{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LISOT6PENT6WFRA5B3EDI6TQAC","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":"0ad48c4b9cff55974ee550f181cdee89c24d4e7a7909d73f7bd51f027a8af9bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T18:57:43Z","title_canon_sha256":"5a2bf978729821560e7cbe87656e956c5703be1760b2de4813c727327b766385"},"schema_version":"1.0","source":{"id":"2507.03120","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03120","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03120v1","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03120","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"LISOT6PENT6W","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_16","alias_value":"LISOT6PENT6WFRA5","created_at":"2026-07-05T11:31:52Z"},{"alias_kind":"pith_short_8","alias_value":"LISOT6PE","created_at":"2026-07-05T11:31:52Z"}],"graph_snapshots":[{"event_id":"sha256:d7b39df8bf292628d8d1023b41a4afa5757c3eb1c09de3b185dcc706ca583b70","target":"graph","created_at":"2026-07-05T11:31:52Z","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/2507.03120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) exhibit strikingly conflicting behaviors: they can appear steadfastly overconfident in their initial answers whilst at the same time being prone to excessive doubt when challenged. To investigate this apparent paradox, we developed a novel experimental paradigm, exploiting the unique ability to obtain confidence estimates from LLMs without creating memory of their initial judgments -- something impossible in human participants. We show that LLMs -- Gemma 3, GPT4o and o1-preview -- exhibit a pronounced choice-supportive bias that reinforces and boosts their estimate","authors_text":"Andrea Banino, Benedetto De Martino, Dharshan Kumaran, Joe Heyward, Larisa Markeeva, Mrinal Mathur, Petar Velickovic, Razvan Pascanu, Simon Osindero, Stephen M Fleming, Viorica Patraucean","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T18:57:43Z","title":"How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03120","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:f212ae3970fa5092a8771bd6c7091ce3e7e5d818977c316336f05fc46d9f85e3","target":"record","created_at":"2026-07-05T11:31:52Z","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":"0ad48c4b9cff55974ee550f181cdee89c24d4e7a7909d73f7bd51f027a8af9bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T18:57:43Z","title_canon_sha256":"5a2bf978729821560e7cbe87656e956c5703be1760b2de4813c727327b766385"},"schema_version":"1.0","source":{"id":"2507.03120","kind":"arxiv","version":1}},"canonical_sha256":"5a24e9f9e46cfd62c41d0ec8347a7000be63b3ba79e3c81a48c98f857f8c1e3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a24e9f9e46cfd62c41d0ec8347a7000be63b3ba79e3c81a48c98f857f8c1e3e","first_computed_at":"2026-07-05T11:31:52.874134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:52.874134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RgZgjrsI583Gcyiz0mUGAOT4Q/fhNthWy7uOmmQ9YEli3D605aFxSQdTEfEC1oC3ovSOLbMF2yHVWx/VBmUIBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:52.874592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03120","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f212ae3970fa5092a8771bd6c7091ce3e7e5d818977c316336f05fc46d9f85e3","sha256:d7b39df8bf292628d8d1023b41a4afa5757c3eb1c09de3b185dcc706ca583b70"],"state_sha256":"67e36f25ef793b6ef29980cd7d04f2f84d018333b32450057a47619a91a2ebca"}