{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WQ25YHZOPDERFK2EHIRE54ZHUM","short_pith_number":"pith:WQ25YHZO","schema_version":"1.0","canonical_sha256":"b435dc1f2e78c912ab443a224ef327a33d3999d70097c1502e608c2acdd5fe0d","source":{"kind":"arxiv","id":"1806.08295","version":2},"attestation_state":"computed","paper":{"title":"How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"C\\'edric Colas, Olivier Sigaud, Pierre-Yves Oudeyer","submitted_at":"2018-06-21T15:39:19Z","abstract_excerpt":"Consistently checking the statistical significance of experimental results is one of the mandatory methodological steps to address the so-called \"reproducibility crisis\" in deep reinforcement learning. In this tutorial paper, we explain how the number of random seeds relates to the probabilities of statistical errors. For both the t-test and the bootstrap confidence interval test, we recall theoretical guidelines to determine the number of random seeds one should use to provide a statistically significant comparison of the performance of two algorithms. Finally, we discuss the influence of dev"},"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":"1806.08295","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-21T15:39:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bbf2f0927b71340a073cfdd89afd5891568afa6a90f1f88e31197ed36f78858f","abstract_canon_sha256":"612718bd5ad41a3ffadd2949bd425f9ac3ebd5c65a4fd95b313225e5a687ded1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:28.812829Z","signature_b64":"DQyr68TeePFwSY8zrvyw7GR8oL9RsYNAfUnhbuaOjjlTDNWbSmCIQbaHc/4OU99xvdkjGJ2/MAqRKWJnIp8XCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b435dc1f2e78c912ab443a224ef327a33d3999d70097c1502e608c2acdd5fe0d","last_reissued_at":"2026-05-18T00:11:28.812492Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:28.812492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"C\\'edric Colas, Olivier Sigaud, Pierre-Yves Oudeyer","submitted_at":"2018-06-21T15:39:19Z","abstract_excerpt":"Consistently checking the statistical significance of experimental results is one of the mandatory methodological steps to address the so-called \"reproducibility crisis\" in deep reinforcement learning. In this tutorial paper, we explain how the number of random seeds relates to the probabilities of statistical errors. For both the t-test and the bootstrap confidence interval test, we recall theoretical guidelines to determine the number of random seeds one should use to provide a statistically significant comparison of the performance of two algorithms. Finally, we discuss the influence of dev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08295","kind":"arxiv","version":2},"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":"1806.08295","created_at":"2026-05-18T00:11:28.812545+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.08295v2","created_at":"2026-05-18T00:11:28.812545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08295","created_at":"2026-05-18T00:11:28.812545+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQ25YHZOPDER","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQ25YHZOPDERFK2E","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQ25YHZO","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.21282","citing_title":"Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21282","citing_title":"Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2405.14573","citing_title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17351","citing_title":"SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQ25YHZOPDERFK2EHIRE54ZHUM","json":"https://pith.science/pith/WQ25YHZOPDERFK2EHIRE54ZHUM.json","graph_json":"https://pith.science/api/pith-number/WQ25YHZOPDERFK2EHIRE54ZHUM/graph.json","events_json":"https://pith.science/api/pith-number/WQ25YHZOPDERFK2EHIRE54ZHUM/events.json","paper":"https://pith.science/paper/WQ25YHZO"},"agent_actions":{"view_html":"https://pith.science/pith/WQ25YHZOPDERFK2EHIRE54ZHUM","download_json":"https://pith.science/pith/WQ25YHZOPDERFK2EHIRE54ZHUM.json","view_paper":"https://pith.science/paper/WQ25YHZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.08295&json=true","fetch_graph":"https://pith.science/api/pith-number/WQ25YHZOPDERFK2EHIRE54ZHUM/graph.json","fetch_events":"https://pith.science/api/pith-number/WQ25YHZOPDERFK2EHIRE54ZHUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQ25YHZOPDERFK2EHIRE54ZHUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQ25YHZOPDERFK2EHIRE54ZHUM/action/storage_attestation","attest_author":"https://pith.science/pith/WQ25YHZOPDERFK2EHIRE54ZHUM/action/author_attestation","sign_citation":"https://pith.science/pith/WQ25YHZOPDERFK2EHIRE54ZHUM/action/citation_signature","submit_replication":"https://pith.science/pith/WQ25YHZOPDERFK2EHIRE54ZHUM/action/replication_record"}},"created_at":"2026-05-18T00:11:28.812545+00:00","updated_at":"2026-05-18T00:11:28.812545+00:00"}