{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U2MBJSMRUSZUUFDQWYQ4GNMF42","short_pith_number":"pith:U2MBJSMR","schema_version":"1.0","canonical_sha256":"a69814c991a4b34a1470b621c33585e6a4124390d2317ebaadc7cad1284348ab","source":{"kind":"arxiv","id":"2509.07355","version":1},"attestation_state":"computed","paper":{"title":"Besting Good--Turing: Optimality of Non-Parametric Maximum Likelihood for Distribution Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Jonathan Niles-Weed, Yandi Shen, Yanjun Han, Yihong Wu","submitted_at":"2025-09-09T03:04:06Z","abstract_excerpt":"When faced with a small sample from a large universe of possible outcomes, scientists often turn to the venerable Good--Turing estimator. Despite its pedigree, however, this estimator comes with considerable drawbacks, such as the need to hand-tune smoothing parameters and the lack of a precise optimality guarantee. We introduce a parameter-free estimator that bests Good--Turing in both theory and practice. Our method marries two classic ideas, namely Robbins's empirical Bayes and Kiefer--Wolfowitz non-parametric maximum likelihood estimation (NPMLE), to learn an implicit prior from data and t"},"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":"2509.07355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-09-09T03:04:06Z","cross_cats_sorted":["cs.IT","math.IT","stat.ME","stat.TH"],"title_canon_sha256":"9fa2c27f7b1c4a91f5dab72d16aabf1c99cfad33dddde54c3299ec1f73aaf895","abstract_canon_sha256":"3de6b0bf7d39af49784372e66c441de45211dab20a178f382a45c47e2160bb5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:20.183381Z","signature_b64":"6Hdv11Apmn3gDtnkHiwT/8L+CGGB7WSgvro74ufRcZF4HWh5rzuA/RYUYTp5nSCVk0uFnkuHR48oWWthgLK5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a69814c991a4b34a1470b621c33585e6a4124390d2317ebaadc7cad1284348ab","last_reissued_at":"2026-07-05T12:07:20.182879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:20.182879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Besting Good--Turing: Optimality of Non-Parametric Maximum Likelihood for Distribution Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Jonathan Niles-Weed, Yandi Shen, Yanjun Han, Yihong Wu","submitted_at":"2025-09-09T03:04:06Z","abstract_excerpt":"When faced with a small sample from a large universe of possible outcomes, scientists often turn to the venerable Good--Turing estimator. Despite its pedigree, however, this estimator comes with considerable drawbacks, such as the need to hand-tune smoothing parameters and the lack of a precise optimality guarantee. We introduce a parameter-free estimator that bests Good--Turing in both theory and practice. Our method marries two classic ideas, namely Robbins's empirical Bayes and Kiefer--Wolfowitz non-parametric maximum likelihood estimation (NPMLE), to learn an implicit prior from data and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07355","kind":"arxiv","version":1},"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/2509.07355/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":"2509.07355","created_at":"2026-07-05T12:07:20.182935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.07355v1","created_at":"2026-07-05T12:07:20.182935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07355","created_at":"2026-07-05T12:07:20.182935+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2MBJSMRUSZU","created_at":"2026-07-05T12:07:20.182935+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2MBJSMRUSZUUFDQ","created_at":"2026-07-05T12:07:20.182935+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2MBJSMR","created_at":"2026-07-05T12:07:20.182935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15219","citing_title":"NOVA: Fundamental Limits of Knowledge Discovery Through AI","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15219","citing_title":"NOVA: Fundamental Limits of Knowledge Discovery Through AI","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03594","citing_title":"Poisson Empirical Bayes via Gamma-Smoothed Nonparametric Maximum Likelihood","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12087","citing_title":"Adaptivity of the NPMLE to finitely discrete mixing distributions in Gaussian/Poisson mixtures","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U2MBJSMRUSZUUFDQWYQ4GNMF42","json":"https://pith.science/pith/U2MBJSMRUSZUUFDQWYQ4GNMF42.json","graph_json":"https://pith.science/api/pith-number/U2MBJSMRUSZUUFDQWYQ4GNMF42/graph.json","events_json":"https://pith.science/api/pith-number/U2MBJSMRUSZUUFDQWYQ4GNMF42/events.json","paper":"https://pith.science/paper/U2MBJSMR"},"agent_actions":{"view_html":"https://pith.science/pith/U2MBJSMRUSZUUFDQWYQ4GNMF42","download_json":"https://pith.science/pith/U2MBJSMRUSZUUFDQWYQ4GNMF42.json","view_paper":"https://pith.science/paper/U2MBJSMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.07355&json=true","fetch_graph":"https://pith.science/api/pith-number/U2MBJSMRUSZUUFDQWYQ4GNMF42/graph.json","fetch_events":"https://pith.science/api/pith-number/U2MBJSMRUSZUUFDQWYQ4GNMF42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2MBJSMRUSZUUFDQWYQ4GNMF42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2MBJSMRUSZUUFDQWYQ4GNMF42/action/storage_attestation","attest_author":"https://pith.science/pith/U2MBJSMRUSZUUFDQWYQ4GNMF42/action/author_attestation","sign_citation":"https://pith.science/pith/U2MBJSMRUSZUUFDQWYQ4GNMF42/action/citation_signature","submit_replication":"https://pith.science/pith/U2MBJSMRUSZUUFDQWYQ4GNMF42/action/replication_record"}},"created_at":"2026-07-05T12:07:20.182935+00:00","updated_at":"2026-07-05T12:07:20.182935+00:00"}