fe061105d"],"state_sha256":"909e69d45ab47773ec3549c7100be5ec12e43992fd4c0b979903300b7bb16d16"}