{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4BFSIZILUXKEO43K464EDBVRQX","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":"7fa73d55a444e0c5288ef48fcb5865529883f8470fad828c327f4f889e8708fb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-07-28T03:56:23Z","title_canon_sha256":"cfe9fca6c15c24cf627ba5e5c081b1d88c7052f8e8810eef99bdaa41154eacc0"},"schema_version":"1.0","source":{"id":"2607.25257","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25257","created_at":"2026-07-29T00:25:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25257v1","created_at":"2026-07-29T00:25:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25257","created_at":"2026-07-29T00:25:11Z"},{"alias_kind":"pith_short_12","alias_value":"4BFSIZILUXKE","created_at":"2026-07-29T00:25:11Z"},{"alias_kind":"pith_short_16","alias_value":"4BFSIZILUXKEO43K","created_at":"2026-07-29T00:25:11Z"},{"alias_kind":"pith_short_8","alias_value":"4BFSIZIL","created_at":"2026-07-29T00:25:11Z"}],"graph_snapshots":[{"event_id":"sha256:7de542aeeba733ce95b8308c43f101c5b4f3a4c54305982ced4a8e9dba4df8db","target":"graph","created_at":"2026-07-29T00:25:11Z","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/2607.25257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Item Response Theory (IRT) has recently been proposed as a framework for evaluating large language model (LLM) benchmarks by separating a model's latent ability from the properties of individual benchmark items. Existing neural IRT approaches, including PSN-IRT, estimate these quantities using point estimates, limiting uncertainty quantification and downstream statistical inference. We introduce Laplace-PSN-IRT, a post-hoc last-layer Laplace approximation that augments a trained PSN-IRT model with approximate Bayesian posterior inference, recovering calibrated uncertainty over model ability an","authors_text":"Juan Francisco, Mandujano Reyes","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-07-28T03:56:23Z","title":"Laplace-PSN-IRT: Uncertainty Quantification for Neural Item Response Theory Models of LLM Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25257","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":"sha256:3dcbed2c95a6abe360fda5797eb77be070d6eacce463dbdf5f71057c1861bfd5","target":"record","created_at":"2026-07-29T00:25:11Z","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":"7fa73d55a444e0c5288ef48fcb5865529883f8470fad828c327f4f889e8708fb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-07-28T03:56:23Z","title_canon_sha256":"cfe9fca6c15c24cf627ba5e5c081b1d88c7052f8e8810eef99bdaa41154eacc0"},"schema_version":"1.0","source":{"id":"2607.25257","kind":"arxiv","version":1}},"canonical_sha256":"e04b24650ba5d447736ae7b84186b185ec55fc4635519af2c19fab04b1b1630f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e04b24650ba5d447736ae7b84186b185ec55fc4635519af2c19fab04b1b1630f","first_computed_at":"2026-07-29T00:25:11.144189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:25:11.144189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UlsokibkqYABnNGsN7Zc+Jhz+ZG1+tA7QqEFjN6vqSE4v5zYYHVSVTSFmNB0s3RP32ervUN81KlMxy1FWwLyCQ==","signature_status":"signed_v1","signed_at":"2026-07-29T00:25:11.145113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.25257","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dcbed2c95a6abe360fda5797eb77be070d6eacce463dbdf5f71057c1861bfd5","sha256:7de542aeeba733ce95b8308c43f101c5b4f3a4c54305982ced4a8e9dba4df8db"],"state_sha256":"f45318d214ebeeb1e5715b815a2a9fb00a5d2abcf68b92892a24bea9a44862d9"}