{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LC2IURWXCU7HI2BMJL2PVZUUM6","short_pith_number":"pith:LC2IURWX","schema_version":"1.0","canonical_sha256":"58b48a46d7153e74682c4af4fae69467b46dff453c230dbbc3701e5e2e027951","source":{"kind":"arxiv","id":"2302.13439","version":2},"attestation_state":"computed","paper":{"title":"Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Kaitlyn Zhou, Tatsunori Hashimoto","submitted_at":"2023-02-26T23:46:29Z","abstract_excerpt":"The increased deployment of LMs for real-world tasks involving knowledge and facts makes it important to understand model epistemology: what LMs think they know, and how their attitudes toward that knowledge are affected by language use in their inputs. Here, we study an aspect of model epistemology: how epistemic markers of certainty, uncertainty, or evidentiality like \"I'm sure it's\", \"I think it's\", or \"Wikipedia says it's\" affect models, and whether they contribute to model failures. We develop a typology of epistemic markers and inject 50 markers into prompts for question answering. We fi"},"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":"2302.13439","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-26T23:46:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dbedfcf680bf75059a607f643aa4cd17d83ef6d31850cfcfd722a812c50ccc7b","abstract_canon_sha256":"438bd177440303f84818fe23b7c0d422249a46e94b04aff2dd4ab1f9d703db79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:54.305912Z","signature_b64":"4zaxS3d0f9oPzWI94P1llCDdM4uNc/GSAseEFqy5ttlpT8HC16QEdXSu36TQmmCl441akXdYIiAKAEYALk9iDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58b48a46d7153e74682c4af4fae69467b46dff453c230dbbc3701e5e2e027951","last_reissued_at":"2026-07-05T07:11:54.305438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:54.305438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Kaitlyn Zhou, Tatsunori Hashimoto","submitted_at":"2023-02-26T23:46:29Z","abstract_excerpt":"The increased deployment of LMs for real-world tasks involving knowledge and facts makes it important to understand model epistemology: what LMs think they know, and how their attitudes toward that knowledge are affected by language use in their inputs. Here, we study an aspect of model epistemology: how epistemic markers of certainty, uncertainty, or evidentiality like \"I'm sure it's\", \"I think it's\", or \"Wikipedia says it's\" affect models, and whether they contribute to model failures. We develop a typology of epistemic markers and inject 50 markers into prompts for question answering. We fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13439","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/2302.13439/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":"2302.13439","created_at":"2026-07-05T07:11:54.305498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.13439v2","created_at":"2026-07-05T07:11:54.305498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13439","created_at":"2026-07-05T07:11:54.305498+00:00"},{"alias_kind":"pith_short_12","alias_value":"LC2IURWXCU7H","created_at":"2026-07-05T07:11:54.305498+00:00"},{"alias_kind":"pith_short_16","alias_value":"LC2IURWXCU7HI2BM","created_at":"2026-07-05T07:11:54.305498+00:00"},{"alias_kind":"pith_short_8","alias_value":"LC2IURWX","created_at":"2026-07-05T07:11:54.305498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11211","citing_title":"Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2308.05374","citing_title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2305.11738","citing_title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17200","citing_title":"Calibrating Model-Based Evaluation Metrics for Summarization","ref_index":101,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LC2IURWXCU7HI2BMJL2PVZUUM6","json":"https://pith.science/pith/LC2IURWXCU7HI2BMJL2PVZUUM6.json","graph_json":"https://pith.science/api/pith-number/LC2IURWXCU7HI2BMJL2PVZUUM6/graph.json","events_json":"https://pith.science/api/pith-number/LC2IURWXCU7HI2BMJL2PVZUUM6/events.json","paper":"https://pith.science/paper/LC2IURWX"},"agent_actions":{"view_html":"https://pith.science/pith/LC2IURWXCU7HI2BMJL2PVZUUM6","download_json":"https://pith.science/pith/LC2IURWXCU7HI2BMJL2PVZUUM6.json","view_paper":"https://pith.science/paper/LC2IURWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.13439&json=true","fetch_graph":"https://pith.science/api/pith-number/LC2IURWXCU7HI2BMJL2PVZUUM6/graph.json","fetch_events":"https://pith.science/api/pith-number/LC2IURWXCU7HI2BMJL2PVZUUM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LC2IURWXCU7HI2BMJL2PVZUUM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LC2IURWXCU7HI2BMJL2PVZUUM6/action/storage_attestation","attest_author":"https://pith.science/pith/LC2IURWXCU7HI2BMJL2PVZUUM6/action/author_attestation","sign_citation":"https://pith.science/pith/LC2IURWXCU7HI2BMJL2PVZUUM6/action/citation_signature","submit_replication":"https://pith.science/pith/LC2IURWXCU7HI2BMJL2PVZUUM6/action/replication_record"}},"created_at":"2026-07-05T07:11:54.305498+00:00","updated_at":"2026-07-05T07:11:54.305498+00:00"}