{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QIS5JY5OGIDFQWVD2RFHOINFDP","short_pith_number":"pith:QIS5JY5O","schema_version":"1.0","canonical_sha256":"8225d4e3ae3206585aa3d44a7721a51bd17602ecf2d91d6c45ef1dd5a2113680","source":{"kind":"arxiv","id":"2505.22655","version":1},"attestation_state":"computed","paper":{"title":"Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Enkelejda Kasneci, Gjergji Kasneci, Michael Kirchhof","submitted_at":"2025-05-28T17:59:08Z","abstract_excerpt":"Large-language models (LLMs) and chatbot agents are known to provide wrong outputs at times, and it was recently found that this can never be fully prevented. Hence, uncertainty quantification plays a crucial role, aiming to quantify the level of ambiguity in either one overall number or two numbers for aleatoric and epistemic uncertainty. This position paper argues that this traditional dichotomy of uncertainties is too limited for the open and interactive setup that LLM agents operate in when communicating with a user, and that we need to research avenues that enrich uncertainties in this no"},"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":"2505.22655","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T17:59:08Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d0d309fa10fc88f0a914e2ad895f6ca303e5ceab7639441e1a06bd9cd6873231","abstract_canon_sha256":"2aa7d78b21d0be057d518c6389b092dea38e17ef311b7af1f4bdb34c407b6dce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:28.493671Z","signature_b64":"Qk2sNA0GKJMPC8slroQ498q5VIMXukdzA+tWFgfzVbH6vydr0l1fY97CQRk6fl65ZwtRqBMSX+dlE+/IhCw3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8225d4e3ae3206585aa3d44a7721a51bd17602ecf2d91d6c45ef1dd5a2113680","last_reissued_at":"2026-07-05T11:11:28.493159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:28.493159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Enkelejda Kasneci, Gjergji Kasneci, Michael Kirchhof","submitted_at":"2025-05-28T17:59:08Z","abstract_excerpt":"Large-language models (LLMs) and chatbot agents are known to provide wrong outputs at times, and it was recently found that this can never be fully prevented. Hence, uncertainty quantification plays a crucial role, aiming to quantify the level of ambiguity in either one overall number or two numbers for aleatoric and epistemic uncertainty. This position paper argues that this traditional dichotomy of uncertainties is too limited for the open and interactive setup that LLM agents operate in when communicating with a user, and that we need to research avenues that enrich uncertainties in this no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22655","kind":"arxiv","version":1},"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/2505.22655/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":"2505.22655","created_at":"2026-07-05T11:11:28.493210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22655v1","created_at":"2026-07-05T11:11:28.493210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22655","created_at":"2026-07-05T11:11:28.493210+00:00"},{"alias_kind":"pith_short_12","alias_value":"QIS5JY5OGIDF","created_at":"2026-07-05T11:11:28.493210+00:00"},{"alias_kind":"pith_short_16","alias_value":"QIS5JY5OGIDFQWVD","created_at":"2026-07-05T11:11:28.493210+00:00"},{"alias_kind":"pith_short_8","alias_value":"QIS5JY5O","created_at":"2026-07-05T11:11:28.493210+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10777","citing_title":"Can we trust our models? Epistemic calibration in second-order classification","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24756","citing_title":"Proper Scoring Rules for Agentic Uncertainty Quantification","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28733","citing_title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26835","citing_title":"Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14642","citing_title":"Uncertainty Quantification on Graph Learning: A Survey","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11737","citing_title":"TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QIS5JY5OGIDFQWVD2RFHOINFDP","json":"https://pith.science/pith/QIS5JY5OGIDFQWVD2RFHOINFDP.json","graph_json":"https://pith.science/api/pith-number/QIS5JY5OGIDFQWVD2RFHOINFDP/graph.json","events_json":"https://pith.science/api/pith-number/QIS5JY5OGIDFQWVD2RFHOINFDP/events.json","paper":"https://pith.science/paper/QIS5JY5O"},"agent_actions":{"view_html":"https://pith.science/pith/QIS5JY5OGIDFQWVD2RFHOINFDP","download_json":"https://pith.science/pith/QIS5JY5OGIDFQWVD2RFHOINFDP.json","view_paper":"https://pith.science/paper/QIS5JY5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22655&json=true","fetch_graph":"https://pith.science/api/pith-number/QIS5JY5OGIDFQWVD2RFHOINFDP/graph.json","fetch_events":"https://pith.science/api/pith-number/QIS5JY5OGIDFQWVD2RFHOINFDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QIS5JY5OGIDFQWVD2RFHOINFDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QIS5JY5OGIDFQWVD2RFHOINFDP/action/storage_attestation","attest_author":"https://pith.science/pith/QIS5JY5OGIDFQWVD2RFHOINFDP/action/author_attestation","sign_citation":"https://pith.science/pith/QIS5JY5OGIDFQWVD2RFHOINFDP/action/citation_signature","submit_replication":"https://pith.science/pith/QIS5JY5OGIDFQWVD2RFHOINFDP/action/replication_record"}},"created_at":"2026-07-05T11:11:28.493210+00:00","updated_at":"2026-07-05T11:11:28.493210+00:00"}