{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XUFABNZGZ5HWN474ALWZRDJ33G","short_pith_number":"pith:XUFABNZG","schema_version":"1.0","canonical_sha256":"bd0a00b726cf4f66f3fc02ed988d3bd9b6a60fdacec8f84b403f4981d67c220b","source":{"kind":"arxiv","id":"2606.02093","version":1},"attestation_state":"computed","paper":{"title":"The Role of Ambiguity in Error Prediction via Uncertainty Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andreas Vlachos, Ieva Raminta Stali\\=unait\\.e, James Bishop","submitted_at":"2026-06-01T11:20:57Z","abstract_excerpt":"The task of Error Prediction, namely predicting whether a model output is correct, is commonly tackled with Uncertainty Quantification (UQ). However, while uncertainty metrics capture when models lack knowledge or capacity to make a prediction, they also reflect aleatoric uncertainty, which is inherent in the model input and context. This paper presents a method for improving error prediction for Large Language Models (LLMs), by disentangling input ambiguity from UQ signal. We conduct experiments on the task of Question Answering (QA) with six UQ metrics and show that UQ metrics are more predi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.02093","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T11:20:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cb11e2c9992e59bc06b5690875b647be57e5eda2005759fdb9094d2c7bb0650b","abstract_canon_sha256":"a5ae84e2d231c63e8d2d8a09f64cafa63108938a570511f28b1a14e1a16fd4e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:06.361139Z","signature_b64":"qSuahEOsKV3wsemmWy1qAwj2kINDoqr1L7tkqOOazOLx14DR0n9TOwrcl5oZlJZrE0hPDRACbJLkrTXKBsHBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd0a00b726cf4f66f3fc02ed988d3bd9b6a60fdacec8f84b403f4981d67c220b","last_reissued_at":"2026-06-02T02:05:06.360790Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:06.360790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Role of Ambiguity in Error Prediction via Uncertainty Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andreas Vlachos, Ieva Raminta Stali\\=unait\\.e, James Bishop","submitted_at":"2026-06-01T11:20:57Z","abstract_excerpt":"The task of Error Prediction, namely predicting whether a model output is correct, is commonly tackled with Uncertainty Quantification (UQ). However, while uncertainty metrics capture when models lack knowledge or capacity to make a prediction, they also reflect aleatoric uncertainty, which is inherent in the model input and context. This paper presents a method for improving error prediction for Large Language Models (LLMs), by disentangling input ambiguity from UQ signal. We conduct experiments on the task of Question Answering (QA) with six UQ metrics and show that UQ metrics are more predi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02093","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/2606.02093/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.02093","created_at":"2026-06-02T02:05:06.360842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02093v1","created_at":"2026-06-02T02:05:06.360842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02093","created_at":"2026-06-02T02:05:06.360842+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUFABNZGZ5HW","created_at":"2026-06-02T02:05:06.360842+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUFABNZGZ5HWN474","created_at":"2026-06-02T02:05:06.360842+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUFABNZG","created_at":"2026-06-02T02:05:06.360842+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XUFABNZGZ5HWN474ALWZRDJ33G","json":"https://pith.science/pith/XUFABNZGZ5HWN474ALWZRDJ33G.json","graph_json":"https://pith.science/api/pith-number/XUFABNZGZ5HWN474ALWZRDJ33G/graph.json","events_json":"https://pith.science/api/pith-number/XUFABNZGZ5HWN474ALWZRDJ33G/events.json","paper":"https://pith.science/paper/XUFABNZG"},"agent_actions":{"view_html":"https://pith.science/pith/XUFABNZGZ5HWN474ALWZRDJ33G","download_json":"https://pith.science/pith/XUFABNZGZ5HWN474ALWZRDJ33G.json","view_paper":"https://pith.science/paper/XUFABNZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02093&json=true","fetch_graph":"https://pith.science/api/pith-number/XUFABNZGZ5HWN474ALWZRDJ33G/graph.json","fetch_events":"https://pith.science/api/pith-number/XUFABNZGZ5HWN474ALWZRDJ33G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUFABNZGZ5HWN474ALWZRDJ33G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUFABNZGZ5HWN474ALWZRDJ33G/action/storage_attestation","attest_author":"https://pith.science/pith/XUFABNZGZ5HWN474ALWZRDJ33G/action/author_attestation","sign_citation":"https://pith.science/pith/XUFABNZGZ5HWN474ALWZRDJ33G/action/citation_signature","submit_replication":"https://pith.science/pith/XUFABNZGZ5HWN474ALWZRDJ33G/action/replication_record"}},"created_at":"2026-06-02T02:05:06.360842+00:00","updated_at":"2026-06-02T02:05:06.360842+00:00"}