{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V3RA457RZTSS73TB4H6R2KL35M","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e4b70930598291f024fad3b49a4d5a9c73e02e000dafd50c914ce8052a39b83d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-19T12:22:56Z","title_canon_sha256":"c5c1671682c4cfe84e91d26d602fda1a217cbdaae4e256e2f01618918f55269d"},"schema_version":"1.0","source":{"id":"2306.10882","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10882","created_at":"2026-07-05T11:13:05Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10882v3","created_at":"2026-07-05T11:13:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10882","created_at":"2026-07-05T11:13:05Z"},{"alias_kind":"pith_short_12","alias_value":"V3RA457RZTSS","created_at":"2026-07-05T11:13:05Z"},{"alias_kind":"pith_short_16","alias_value":"V3RA457RZTSS73TB","created_at":"2026-07-05T11:13:05Z"},{"alias_kind":"pith_short_8","alias_value":"V3RA457R","created_at":"2026-07-05T11:13:05Z"}],"graph_snapshots":[{"event_id":"sha256:4f74290aaff9ea8fa6a0faff0befbb533a760288e42009570b801ef45682670e","target":"graph","created_at":"2026-07-05T11:13:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.10882/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, the scientific community has questioned the statistical reproducibility of many empirical results, especially in the field of machine learning. To contribute to the resolution of this reproducibility crisis, we propose a theoretically sound methodology for comparing the performance of a set of algorithms. We exemplify our methodology in Deep Reinforcement Learning (Deep RL). The performance of one execution of a Deep RL algorithm is a random variable. Therefore, several independent executions are needed to evaluate its performance. When comparing algorithms with random performance, a","authors_text":"Alena Shilova, Hector Kohler, Matheus Medeiros Centa, Odalric-Ambrym Maillard, Philippe Preux, Riccardo Della Vecchia, Timoth\\'ee Mathieu","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-19T12:22:56Z","title":"AdaStop: adaptive statistical testing for sound comparisons of Deep RL agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10882","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6fdf00933bc67db730b0e7385e59d805cce462e9d5a9df4e864b8cd1fa4f3b50","target":"record","created_at":"2026-07-05T11:13:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e4b70930598291f024fad3b49a4d5a9c73e02e000dafd50c914ce8052a39b83d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-19T12:22:56Z","title_canon_sha256":"c5c1671682c4cfe84e91d26d602fda1a217cbdaae4e256e2f01618918f55269d"},"schema_version":"1.0","source":{"id":"2306.10882","kind":"arxiv","version":3}},"canonical_sha256":"aee20e77f1cce52fee61e1fd1d297beb32f604d51c6b8833cf35f66f26e0bf49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aee20e77f1cce52fee61e1fd1d297beb32f604d51c6b8833cf35f66f26e0bf49","first_computed_at":"2026-07-05T11:13:05.315971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:05.315971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AG7fU0C4usbwGu+LkgXW3me30gpV/d6nN80mdgpFO3UCoCNCziputpyn2gwQne6GXLQw/wkTJNG95SoYwxmFAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:05.316507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.10882","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fdf00933bc67db730b0e7385e59d805cce462e9d5a9df4e864b8cd1fa4f3b50","sha256:4f74290aaff9ea8fa6a0faff0befbb533a760288e42009570b801ef45682670e"],"state_sha256":"21a1a8a4aeae4a251513789d37c67a5d2b20a4e942343f5c7b25994a977caee6"}