{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YZIWWRIWKY7P453TMAVW4GOSIX","short_pith_number":"pith:YZIWWRIW","schema_version":"1.0","canonical_sha256":"c6516b4516563efe7773602b6e19d245e4367adeb758cd2f7cf290c9b01fb296","source":{"kind":"arxiv","id":"2504.12098","version":2},"attestation_state":"computed","paper":{"title":"Gauging Overprecision in LLMs: An Empirical Study","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adil Bahaj, Hamed Rahimi, Mohamed Chetouani, Mounir Ghogho","submitted_at":"2025-04-16T14:02:21Z","abstract_excerpt":"Recently, overconfidence in large language models (LLMs) has garnered considerable attention due to its fundamental importance in quantifying the trustworthiness of LLM generation. However, existing approaches prompt the \\textit{black box LLMs} to produce their confidence (\\textit{verbalized confidence}), which can be subject to many biases and hallucinations. Inspired by a different aspect of overconfidence in cognitive science called \\textit{overprecision}, we designed a framework for its study in black box LLMs. This framework contains three main phases: 1) generation, 2) refinement and 3) "},"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":"2504.12098","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-16T14:02:21Z","cross_cats_sorted":[],"title_canon_sha256":"c314493512227a4c0d094ec6597d4f9389d2dd5649c393866bb7d88ca9e49a00","abstract_canon_sha256":"7dd940a84ac9d91fcd3adfbfe8b6b7b8ebb27769bb344c8eee1010c7608a222a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:46.753205Z","signature_b64":"L+whzoONfzy/cgKvfcCJBFGRXnQle54rFy01fy8SEo6yEK4lX8rqwU3UI01pkhRdIhfznT0HfEACyZBcIdxNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6516b4516563efe7773602b6e19d245e4367adeb758cd2f7cf290c9b01fb296","last_reissued_at":"2026-07-05T10:54:46.752734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:46.752734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gauging Overprecision in LLMs: An Empirical Study","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adil Bahaj, Hamed Rahimi, Mohamed Chetouani, Mounir Ghogho","submitted_at":"2025-04-16T14:02:21Z","abstract_excerpt":"Recently, overconfidence in large language models (LLMs) has garnered considerable attention due to its fundamental importance in quantifying the trustworthiness of LLM generation. However, existing approaches prompt the \\textit{black box LLMs} to produce their confidence (\\textit{verbalized confidence}), which can be subject to many biases and hallucinations. Inspired by a different aspect of overconfidence in cognitive science called \\textit{overprecision}, we designed a framework for its study in black box LLMs. This framework contains three main phases: 1) generation, 2) refinement and 3) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12098","kind":"arxiv","version":2},"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/2504.12098/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":"2504.12098","created_at":"2026-07-05T10:54:46.752790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12098v2","created_at":"2026-07-05T10:54:46.752790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12098","created_at":"2026-07-05T10:54:46.752790+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZIWWRIWKY7P","created_at":"2026-07-05T10:54:46.752790+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZIWWRIWKY7P453T","created_at":"2026-07-05T10:54:46.752790+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZIWWRIW","created_at":"2026-07-05T10:54:46.752790+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/YZIWWRIWKY7P453TMAVW4GOSIX","json":"https://pith.science/pith/YZIWWRIWKY7P453TMAVW4GOSIX.json","graph_json":"https://pith.science/api/pith-number/YZIWWRIWKY7P453TMAVW4GOSIX/graph.json","events_json":"https://pith.science/api/pith-number/YZIWWRIWKY7P453TMAVW4GOSIX/events.json","paper":"https://pith.science/paper/YZIWWRIW"},"agent_actions":{"view_html":"https://pith.science/pith/YZIWWRIWKY7P453TMAVW4GOSIX","download_json":"https://pith.science/pith/YZIWWRIWKY7P453TMAVW4GOSIX.json","view_paper":"https://pith.science/paper/YZIWWRIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12098&json=true","fetch_graph":"https://pith.science/api/pith-number/YZIWWRIWKY7P453TMAVW4GOSIX/graph.json","fetch_events":"https://pith.science/api/pith-number/YZIWWRIWKY7P453TMAVW4GOSIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZIWWRIWKY7P453TMAVW4GOSIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZIWWRIWKY7P453TMAVW4GOSIX/action/storage_attestation","attest_author":"https://pith.science/pith/YZIWWRIWKY7P453TMAVW4GOSIX/action/author_attestation","sign_citation":"https://pith.science/pith/YZIWWRIWKY7P453TMAVW4GOSIX/action/citation_signature","submit_replication":"https://pith.science/pith/YZIWWRIWKY7P453TMAVW4GOSIX/action/replication_record"}},"created_at":"2026-07-05T10:54:46.752790+00:00","updated_at":"2026-07-05T10:54:46.752790+00:00"}