{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I4C62GQO4ZAEWYRU3W6HXMXNLG","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":"f63897c93838b082e96adce9ca3485bf481cc6d23b5eb617bce3539ae8b5eb00","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T07:27:53Z","title_canon_sha256":"fbc2893f32a8efe22dbe8771c78ffcb694d4c683f5a34b68dcfd019f71141229"},"schema_version":"1.0","source":{"id":"2606.05799","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05799","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05799v1","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05799","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"I4C62GQO4ZAE","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"I4C62GQO4ZAEWYRU","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"I4C62GQO","created_at":"2026-06-05T01:15:03Z"}],"graph_snapshots":[{"event_id":"sha256:2a1030cbce2d03827602fb6c90ff19c504f87497a49dce3a5d357271c1301b41","target":"graph","created_at":"2026-06-05T01:15:03Z","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/2606.05799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing calibration methods for Large Language Models (LLMs) often overlook a critical dimension of trustworthiness: a model's {\\em behavioral robustness} to irrelevant or misleading information. In this paper, we argue that a model's true confidence should reflect its stability under cognitive pressure. We introduce \\textsc{CaliDist}, a novel post-hoc calibration approach that directly measures and penalizes a model's susceptibility to distraction. \\textsc{CaliDist} quantifies how an LLM's predictions and uncertainty change when its input prompt is perturbed with semantic \\textit{distractors","authors_text":"Cornelia Caragea, Mohammad Anas Jawad","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T07:27:53Z","title":"CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05799","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":"sha256:3d15872e98b8679698ccb3d1038d95a2a886a2d6d973ae04a23c675039a02db5","target":"record","created_at":"2026-06-05T01:15:03Z","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":"f63897c93838b082e96adce9ca3485bf481cc6d23b5eb617bce3539ae8b5eb00","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T07:27:53Z","title_canon_sha256":"fbc2893f32a8efe22dbe8771c78ffcb694d4c683f5a34b68dcfd019f71141229"},"schema_version":"1.0","source":{"id":"2606.05799","kind":"arxiv","version":1}},"canonical_sha256":"4705ed1a0ee6404b6234ddbc7bb2ed59b433fdd83f95a960876e939a0cca386e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4705ed1a0ee6404b6234ddbc7bb2ed59b433fdd83f95a960876e939a0cca386e","first_computed_at":"2026-06-05T01:15:03.720284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:03.720284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZSvHZZaEntDttVAcc66EM/B+iWobS/PiY/DeT8qjF5510/Glz+aDuaZ04LxpM80meWPA5L5O3yvE5fFHcryzAQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:03.720731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05799","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d15872e98b8679698ccb3d1038d95a2a886a2d6d973ae04a23c675039a02db5","sha256:2a1030cbce2d03827602fb6c90ff19c504f87497a49dce3a5d357271c1301b41"],"state_sha256":"cc9bd6bc3483b6aefa1a0aa7921269630a77812cfb4c124bf82ad5696cedbe65"}