{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CSDCH64VVQMIBJDKCKW2TCE5I2","short_pith_number":"pith:CSDCH64V","schema_version":"1.0","canonical_sha256":"148623fb95ac1880a46a12ada9889d46946c9e50945579d2c01321f8840bfa5f","source":{"kind":"arxiv","id":"1707.05342","version":3},"attestation_state":"computed","paper":{"title":"An optimal unrestricted learning procedure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Shahar Mendelson","submitted_at":"2017-07-17T18:05:59Z","abstract_excerpt":"We study learning problems involving arbitrary classes of functions $F$, distributions $X$ and targets $Y$. Because proper learning procedures, i.e., procedures that are only allowed to select functions in $F$, tend to perform poorly unless the problem satisfies some additional structural property (e.g., that $F$ is convex), we consider unrestricted learning procedures that are free to choose functions outside the given class.\n  We present a new unrestricted procedure that is optimal in a very strong sense: the required sample complexity is essentially the best one can hope for, and the estima"},"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":"1707.05342","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-17T18:05:59Z","cross_cats_sorted":[],"title_canon_sha256":"66b21258c230662f222b8b21e75535601f16d22f6a1bbcb54da1dbc9f4f60af9","abstract_canon_sha256":"9a2c4c21e8ae998b62a5247d3b6f596e9ff815749abd7c381b5cfa85a66eebbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:31.707560Z","signature_b64":"WcqkuMy5VPHUrE2x0J+A4flYHGoL9KqzeiCnnw+LKq1noAAUcKY90eLdKNi0j6BcMxLYVfYZiAP3waF58wMmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"148623fb95ac1880a46a12ada9889d46946c9e50945579d2c01321f8840bfa5f","last_reissued_at":"2026-05-18T00:18:31.707091Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:31.707091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An optimal unrestricted learning procedure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Shahar Mendelson","submitted_at":"2017-07-17T18:05:59Z","abstract_excerpt":"We study learning problems involving arbitrary classes of functions $F$, distributions $X$ and targets $Y$. Because proper learning procedures, i.e., procedures that are only allowed to select functions in $F$, tend to perform poorly unless the problem satisfies some additional structural property (e.g., that $F$ is convex), we consider unrestricted learning procedures that are free to choose functions outside the given class.\n  We present a new unrestricted procedure that is optimal in a very strong sense: the required sample complexity is essentially the best one can hope for, and the estima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.05342","kind":"arxiv","version":3},"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":"1707.05342","created_at":"2026-05-18T00:18:31.707150+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.05342v3","created_at":"2026-05-18T00:18:31.707150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.05342","created_at":"2026-05-18T00:18:31.707150+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSDCH64VVQMI","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSDCH64VVQMIBJDK","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSDCH64V","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2409.03410","citing_title":"Error bounds of Median-of-means estimators with VC-dimension","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CSDCH64VVQMIBJDKCKW2TCE5I2","json":"https://pith.science/pith/CSDCH64VVQMIBJDKCKW2TCE5I2.json","graph_json":"https://pith.science/api/pith-number/CSDCH64VVQMIBJDKCKW2TCE5I2/graph.json","events_json":"https://pith.science/api/pith-number/CSDCH64VVQMIBJDKCKW2TCE5I2/events.json","paper":"https://pith.science/paper/CSDCH64V"},"agent_actions":{"view_html":"https://pith.science/pith/CSDCH64VVQMIBJDKCKW2TCE5I2","download_json":"https://pith.science/pith/CSDCH64VVQMIBJDKCKW2TCE5I2.json","view_paper":"https://pith.science/paper/CSDCH64V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.05342&json=true","fetch_graph":"https://pith.science/api/pith-number/CSDCH64VVQMIBJDKCKW2TCE5I2/graph.json","fetch_events":"https://pith.science/api/pith-number/CSDCH64VVQMIBJDKCKW2TCE5I2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSDCH64VVQMIBJDKCKW2TCE5I2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSDCH64VVQMIBJDKCKW2TCE5I2/action/storage_attestation","attest_author":"https://pith.science/pith/CSDCH64VVQMIBJDKCKW2TCE5I2/action/author_attestation","sign_citation":"https://pith.science/pith/CSDCH64VVQMIBJDKCKW2TCE5I2/action/citation_signature","submit_replication":"https://pith.science/pith/CSDCH64VVQMIBJDKCKW2TCE5I2/action/replication_record"}},"created_at":"2026-05-18T00:18:31.707150+00:00","updated_at":"2026-05-18T00:18:31.707150+00:00"}