{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:R5JZXREEWJU6JSE7U4YT77HBOM","short_pith_number":"pith:R5JZXREE","schema_version":"1.0","canonical_sha256":"8f539bc484b269e4c89fa7313ffce1733451672fd75b0e476bcb554e3dbcddb4","source":{"kind":"arxiv","id":"1708.06425","version":2},"attestation_state":"computed","paper":{"title":"SafePredict: A Meta-Algorithm for Machine Learning That Uses Refusals to Guarantee Correctness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"David Ramirez, Dennis E. Shasha, Elza Erkip, Mustafa A. Kocak","submitted_at":"2017-08-21T21:23:42Z","abstract_excerpt":"SafePredict is a novel meta-algorithm that works with any base prediction algorithm for online data to guarantee an arbitrarily chosen correctness rate, $1-\\epsilon$, by allowing refusals. Allowing refusals means that the meta-algorithm may refuse to emit a prediction produced by the base algorithm on occasion so that the error rate on non-refused predictions does not exceed $\\epsilon$. The SafePredict error bound does not rely on any assumptions on the data distribution or the base predictor. When the base predictor happens not to exceed the target error rate $\\epsilon$, SafePredict refuses o"},"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":"1708.06425","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-21T21:23:42Z","cross_cats_sorted":["cs.AI","math.ST","stat.TH"],"title_canon_sha256":"20127c6411b6d7b772ec96eaa73a6ff2055e095e8e7716f48a24ffcedbff34f3","abstract_canon_sha256":"4ca2099905e94eb5c47e33bcda9a39fb3b289ec8cd560248b412146706810b3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:57.448794Z","signature_b64":"JLgFM3ALSh9z0fuduLcLHt41jI0Bx2yt3xCMptPGX8BackEoPXxlaPuDbwLm+wkwExvcQYal7787EjB1nUhGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f539bc484b269e4c89fa7313ffce1733451672fd75b0e476bcb554e3dbcddb4","last_reissued_at":"2026-05-18T00:30:57.448089Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:57.448089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SafePredict: A Meta-Algorithm for Machine Learning That Uses Refusals to Guarantee Correctness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"David Ramirez, Dennis E. Shasha, Elza Erkip, Mustafa A. Kocak","submitted_at":"2017-08-21T21:23:42Z","abstract_excerpt":"SafePredict is a novel meta-algorithm that works with any base prediction algorithm for online data to guarantee an arbitrarily chosen correctness rate, $1-\\epsilon$, by allowing refusals. Allowing refusals means that the meta-algorithm may refuse to emit a prediction produced by the base algorithm on occasion so that the error rate on non-refused predictions does not exceed $\\epsilon$. The SafePredict error bound does not rely on any assumptions on the data distribution or the base predictor. When the base predictor happens not to exceed the target error rate $\\epsilon$, SafePredict refuses o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.06425","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":""},"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":"1708.06425","created_at":"2026-05-18T00:30:57.448202+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.06425v2","created_at":"2026-05-18T00:30:57.448202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.06425","created_at":"2026-05-18T00:30:57.448202+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5JZXREEWJU6","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5JZXREEWJU6JSE7","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5JZXREE","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5JZXREEWJU6JSE7U4YT77HBOM","json":"https://pith.science/pith/R5JZXREEWJU6JSE7U4YT77HBOM.json","graph_json":"https://pith.science/api/pith-number/R5JZXREEWJU6JSE7U4YT77HBOM/graph.json","events_json":"https://pith.science/api/pith-number/R5JZXREEWJU6JSE7U4YT77HBOM/events.json","paper":"https://pith.science/paper/R5JZXREE"},"agent_actions":{"view_html":"https://pith.science/pith/R5JZXREEWJU6JSE7U4YT77HBOM","download_json":"https://pith.science/pith/R5JZXREEWJU6JSE7U4YT77HBOM.json","view_paper":"https://pith.science/paper/R5JZXREE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.06425&json=true","fetch_graph":"https://pith.science/api/pith-number/R5JZXREEWJU6JSE7U4YT77HBOM/graph.json","fetch_events":"https://pith.science/api/pith-number/R5JZXREEWJU6JSE7U4YT77HBOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5JZXREEWJU6JSE7U4YT77HBOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5JZXREEWJU6JSE7U4YT77HBOM/action/storage_attestation","attest_author":"https://pith.science/pith/R5JZXREEWJU6JSE7U4YT77HBOM/action/author_attestation","sign_citation":"https://pith.science/pith/R5JZXREEWJU6JSE7U4YT77HBOM/action/citation_signature","submit_replication":"https://pith.science/pith/R5JZXREEWJU6JSE7U4YT77HBOM/action/replication_record"}},"created_at":"2026-05-18T00:30:57.448202+00:00","updated_at":"2026-05-18T00:30:57.448202+00:00"}