{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GD2EAQHVBB7V4BLZD4IBSF7QO4","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":"667fe27356832b6e2c00205944678c87443817b09e2282dd59900959cca38767","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T14:25:09Z","title_canon_sha256":"d2d4916ee0bec59bdbf3484614945ef3cc76aaff56dbe42d8dbc6b5b4a5a5f1a"},"schema_version":"1.0","source":{"id":"2607.06327","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06327","created_at":"2026-07-08T01:19:21Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06327v1","created_at":"2026-07-08T01:19:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06327","created_at":"2026-07-08T01:19:21Z"},{"alias_kind":"pith_short_12","alias_value":"GD2EAQHVBB7V","created_at":"2026-07-08T01:19:21Z"},{"alias_kind":"pith_short_16","alias_value":"GD2EAQHVBB7V4BLZ","created_at":"2026-07-08T01:19:21Z"},{"alias_kind":"pith_short_8","alias_value":"GD2EAQHV","created_at":"2026-07-08T01:19:21Z"}],"graph_snapshots":[{"event_id":"sha256:053cd4a17e74f57b43d8aab3e3d950d281643c59ff0eceeb9f96b9e72194a910","target":"graph","created_at":"2026-07-08T01:19:21Z","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/2607.06327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English. We present the first large-scale evaluation of UE methods across 22 languages, spanning high-, mid-, and low-resource settings. Using two human-curated Q\\&A datasets, we compare open and closed box UE methods (nine in total) across different model sizes and architectures while eliciting long-form reasoning, avoiding LLM-as-a-judge and embedding-based scoring, which can introduce evaluation noise. We report three main actionable findings. First, we fi","authors_text":"Amin Mantrach, Andrea Alfarano, Andrea Bacciu, Marcello Federico, Saab Mansour","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T14:25:09Z","title":"Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06327","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":"sha256:5fa9feebb50a58d1b44cbbdda9c6aa4e484ebc918f65e4828e41b35f0df83a45","target":"record","created_at":"2026-07-08T01:19:21Z","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":"667fe27356832b6e2c00205944678c87443817b09e2282dd59900959cca38767","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T14:25:09Z","title_canon_sha256":"d2d4916ee0bec59bdbf3484614945ef3cc76aaff56dbe42d8dbc6b5b4a5a5f1a"},"schema_version":"1.0","source":{"id":"2607.06327","kind":"arxiv","version":1}},"canonical_sha256":"30f44040f5087f5e05791f101917f0773e51ac6efaebd94c2a21c71f8b0674ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30f44040f5087f5e05791f101917f0773e51ac6efaebd94c2a21c71f8b0674ee","first_computed_at":"2026-07-08T01:19:21.514284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:19:21.514284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aqTTd3oPY0ymfDAZ4i+YHQWO+Um1HSPmgnewsG1q/EfRtEatjvvyCFYvpv6WxjcozrYNHBjT4asCw91Z13NIBQ==","signature_status":"signed_v1","signed_at":"2026-07-08T01:19:21.514710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06327","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fa9feebb50a58d1b44cbbdda9c6aa4e484ebc918f65e4828e41b35f0df83a45","sha256:053cd4a17e74f57b43d8aab3e3d950d281643c59ff0eceeb9f96b9e72194a910"],"state_sha256":"03cc686a8da70606138a61289d3d21af8a9c6c2bd6d8e1be92f686859e603c72"}