{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:Y5POH3PWYHZDIQUBU322ZF56RX","short_pith_number":"pith:Y5POH3PW","canonical_record":{"source":{"id":"2108.13264","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-30T14:23:48Z","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"title_canon_sha256":"6c829853fdb66010aa5af3f0979e859c178ef5ed6a9f2d7ad54348463f3e830e","abstract_canon_sha256":"4782fa0b4ff7d664b122209fee880c4fbf362ff4512eaa11b296853d77177c49"},"schema_version":"1.0"},"canonical_sha256":"c75ee3edf6c1f2344281a6f5ac97be8dfef244f3beae6961b037c2f487b496db","source":{"kind":"arxiv","id":"2108.13264","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.13264","created_at":"2026-07-05T03:46:13Z"},{"alias_kind":"arxiv_version","alias_value":"2108.13264v4","created_at":"2026-07-05T03:46:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13264","created_at":"2026-07-05T03:46:13Z"},{"alias_kind":"pith_short_12","alias_value":"Y5POH3PWYHZD","created_at":"2026-07-05T03:46:13Z"},{"alias_kind":"pith_short_16","alias_value":"Y5POH3PWYHZDIQUB","created_at":"2026-07-05T03:46:13Z"},{"alias_kind":"pith_short_8","alias_value":"Y5POH3PW","created_at":"2026-07-05T03:46:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:Y5POH3PWYHZDIQUBU322ZF56RX","target":"record","payload":{"canonical_record":{"source":{"id":"2108.13264","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-30T14:23:48Z","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"title_canon_sha256":"6c829853fdb66010aa5af3f0979e859c178ef5ed6a9f2d7ad54348463f3e830e","abstract_canon_sha256":"4782fa0b4ff7d664b122209fee880c4fbf362ff4512eaa11b296853d77177c49"},"schema_version":"1.0"},"canonical_sha256":"c75ee3edf6c1f2344281a6f5ac97be8dfef244f3beae6961b037c2f487b496db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:13.827012Z","signature_b64":"UDtK+duKTvJk746gq/EfTOAn0al7wVzArmRkLbmoJ07pL/9vrvQAPBRZrTj/C4AbAPvFNgtcpVoCmITzDl68Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c75ee3edf6c1f2344281a6f5ac97be8dfef244f3beae6961b037c2f487b496db","last_reissued_at":"2026-07-05T03:46:13.826451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:13.826451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.13264","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:46:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oSl80lJ4jyOMg+RRwd5j1QGa+Qjcih9AY64AynTqjQSrQ13+8dFk8hRMGA2SF7LZloiy7KePHm4C/a+BY+c5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:49:51.514637Z"},"content_sha256":"7457b263afa7d81e5956f86003f562caffc15a8528bfaf34c613c9bd2f02097a","schema_version":"1.0","event_id":"sha256:7457b263afa7d81e5956f86003f562caffc15a8528bfaf34c613c9bd2f02097a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:Y5POH3PWYHZDIQUBU322ZF56RX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Marc G. Bellemare, Max Schwarzer, Pablo Samuel Castro, Rishabh Agarwal","submitted_at":"2021-08-30T14:23:48Z","abstract_excerpt":"Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing their relative performance on a large suite of tasks. Most published results on deep RL benchmarks compare point estimates of aggregate performance such as mean and median scores across tasks, ignoring the statistical uncertainty implied by the use of a finite number of training runs. Beginning with the Arcade Learning Environment (ALE), the shift towards computationally-demanding benchmarks has led to the practice of evaluating only a small number of runs per task, exacerbating the statistical uncertainty in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13264","kind":"arxiv","version":4},"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/2108.13264/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:46:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GPqPK0oGyp4PiQOdjVqrKnpAwUWwATvgKFFK4hSMDFY7dspAh6ixDL6QtiHF+FejKRRYY16IyzyXPz2o0ZwBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:49:51.515265Z"},"content_sha256":"31a41995e97e2bb522f7fd60b7fb9b30046dc9e86437312d39077259f716633f","schema_version":"1.0","event_id":"sha256:31a41995e97e2bb522f7fd60b7fb9b30046dc9e86437312d39077259f716633f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5POH3PWYHZDIQUBU322ZF56RX/bundle.json","state_url":"https://pith.science/pith/Y5POH3PWYHZDIQUBU322ZF56RX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5POH3PWYHZDIQUBU322ZF56RX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T02:49:51Z","links":{"resolver":"https://pith.science/pith/Y5POH3PWYHZDIQUBU322ZF56RX","bundle":"https://pith.science/pith/Y5POH3PWYHZDIQUBU322ZF56RX/bundle.json","state":"https://pith.science/pith/Y5POH3PWYHZDIQUBU322ZF56RX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5POH3PWYHZDIQUBU322ZF56RX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Y5POH3PWYHZDIQUBU322ZF56RX","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":"4782fa0b4ff7d664b122209fee880c4fbf362ff4512eaa11b296853d77177c49","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-30T14:23:48Z","title_canon_sha256":"6c829853fdb66010aa5af3f0979e859c178ef5ed6a9f2d7ad54348463f3e830e"},"schema_version":"1.0","source":{"id":"2108.13264","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.13264","created_at":"2026-07-05T03:46:13Z"},{"alias_kind":"arxiv_version","alias_value":"2108.13264v4","created_at":"2026-07-05T03:46:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13264","created_at":"2026-07-05T03:46:13Z"},{"alias_kind":"pith_short_12","alias_value":"Y5POH3PWYHZD","created_at":"2026-07-05T03:46:13Z"},{"alias_kind":"pith_short_16","alias_value":"Y5POH3PWYHZDIQUB","created_at":"2026-07-05T03:46:13Z"},{"alias_kind":"pith_short_8","alias_value":"Y5POH3PW","created_at":"2026-07-05T03:46:13Z"}],"graph_snapshots":[{"event_id":"sha256:31a41995e97e2bb522f7fd60b7fb9b30046dc9e86437312d39077259f716633f","target":"graph","created_at":"2026-07-05T03:46:13Z","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/2108.13264/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing their relative performance on a large suite of tasks. Most published results on deep RL benchmarks compare point estimates of aggregate performance such as mean and median scores across tasks, ignoring the statistical uncertainty implied by the use of a finite number of training runs. Beginning with the Arcade Learning Environment (ALE), the shift towards computationally-demanding benchmarks has led to the practice of evaluating only a small number of runs per task, exacerbating the statistical uncertainty in ","authors_text":"Aaron Courville, Marc G. Bellemare, Max Schwarzer, Pablo Samuel Castro, Rishabh Agarwal","cross_cats":["cs.AI","stat.ME","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-30T14:23:48Z","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13264","kind":"arxiv","version":4},"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":"sha256:7457b263afa7d81e5956f86003f562caffc15a8528bfaf34c613c9bd2f02097a","target":"record","created_at":"2026-07-05T03:46:13Z","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":"4782fa0b4ff7d664b122209fee880c4fbf362ff4512eaa11b296853d77177c49","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-30T14:23:48Z","title_canon_sha256":"6c829853fdb66010aa5af3f0979e859c178ef5ed6a9f2d7ad54348463f3e830e"},"schema_version":"1.0","source":{"id":"2108.13264","kind":"arxiv","version":4}},"canonical_sha256":"c75ee3edf6c1f2344281a6f5ac97be8dfef244f3beae6961b037c2f487b496db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c75ee3edf6c1f2344281a6f5ac97be8dfef244f3beae6961b037c2f487b496db","first_computed_at":"2026-07-05T03:46:13.826451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:13.826451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UDtK+duKTvJk746gq/EfTOAn0al7wVzArmRkLbmoJ07pL/9vrvQAPBRZrTj/C4AbAPvFNgtcpVoCmITzDl68Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:13.827012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.13264","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7457b263afa7d81e5956f86003f562caffc15a8528bfaf34c613c9bd2f02097a","sha256:31a41995e97e2bb522f7fd60b7fb9b30046dc9e86437312d39077259f716633f"],"state_sha256":"1fc7edc5bdc4e41fdd7d14383c17715e8818f14758550cb45b8134569c16aa47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BB7geqapnO/wFur5ANH0FQZIRriQyc0EwqeKmtISfUw5x1mlYGZhRxsielpIuTvezX3WfheVGPRIlbHxSv7hDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:49:51.520251Z","bundle_sha256":"1d912dd4a1106c2dc6f41aa8b98222ffab1e8ce8c29f968424a433b29686b330"}}