{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YFH3M5VCWRYTDNMERUMUUMEHJE","short_pith_number":"pith:YFH3M5VC","schema_version":"1.0","canonical_sha256":"c14fb676a2b47131b5848d194a30874913044aac8329887480dbb87e35f5ad87","source":{"kind":"arxiv","id":"2502.17671","version":3},"attestation_state":"computed","paper":{"title":"Optimal Recovery Meets Minimax Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Guergana Petrova, Jonathan W. Siegel, Rahul Parhi, Robert D. Nowak, Ronald DeVore","submitted_at":"2025-02-24T21:37:54Z","abstract_excerpt":"A fundamental problem in statistics and machine learning is to estimate a function $f$ from possibly noisy observations of its point samples. The goal is to design a numerical algorithm to construct an approximation $\\hat f$ to $f$ in a prescribed norm that asymptotically achieves the best possible error (as a function of the number $m$ of observations and the variance $\\sigma^2$ of the noise). This problem has received considerable attention in both nonparametric statistics (noisy observations) and optimal recovery (noiseless observations). Quantitative bounds require assumptions on $f$, know"},"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":"2502.17671","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-02-24T21:37:54Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML","stat.TH"],"title_canon_sha256":"2a19037a1f1baed1558548c4bfb812d254ff803232d7ca2db28847994a80cb34","abstract_canon_sha256":"189cd020923af89bdfccc0f80f20aa13068813a53aa8269a8f9d66cb6a5877d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:42.529302Z","signature_b64":"bXxd/nwoY7y2dBmI14NUfWrD4GypLOcr3fqc7IrjJCsgCx5ervKNN6O+IdA05ONnhjiFqi4Y8Eb0LNQQeP3NDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c14fb676a2b47131b5848d194a30874913044aac8329887480dbb87e35f5ad87","last_reissued_at":"2026-07-05T11:11:42.528830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:42.528830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Recovery Meets Minimax Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Guergana Petrova, Jonathan W. Siegel, Rahul Parhi, Robert D. Nowak, Ronald DeVore","submitted_at":"2025-02-24T21:37:54Z","abstract_excerpt":"A fundamental problem in statistics and machine learning is to estimate a function $f$ from possibly noisy observations of its point samples. The goal is to design a numerical algorithm to construct an approximation $\\hat f$ to $f$ in a prescribed norm that asymptotically achieves the best possible error (as a function of the number $m$ of observations and the variance $\\sigma^2$ of the noise). This problem has received considerable attention in both nonparametric statistics (noisy observations) and optimal recovery (noiseless observations). Quantitative bounds require assumptions on $f$, know"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17671","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.17671/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":"2502.17671","created_at":"2026-07-05T11:11:42.528883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17671v3","created_at":"2026-07-05T11:11:42.528883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17671","created_at":"2026-07-05T11:11:42.528883+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFH3M5VCWRYT","created_at":"2026-07-05T11:11:42.528883+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFH3M5VCWRYTDNME","created_at":"2026-07-05T11:11:42.528883+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFH3M5VC","created_at":"2026-07-05T11:11:42.528883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07660","citing_title":"Universal, sample-optimal algorithms for recovery of anisotropic functions from i.i.d. samples","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YFH3M5VCWRYTDNMERUMUUMEHJE","json":"https://pith.science/pith/YFH3M5VCWRYTDNMERUMUUMEHJE.json","graph_json":"https://pith.science/api/pith-number/YFH3M5VCWRYTDNMERUMUUMEHJE/graph.json","events_json":"https://pith.science/api/pith-number/YFH3M5VCWRYTDNMERUMUUMEHJE/events.json","paper":"https://pith.science/paper/YFH3M5VC"},"agent_actions":{"view_html":"https://pith.science/pith/YFH3M5VCWRYTDNMERUMUUMEHJE","download_json":"https://pith.science/pith/YFH3M5VCWRYTDNMERUMUUMEHJE.json","view_paper":"https://pith.science/paper/YFH3M5VC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17671&json=true","fetch_graph":"https://pith.science/api/pith-number/YFH3M5VCWRYTDNMERUMUUMEHJE/graph.json","fetch_events":"https://pith.science/api/pith-number/YFH3M5VCWRYTDNMERUMUUMEHJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFH3M5VCWRYTDNMERUMUUMEHJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFH3M5VCWRYTDNMERUMUUMEHJE/action/storage_attestation","attest_author":"https://pith.science/pith/YFH3M5VCWRYTDNMERUMUUMEHJE/action/author_attestation","sign_citation":"https://pith.science/pith/YFH3M5VCWRYTDNMERUMUUMEHJE/action/citation_signature","submit_replication":"https://pith.science/pith/YFH3M5VCWRYTDNMERUMUUMEHJE/action/replication_record"}},"created_at":"2026-07-05T11:11:42.528883+00:00","updated_at":"2026-07-05T11:11:42.528883+00:00"}