{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LUNBPAGP4XAMBCOCSX3UPWQROT","short_pith_number":"pith:LUNBPAGP","schema_version":"1.0","canonical_sha256":"5d1a1780cfe5c0c089c295f747da1174cda7c39a5c87b5f0b0f003e308c418d6","source":{"kind":"arxiv","id":"2306.10193","version":2},"attestation_state":"computed","paper":{"title":"Conformal Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Fisch, Adam Yala, Jae Ho Sohn, Regina Barzilay, Tal Schuster, Tommi S. Jaakkola, Victor Quach","submitted_at":"2023-06-16T21:55:08Z","abstract_excerpt":"We propose a novel approach to conformal prediction for generative language models (LMs). Standard conformal prediction produces prediction sets -- in place of single predictions -- that have rigorous, statistical performance guarantees. LM responses are typically sampled from the model's predicted distribution over the large, combinatorial output space of natural language. Translating this process to conformal prediction, we calibrate a stopping rule for sampling different outputs from the LM that get added to a growing set of candidates until we are confident that the output set is sufficien"},"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":"2306.10193","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-16T21:55:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bf88984063fdb5a833aa0688d843a25371eafa34b705ae9d2d72309a9b0e9d87","abstract_canon_sha256":"cb73359429c137971fb1c28ea0dfc1f676829d6b077c115cfdfc8f62cf404bd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:12.291222Z","signature_b64":"mlrlj0ZDrjAgD52pieWnKA/UMxWtO/nGnxvJrkq9AfoHe4T713eK2jzfqeiHTwWL3L7eAKQxqSBnxZzX5Zs3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d1a1780cfe5c0c089c295f747da1174cda7c39a5c87b5f0b0f003e308c418d6","last_reissued_at":"2026-07-05T08:26:12.290628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:12.290628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conformal Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Fisch, Adam Yala, Jae Ho Sohn, Regina Barzilay, Tal Schuster, Tommi S. Jaakkola, Victor Quach","submitted_at":"2023-06-16T21:55:08Z","abstract_excerpt":"We propose a novel approach to conformal prediction for generative language models (LMs). Standard conformal prediction produces prediction sets -- in place of single predictions -- that have rigorous, statistical performance guarantees. LM responses are typically sampled from the model's predicted distribution over the large, combinatorial output space of natural language. Translating this process to conformal prediction, we calibrate a stopping rule for sampling different outputs from the LM that get added to a growing set of candidates until we are confident that the output set is sufficien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10193","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/2306.10193/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":"2306.10193","created_at":"2026-07-05T08:26:12.290694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10193v2","created_at":"2026-07-05T08:26:12.290694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10193","created_at":"2026-07-05T08:26:12.290694+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUNBPAGP4XAM","created_at":"2026-07-05T08:26:12.290694+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUNBPAGP4XAMBCOC","created_at":"2026-07-05T08:26:12.290694+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUNBPAGP","created_at":"2026-07-05T08:26:12.290694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02510","citing_title":"Online Safety Monitoring for LLMs","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12587","citing_title":"Strategic Decision Support for AI Agents","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02206","citing_title":"Prediction Sets for Counterfactual Decisions: Coverage, Optimality, and Conformal Prediction","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08277","citing_title":"Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29654","citing_title":"Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28264","citing_title":"Entropy Distribution as a Fingerprint for Hallucinations in Generative Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00251","citing_title":"Capability Self-Assessment: Teaching LLMs to Know Their Limits","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04406","citing_title":"Decomposition-Based Modular Conformal Prediction for Two-Stage Modeling","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23189","citing_title":"Empirical Bayes Conformal Prediction for Vision and Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17487","citing_title":"Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16407","citing_title":"Proof-Carrying Certificates for LLM Pipelines: A Trust-Boundary Architecture","ref_index":49,"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":117,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07633","citing_title":"Flow-Based Conformal Predictive Distributions","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01413","citing_title":"Adaptive Stopping for Multi-Turn LLM Reasoning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27914","citing_title":"Geometry-Calibrated Conformal Abstention for Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17487","citing_title":"Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUNBPAGP4XAMBCOCSX3UPWQROT","json":"https://pith.science/pith/LUNBPAGP4XAMBCOCSX3UPWQROT.json","graph_json":"https://pith.science/api/pith-number/LUNBPAGP4XAMBCOCSX3UPWQROT/graph.json","events_json":"https://pith.science/api/pith-number/LUNBPAGP4XAMBCOCSX3UPWQROT/events.json","paper":"https://pith.science/paper/LUNBPAGP"},"agent_actions":{"view_html":"https://pith.science/pith/LUNBPAGP4XAMBCOCSX3UPWQROT","download_json":"https://pith.science/pith/LUNBPAGP4XAMBCOCSX3UPWQROT.json","view_paper":"https://pith.science/paper/LUNBPAGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10193&json=true","fetch_graph":"https://pith.science/api/pith-number/LUNBPAGP4XAMBCOCSX3UPWQROT/graph.json","fetch_events":"https://pith.science/api/pith-number/LUNBPAGP4XAMBCOCSX3UPWQROT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUNBPAGP4XAMBCOCSX3UPWQROT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUNBPAGP4XAMBCOCSX3UPWQROT/action/storage_attestation","attest_author":"https://pith.science/pith/LUNBPAGP4XAMBCOCSX3UPWQROT/action/author_attestation","sign_citation":"https://pith.science/pith/LUNBPAGP4XAMBCOCSX3UPWQROT/action/citation_signature","submit_replication":"https://pith.science/pith/LUNBPAGP4XAMBCOCSX3UPWQROT/action/replication_record"}},"created_at":"2026-07-05T08:26:12.290694+00:00","updated_at":"2026-07-05T08:26:12.290694+00:00"}