{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:73DXSTZYAZ2XXS2KC2HZP45VEK","short_pith_number":"pith:73DXSTZY","schema_version":"1.0","canonical_sha256":"fec7794f3806757bcb4a168f97f3b52296d040710704dd0cb71f84dee13b1938","source":{"kind":"arxiv","id":"1511.04066","version":1},"attestation_state":"computed","paper":{"title":"Properly Learning Poisson Binomial Distributions in Almost Polynomial Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"cs.DS","authors_text":"Alistair Stewart, Daniel M. Kane, Ilias Diakonikolas","submitted_at":"2015-11-12T20:47:37Z","abstract_excerpt":"We give an algorithm for properly learning Poisson binomial distributions. A Poisson binomial distribution (PBD) of order $n$ is the discrete probability distribution of the sum of $n$ mutually independent Bernoulli random variables. Given $\\widetilde{O}(1/\\epsilon^2)$ samples from an unknown PBD $\\mathbf{p}$, our algorithm runs in time $(1/\\epsilon)^{O(\\log \\log (1/\\epsilon))}$, and outputs a hypothesis PBD that is $\\epsilon$-close to $\\mathbf{p}$ in total variation distance. The previously best known running time for properly learning PBDs was $(1/\\epsilon)^{O(\\log(1/\\epsilon))}$.\n  As one 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":"1511.04066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-11-12T20:47:37Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"e081e9fec5f6939087d3f83c3f08a28ecef6ee33da76abd79a77504957f4181f","abstract_canon_sha256":"3e23ff3229f2e90487363dc9e93a02cb0281d68917cffba40f48f8553833aa00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:27:06.025561Z","signature_b64":"+yIw4wG9nIZNCYCzWBX4TO5VmIc6rShZS3X6ORV7ORwCZDGzUeSY3Ojg3wnJ/EuCf8ilZYpO2nFEvbtTGfFQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fec7794f3806757bcb4a168f97f3b52296d040710704dd0cb71f84dee13b1938","last_reissued_at":"2026-05-18T01:27:06.024930Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:27:06.024930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Properly Learning Poisson Binomial Distributions in Almost Polynomial Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"cs.DS","authors_text":"Alistair Stewart, Daniel M. Kane, Ilias Diakonikolas","submitted_at":"2015-11-12T20:47:37Z","abstract_excerpt":"We give an algorithm for properly learning Poisson binomial distributions. A Poisson binomial distribution (PBD) of order $n$ is the discrete probability distribution of the sum of $n$ mutually independent Bernoulli random variables. Given $\\widetilde{O}(1/\\epsilon^2)$ samples from an unknown PBD $\\mathbf{p}$, our algorithm runs in time $(1/\\epsilon)^{O(\\log \\log (1/\\epsilon))}$, and outputs a hypothesis PBD that is $\\epsilon$-close to $\\mathbf{p}$ in total variation distance. The previously best known running time for properly learning PBDs was $(1/\\epsilon)^{O(\\log(1/\\epsilon))}$.\n  As one o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.04066","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":""},"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":"1511.04066","created_at":"2026-05-18T01:27:06.025030+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.04066v1","created_at":"2026-05-18T01:27:06.025030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.04066","created_at":"2026-05-18T01:27:06.025030+00:00"},{"alias_kind":"pith_short_12","alias_value":"73DXSTZYAZ2X","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"73DXSTZYAZ2XXS2K","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"73DXSTZY","created_at":"2026-05-18T12:29:07.941421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.08306","citing_title":"A Polynomial Time Algorithm for Log-Concave Maximum Likelihood via Locally Exponential Families","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73DXSTZYAZ2XXS2KC2HZP45VEK","json":"https://pith.science/pith/73DXSTZYAZ2XXS2KC2HZP45VEK.json","graph_json":"https://pith.science/api/pith-number/73DXSTZYAZ2XXS2KC2HZP45VEK/graph.json","events_json":"https://pith.science/api/pith-number/73DXSTZYAZ2XXS2KC2HZP45VEK/events.json","paper":"https://pith.science/paper/73DXSTZY"},"agent_actions":{"view_html":"https://pith.science/pith/73DXSTZYAZ2XXS2KC2HZP45VEK","download_json":"https://pith.science/pith/73DXSTZYAZ2XXS2KC2HZP45VEK.json","view_paper":"https://pith.science/paper/73DXSTZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.04066&json=true","fetch_graph":"https://pith.science/api/pith-number/73DXSTZYAZ2XXS2KC2HZP45VEK/graph.json","fetch_events":"https://pith.science/api/pith-number/73DXSTZYAZ2XXS2KC2HZP45VEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73DXSTZYAZ2XXS2KC2HZP45VEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73DXSTZYAZ2XXS2KC2HZP45VEK/action/storage_attestation","attest_author":"https://pith.science/pith/73DXSTZYAZ2XXS2KC2HZP45VEK/action/author_attestation","sign_citation":"https://pith.science/pith/73DXSTZYAZ2XXS2KC2HZP45VEK/action/citation_signature","submit_replication":"https://pith.science/pith/73DXSTZYAZ2XXS2KC2HZP45VEK/action/replication_record"}},"created_at":"2026-05-18T01:27:06.025030+00:00","updated_at":"2026-05-18T01:27:06.025030+00:00"}