{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VU34RUPVCBU2ADHYUJVBBMASV4","short_pith_number":"pith:VU34RUPV","schema_version":"1.0","canonical_sha256":"ad37c8d1f51069a00cf8a26a10b012af33fc448e56d3d65610e7006fd8ee4738","source":{"kind":"arxiv","id":"1904.06979","version":2},"attestation_state":"computed","paper":{"title":"A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"C\\'edric Colas, Olivier Sigaud, Pierre-Yves Oudeyer","submitted_at":"2019-04-15T12:00:29Z","abstract_excerpt":"Consistently checking the statistical significance of experimental results is the first mandatory step towards reproducible science. This paper presents a hitchhiker's guide to rigorous comparisons of reinforcement learning algorithms. After introducing the concepts of statistical testing, we review the relevant statistical tests and compare them empirically in terms of false positive rate and statistical power as a function of the sample size (number of seeds) and effect size. We further investigate the robustness of these tests to violations of the most common hypotheses (normal distribution"},"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":"1904.06979","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2019-04-15T12:00:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a175905b2126153c20bc1e9e20f5b03fc7be6fbaa348e4516468f0c52b5ba713","abstract_canon_sha256":"62add3b6914c1313606c8cb28177a6f459deb94a0712edde4aa0ef0b01ee0672"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:50.828273Z","signature_b64":"tDYg7sisZqcUPWK4FDshmdX4mcesGvCOYUJlBKyn4OEKdGjW30yOqvHSilffpV4tpdvL4ZmRdcsBeomTPc2TCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad37c8d1f51069a00cf8a26a10b012af33fc448e56d3d65610e7006fd8ee4738","last_reissued_at":"2026-07-05T04:51:50.827842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:50.827842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"C\\'edric Colas, Olivier Sigaud, Pierre-Yves Oudeyer","submitted_at":"2019-04-15T12:00:29Z","abstract_excerpt":"Consistently checking the statistical significance of experimental results is the first mandatory step towards reproducible science. This paper presents a hitchhiker's guide to rigorous comparisons of reinforcement learning algorithms. After introducing the concepts of statistical testing, we review the relevant statistical tests and compare them empirically in terms of false positive rate and statistical power as a function of the sample size (number of seeds) and effect size. We further investigate the robustness of these tests to violations of the most common hypotheses (normal distribution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06979","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1904.06979/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":"1904.06979","created_at":"2026-07-05T04:51:50.827898+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.06979v2","created_at":"2026-07-05T04:51:50.827898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06979","created_at":"2026-07-05T04:51:50.827898+00:00"},{"alias_kind":"pith_short_12","alias_value":"VU34RUPVCBU2","created_at":"2026-07-05T04:51:50.827898+00:00"},{"alias_kind":"pith_short_16","alias_value":"VU34RUPVCBU2ADHY","created_at":"2026-07-05T04:51:50.827898+00:00"},{"alias_kind":"pith_short_8","alias_value":"VU34RUPV","created_at":"2026-07-05T04:51:50.827898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28287","citing_title":"AtomComposer: Discovering Chemical Space from First Principles with Reinforcement Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24018","citing_title":"Betting for Sim-to-Real Performance Evaluation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VU34RUPVCBU2ADHYUJVBBMASV4","json":"https://pith.science/pith/VU34RUPVCBU2ADHYUJVBBMASV4.json","graph_json":"https://pith.science/api/pith-number/VU34RUPVCBU2ADHYUJVBBMASV4/graph.json","events_json":"https://pith.science/api/pith-number/VU34RUPVCBU2ADHYUJVBBMASV4/events.json","paper":"https://pith.science/paper/VU34RUPV"},"agent_actions":{"view_html":"https://pith.science/pith/VU34RUPVCBU2ADHYUJVBBMASV4","download_json":"https://pith.science/pith/VU34RUPVCBU2ADHYUJVBBMASV4.json","view_paper":"https://pith.science/paper/VU34RUPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.06979&json=true","fetch_graph":"https://pith.science/api/pith-number/VU34RUPVCBU2ADHYUJVBBMASV4/graph.json","fetch_events":"https://pith.science/api/pith-number/VU34RUPVCBU2ADHYUJVBBMASV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VU34RUPVCBU2ADHYUJVBBMASV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VU34RUPVCBU2ADHYUJVBBMASV4/action/storage_attestation","attest_author":"https://pith.science/pith/VU34RUPVCBU2ADHYUJVBBMASV4/action/author_attestation","sign_citation":"https://pith.science/pith/VU34RUPVCBU2ADHYUJVBBMASV4/action/citation_signature","submit_replication":"https://pith.science/pith/VU34RUPVCBU2ADHYUJVBBMASV4/action/replication_record"}},"created_at":"2026-07-05T04:51:50.827898+00:00","updated_at":"2026-07-05T04:51:50.827898+00:00"}