{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GAYCCKDMQY7VAIVKJ26TYUWIKD","short_pith_number":"pith:GAYCCKDM","schema_version":"1.0","canonical_sha256":"303021286c863f5022aa4ebd3c52c850c8b6fdbf1d7825bc7ecfce4886a7f810","source":{"kind":"arxiv","id":"2001.00106","version":2},"attestation_state":"computed","paper":{"title":"PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Insup Lee, Nikolai Matni, Osbert Bastani, Sangdon Park","submitted_at":"2019-12-31T23:02:01Z","abstract_excerpt":"We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i.e., the confidence set for a given input contains the true label with high probability. We demonstrate how our approach can be used to construct PAC confidence sets on ResNet for ImageNet, a visual object tracking model, and a dynamics model for the half-cheetah reinforcement learning problem."},"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":"2001.00106","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-31T23:02:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b7be606f3081c1594d8f7eaca931459c691374d900feaee85762d03b4d9bfada","abstract_canon_sha256":"0138675dc682a64b7c0bea28b962d364f70cba0c22172f45a1ad61cdeca2f2a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:41:02.058896Z","signature_b64":"mhzq9HeqMDtoz9m32I1v1//skUQE69rVUrCT7ZBPxw/O94+hQ0GT5IYiYQ8ZlWbAbbAOEb/G2SYebz421jCNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"303021286c863f5022aa4ebd3c52c850c8b6fdbf1d7825bc7ecfce4886a7f810","last_reissued_at":"2026-07-05T00:41:02.058343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:41:02.058343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Insup Lee, Nikolai Matni, Osbert Bastani, Sangdon Park","submitted_at":"2019-12-31T23:02:01Z","abstract_excerpt":"We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i.e., the confidence set for a given input contains the true label with high probability. We demonstrate how our approach can be used to construct PAC confidence sets on ResNet for ImageNet, a visual object tracking model, and a dynamics model for the half-cheetah reinforcement learning problem."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00106","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/2001.00106/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":"2001.00106","created_at":"2026-07-05T00:41:02.058416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.00106v2","created_at":"2026-07-05T00:41:02.058416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00106","created_at":"2026-07-05T00:41:02.058416+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAYCCKDMQY7V","created_at":"2026-07-05T00:41:02.058416+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAYCCKDMQY7VAIVK","created_at":"2026-07-05T00:41:02.058416+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAYCCKDM","created_at":"2026-07-05T00:41:02.058416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06605","citing_title":"How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAYCCKDMQY7VAIVKJ26TYUWIKD","json":"https://pith.science/pith/GAYCCKDMQY7VAIVKJ26TYUWIKD.json","graph_json":"https://pith.science/api/pith-number/GAYCCKDMQY7VAIVKJ26TYUWIKD/graph.json","events_json":"https://pith.science/api/pith-number/GAYCCKDMQY7VAIVKJ26TYUWIKD/events.json","paper":"https://pith.science/paper/GAYCCKDM"},"agent_actions":{"view_html":"https://pith.science/pith/GAYCCKDMQY7VAIVKJ26TYUWIKD","download_json":"https://pith.science/pith/GAYCCKDMQY7VAIVKJ26TYUWIKD.json","view_paper":"https://pith.science/paper/GAYCCKDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.00106&json=true","fetch_graph":"https://pith.science/api/pith-number/GAYCCKDMQY7VAIVKJ26TYUWIKD/graph.json","fetch_events":"https://pith.science/api/pith-number/GAYCCKDMQY7VAIVKJ26TYUWIKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAYCCKDMQY7VAIVKJ26TYUWIKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAYCCKDMQY7VAIVKJ26TYUWIKD/action/storage_attestation","attest_author":"https://pith.science/pith/GAYCCKDMQY7VAIVKJ26TYUWIKD/action/author_attestation","sign_citation":"https://pith.science/pith/GAYCCKDMQY7VAIVKJ26TYUWIKD/action/citation_signature","submit_replication":"https://pith.science/pith/GAYCCKDMQY7VAIVKJ26TYUWIKD/action/replication_record"}},"created_at":"2026-07-05T00:41:02.058416+00:00","updated_at":"2026-07-05T00:41:02.058416+00:00"}