{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ARYT2TPSXPKCVLHGBQEPDSJTND","short_pith_number":"pith:ARYT2TPS","schema_version":"1.0","canonical_sha256":"04713d4df2bbd42aace60c08f1c93368e547114c6b95fa452da50287fc9832d8","source":{"kind":"arxiv","id":"2110.01052","version":5},"attestation_state":"computed","paper":{"title":"Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anastasios N. Angelopoulos, Emmanuel J. Cand\\`es, Lihua Lei, Michael I. Jordan, Stephen Bates","submitted_at":"2021-10-03T17:42:03Z","abstract_excerpt":"We introduce a framework for calibrating machine learning models so that their predictions satisfy explicit, finite-sample statistical guarantees. Our calibration algorithms work with any underlying model and (unknown) data-generating distribution and do not require model refitting. The framework addresses, among other examples, false discovery rate control in multi-label classification, intersection-over-union control in instance segmentation, and the simultaneous control of the type-1 error of outlier detection and confidence set coverage in classification or regression. Our main insight is "},"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":"2110.01052","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-03T17:42:03Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ME","stat.ML"],"title_canon_sha256":"fa80940d3ac56673f4f6f18cc51585db115939579e3a2843bdfb767845212510","abstract_canon_sha256":"5d9e1157ef2751ffc443e0c7fadd74cbf4b059ebed88085f9ef59b28ed34f371"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:09.494692Z","signature_b64":"lpTCu9ArlqhGmPuWC3M6wOCKtC5kku8GkEeLZ0dCSxdWs9DntC4pbJdKf/QJh9oy4J4f+q9vAaqx5xHGvzhSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04713d4df2bbd42aace60c08f1c93368e547114c6b95fa452da50287fc9832d8","last_reissued_at":"2026-07-05T05:02:09.494081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:09.494081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anastasios N. Angelopoulos, Emmanuel J. Cand\\`es, Lihua Lei, Michael I. Jordan, Stephen Bates","submitted_at":"2021-10-03T17:42:03Z","abstract_excerpt":"We introduce a framework for calibrating machine learning models so that their predictions satisfy explicit, finite-sample statistical guarantees. Our calibration algorithms work with any underlying model and (unknown) data-generating distribution and do not require model refitting. The framework addresses, among other examples, false discovery rate control in multi-label classification, intersection-over-union control in instance segmentation, and the simultaneous control of the type-1 error of outlier detection and confidence set coverage in classification or regression. Our main insight is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01052","kind":"arxiv","version":5},"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/2110.01052/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":"2110.01052","created_at":"2026-07-05T05:02:09.494153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.01052v5","created_at":"2026-07-05T05:02:09.494153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01052","created_at":"2026-07-05T05:02:09.494153+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARYT2TPSXPKC","created_at":"2026-07-05T05:02:09.494153+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARYT2TPSXPKCVLHG","created_at":"2026-07-05T05:02:09.494153+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARYT2TPS","created_at":"2026-07-05T05:02:09.494153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06799","citing_title":"What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2607.08456","citing_title":"Two Axes of LLM Abstention: Answer Correctness and Question Answerability","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25760","citing_title":"Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09919","citing_title":"Co-GLANCE: Uncertainty-Aware Active Perception for Heterogeneous Robot Teaming","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08517","citing_title":"A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Control","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05551","citing_title":"Conformal Risk-Averse Decision Making with Action Conditional Guarantee","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01000","citing_title":"Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher","ref_index":91,"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":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30660","citing_title":"BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00437","citing_title":"EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01000","citing_title":"Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04406","citing_title":"Decomposition-Based Modular Conformal Prediction for Two-Stage Modeling","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23189","citing_title":"Empirical Bayes Conformal Prediction for Vision and Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20084","citing_title":"BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09471","citing_title":"The Statistical Cost of Adaptation in Multi-Source Transfer Learning","ref_index":184,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25235","citing_title":"VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06605","citing_title":"How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19444","citing_title":"Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2107.07511","citing_title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06479","citing_title":"Risk-Controlled Post-Processing of Decision Policies","ref_index":125,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARYT2TPSXPKCVLHGBQEPDSJTND","json":"https://pith.science/pith/ARYT2TPSXPKCVLHGBQEPDSJTND.json","graph_json":"https://pith.science/api/pith-number/ARYT2TPSXPKCVLHGBQEPDSJTND/graph.json","events_json":"https://pith.science/api/pith-number/ARYT2TPSXPKCVLHGBQEPDSJTND/events.json","paper":"https://pith.science/paper/ARYT2TPS"},"agent_actions":{"view_html":"https://pith.science/pith/ARYT2TPSXPKCVLHGBQEPDSJTND","download_json":"https://pith.science/pith/ARYT2TPSXPKCVLHGBQEPDSJTND.json","view_paper":"https://pith.science/paper/ARYT2TPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.01052&json=true","fetch_graph":"https://pith.science/api/pith-number/ARYT2TPSXPKCVLHGBQEPDSJTND/graph.json","fetch_events":"https://pith.science/api/pith-number/ARYT2TPSXPKCVLHGBQEPDSJTND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARYT2TPSXPKCVLHGBQEPDSJTND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARYT2TPSXPKCVLHGBQEPDSJTND/action/storage_attestation","attest_author":"https://pith.science/pith/ARYT2TPSXPKCVLHGBQEPDSJTND/action/author_attestation","sign_citation":"https://pith.science/pith/ARYT2TPSXPKCVLHGBQEPDSJTND/action/citation_signature","submit_replication":"https://pith.science/pith/ARYT2TPSXPKCVLHGBQEPDSJTND/action/replication_record"}},"created_at":"2026-07-05T05:02:09.494153+00:00","updated_at":"2026-07-05T05:02:09.494153+00:00"}