{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:S2G7ZYJ6MGAHQQR7VTWM5DHM7D","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":"92a57e169427c29d434fad970bf746f5842675d7c4a8bc6c220fd02b2a957f35","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T13:13:42Z","title_canon_sha256":"22a999838a7ff3d3a85cc88103ae5faa4dd4310f3b2bd8894ab789cae9fa8378"},"schema_version":"1.0","source":{"id":"2504.13677","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13677","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13677v2","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13677","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"S2G7ZYJ6MGAH","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_16","alias_value":"S2G7ZYJ6MGAHQQR7","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_8","alias_value":"S2G7ZYJ6","created_at":"2026-07-05T11:50:34Z"}],"graph_snapshots":[{"event_id":"sha256:2fc9d923db250c7530e14b24e4da3d3c764a5f1dee57dd4e570c40006ca8fa48","target":"graph","created_at":"2026-07-05T11:50:34Z","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/2504.13677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Uncertainty Quantification (UQ) in Language Models (LMs) is key to improving their safety and reliability. Evaluations often use metrics like AUROC to assess how well UQ methods (e.g., negative sequence probabilities) correlate with task correctness functions (e.g., ROUGE-L). We show that mutual biases--when both UQ methods and correctness functions are biased by the same factors--systematically distort evaluation. First, we formally prove that any mutual bias non-randomly skews AUROC rankings, compromising benchmark integrity. Second, we confirm this happens empirically by testing 7 widely us","authors_text":"Adam Golinski, Andrea Santilli, Arno Blaas, Federico Danieli, Luca Zappella, Miao Xiong, Michael Kirchhof, Sinead Williamson","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T13:13:42Z","title":"Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13677","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:b828dd22ded7d3e143c25746ca0a13b360004b49ca698387e4fd189923313cd6","target":"record","created_at":"2026-07-05T11:50:34Z","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":"92a57e169427c29d434fad970bf746f5842675d7c4a8bc6c220fd02b2a957f35","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T13:13:42Z","title_canon_sha256":"22a999838a7ff3d3a85cc88103ae5faa4dd4310f3b2bd8894ab789cae9fa8378"},"schema_version":"1.0","source":{"id":"2504.13677","kind":"arxiv","version":2}},"canonical_sha256":"968dfce13e618078423facecce8cecf8dbfd08c84f758d5c255c65d3fe083e7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"968dfce13e618078423facecce8cecf8dbfd08c84f758d5c255c65d3fe083e7a","first_computed_at":"2026-07-05T11:50:34.927032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:34.927032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nBrYp6kE/3AujcbLqAAvgyPBwNZr9PwiBhrCoWEtE0ZZEmdjukTlk1Vdo00hBgpXRozLkI0zdrZx5cE00bW7Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:34.927490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13677","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b828dd22ded7d3e143c25746ca0a13b360004b49ca698387e4fd189923313cd6","sha256:2fc9d923db250c7530e14b24e4da3d3c764a5f1dee57dd4e570c40006ca8fa48"],"state_sha256":"707a557a1128f2fde704cda3568be50856cbdbca9c36bad681179177873656d3"}