{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NPVUWH7CLXI7RP3MRGP4Y3EMME","short_pith_number":"pith:NPVUWH7C","schema_version":"1.0","canonical_sha256":"6beb4b1fe25dd1f8bf6c899fcc6c8c613aad85150aca9bf9c9d5419541e83d96","source":{"kind":"arxiv","id":"2403.02509","version":1},"attestation_state":"computed","paper":{"title":"SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiaxin Zhang, Kamalika Das, Lalla Mouatadid, Xiang Gao","submitted_at":"2024-03-04T21:55:22Z","abstract_excerpt":"In recent years, large language models (LLMs) have become increasingly prevalent, offering remarkable text generation capabilities. However, a pressing challenge is their tendency to make confidently wrong predictions, highlighting the critical need for uncertainty quantification (UQ) in LLMs. While previous works have mainly focused on addressing aleatoric uncertainty, the full spectrum of uncertainties, including epistemic, remains inadequately explored. Motivated by this gap, we introduce a novel UQ method, sampling with perturbation for UQ (SPUQ), designed to tackle both aleatoric and epis"},"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":"2403.02509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T21:55:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6aa617ba4be7ea19fa909f7f158aa05f3204c1d75b67faa700d35559bbbce8ef","abstract_canon_sha256":"7fe0a0b7f6412706846ace909557091dd02508056067142e7e9f1fb1b3bdbfbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:18.401378Z","signature_b64":"VOzf+6jKBHbeTMv8qRtQ/o+AtA5zMFxG3d6MrGoHtNb+xHzwCFcEY6CgX5gjVrWgYqQbuJFZ6nMfgnJStPFsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6beb4b1fe25dd1f8bf6c899fcc6c8c613aad85150aca9bf9c9d5419541e83d96","last_reissued_at":"2026-07-05T07:52:18.400922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:18.400922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiaxin Zhang, Kamalika Das, Lalla Mouatadid, Xiang Gao","submitted_at":"2024-03-04T21:55:22Z","abstract_excerpt":"In recent years, large language models (LLMs) have become increasingly prevalent, offering remarkable text generation capabilities. However, a pressing challenge is their tendency to make confidently wrong predictions, highlighting the critical need for uncertainty quantification (UQ) in LLMs. While previous works have mainly focused on addressing aleatoric uncertainty, the full spectrum of uncertainties, including epistemic, remains inadequately explored. Motivated by this gap, we introduce a novel UQ method, sampling with perturbation for UQ (SPUQ), designed to tackle both aleatoric and epis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02509","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/2403.02509/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":"2403.02509","created_at":"2026-07-05T07:52:18.400982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02509v1","created_at":"2026-07-05T07:52:18.400982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02509","created_at":"2026-07-05T07:52:18.400982+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPVUWH7CLXI7","created_at":"2026-07-05T07:52:18.400982+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPVUWH7CLXI7RP3M","created_at":"2026-07-05T07:52:18.400982+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPVUWH7C","created_at":"2026-07-05T07:52:18.400982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.06431","citing_title":"Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2506.10060","citing_title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17112","citing_title":"Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01048","citing_title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPVUWH7CLXI7RP3MRGP4Y3EMME","json":"https://pith.science/pith/NPVUWH7CLXI7RP3MRGP4Y3EMME.json","graph_json":"https://pith.science/api/pith-number/NPVUWH7CLXI7RP3MRGP4Y3EMME/graph.json","events_json":"https://pith.science/api/pith-number/NPVUWH7CLXI7RP3MRGP4Y3EMME/events.json","paper":"https://pith.science/paper/NPVUWH7C"},"agent_actions":{"view_html":"https://pith.science/pith/NPVUWH7CLXI7RP3MRGP4Y3EMME","download_json":"https://pith.science/pith/NPVUWH7CLXI7RP3MRGP4Y3EMME.json","view_paper":"https://pith.science/paper/NPVUWH7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02509&json=true","fetch_graph":"https://pith.science/api/pith-number/NPVUWH7CLXI7RP3MRGP4Y3EMME/graph.json","fetch_events":"https://pith.science/api/pith-number/NPVUWH7CLXI7RP3MRGP4Y3EMME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPVUWH7CLXI7RP3MRGP4Y3EMME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPVUWH7CLXI7RP3MRGP4Y3EMME/action/storage_attestation","attest_author":"https://pith.science/pith/NPVUWH7CLXI7RP3MRGP4Y3EMME/action/author_attestation","sign_citation":"https://pith.science/pith/NPVUWH7CLXI7RP3MRGP4Y3EMME/action/citation_signature","submit_replication":"https://pith.science/pith/NPVUWH7CLXI7RP3MRGP4Y3EMME/action/replication_record"}},"created_at":"2026-07-05T07:52:18.400982+00:00","updated_at":"2026-07-05T07:52:18.400982+00:00"}