{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U52YWVMLDJ5SSYECMNNVWQNODQ","short_pith_number":"pith:U52YWVML","schema_version":"1.0","canonical_sha256":"a7758b558b1a7b296082635b5b41ae1c330c175a1274d4f670ae000d060c39e1","source":{"kind":"arxiv","id":"2406.02628","version":1},"attestation_state":"computed","paper":{"title":"Replicability in High Dimensional Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DS","cs.LG"],"primary_cat":"stat.ML","authors_text":"Christopher Ye, Daniel Kane, Max Hopkins, Russell Impagliazzo, Sihan Liu","submitted_at":"2024-06-04T00:06:42Z","abstract_excerpt":"The replicability crisis is a major issue across nearly all areas of empirical science, calling for the formal study of replicability in statistics. Motivated in this context, [Impagliazzo, Lei, Pitassi, and Sorrell STOC 2022] introduced the notion of replicable learning algorithms, and gave basic procedures for $1$-dimensional tasks including statistical queries. In this work, we study the computational and statistical cost of replicability for several fundamental high dimensional statistical tasks, including multi-hypothesis testing and mean estimation.\n  Our main contribution establishes a "},"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":"2406.02628","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-06-04T00:06:42Z","cross_cats_sorted":["cs.CC","cs.DS","cs.LG"],"title_canon_sha256":"08b4f7f8362fc6aed43718b8de26d31ccc66934ee98a81eb9e866c203aba6461","abstract_canon_sha256":"ea9e6ec7eb5eba206bddfc4a5fb2d3a810c42635f4980b023927011b1e969b40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:28.207619Z","signature_b64":"AhILAmnrt7MOfuNFSRtveYMX9+Crkk35eSuF5v/vDU4rl4pZsvLwIKALsq/Tj9bvoYWOuiu4UPzwQ1rbefyPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7758b558b1a7b296082635b5b41ae1c330c175a1274d4f670ae000d060c39e1","last_reissued_at":"2026-07-05T08:27:28.207200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:28.207200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Replicability in High Dimensional Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DS","cs.LG"],"primary_cat":"stat.ML","authors_text":"Christopher Ye, Daniel Kane, Max Hopkins, Russell Impagliazzo, Sihan Liu","submitted_at":"2024-06-04T00:06:42Z","abstract_excerpt":"The replicability crisis is a major issue across nearly all areas of empirical science, calling for the formal study of replicability in statistics. Motivated in this context, [Impagliazzo, Lei, Pitassi, and Sorrell STOC 2022] introduced the notion of replicable learning algorithms, and gave basic procedures for $1$-dimensional tasks including statistical queries. In this work, we study the computational and statistical cost of replicability for several fundamental high dimensional statistical tasks, including multi-hypothesis testing and mean estimation.\n  Our main contribution establishes a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02628","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/2406.02628/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":"2406.02628","created_at":"2026-07-05T08:27:28.207256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02628v1","created_at":"2026-07-05T08:27:28.207256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02628","created_at":"2026-07-05T08:27:28.207256+00:00"},{"alias_kind":"pith_short_12","alias_value":"U52YWVMLDJ5S","created_at":"2026-07-05T08:27:28.207256+00:00"},{"alias_kind":"pith_short_16","alias_value":"U52YWVMLDJ5SSYEC","created_at":"2026-07-05T08:27:28.207256+00:00"},{"alias_kind":"pith_short_8","alias_value":"U52YWVML","created_at":"2026-07-05T08:27:28.207256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.08660","citing_title":"Replicable Reinforcement Learning with Linear Function Approximation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20024","citing_title":"Replicable Bandits with UCB based Exploration","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10423","citing_title":"Replicable Composition","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U52YWVMLDJ5SSYECMNNVWQNODQ","json":"https://pith.science/pith/U52YWVMLDJ5SSYECMNNVWQNODQ.json","graph_json":"https://pith.science/api/pith-number/U52YWVMLDJ5SSYECMNNVWQNODQ/graph.json","events_json":"https://pith.science/api/pith-number/U52YWVMLDJ5SSYECMNNVWQNODQ/events.json","paper":"https://pith.science/paper/U52YWVML"},"agent_actions":{"view_html":"https://pith.science/pith/U52YWVMLDJ5SSYECMNNVWQNODQ","download_json":"https://pith.science/pith/U52YWVMLDJ5SSYECMNNVWQNODQ.json","view_paper":"https://pith.science/paper/U52YWVML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02628&json=true","fetch_graph":"https://pith.science/api/pith-number/U52YWVMLDJ5SSYECMNNVWQNODQ/graph.json","fetch_events":"https://pith.science/api/pith-number/U52YWVMLDJ5SSYECMNNVWQNODQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U52YWVMLDJ5SSYECMNNVWQNODQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U52YWVMLDJ5SSYECMNNVWQNODQ/action/storage_attestation","attest_author":"https://pith.science/pith/U52YWVMLDJ5SSYECMNNVWQNODQ/action/author_attestation","sign_citation":"https://pith.science/pith/U52YWVMLDJ5SSYECMNNVWQNODQ/action/citation_signature","submit_replication":"https://pith.science/pith/U52YWVMLDJ5SSYECMNNVWQNODQ/action/replication_record"}},"created_at":"2026-07-05T08:27:28.207256+00:00","updated_at":"2026-07-05T08:27:28.207256+00:00"}