{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZYXQIT4PR5T462S7RCS5YTGJFD","short_pith_number":"pith:ZYXQIT4P","canonical_record":{"source":{"id":"2006.05990","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T17:59:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4af9e13ef012a5295aab85ec338c0dc010f1dd620c2fd9cb26ed743690db76c5","abstract_canon_sha256":"2311d2c1f9c7b47d9516703ff319e0cba2bac1424021cb5bd6c033eb91d65b58"},"schema_version":"1.0"},"canonical_sha256":"ce2f044f8f8f67cf6a5f88a5dc4cc928f5270ec52565eda1708830b8ceb67ec0","source":{"kind":"arxiv","id":"2006.05990","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05990","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05990v1","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05990","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZYXQIT4PR5T4","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZYXQIT4PR5T462S7","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZYXQIT4P","created_at":"2026-07-05T01:09:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZYXQIT4PR5T462S7RCS5YTGJFD","target":"record","payload":{"canonical_record":{"source":{"id":"2006.05990","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T17:59:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4af9e13ef012a5295aab85ec338c0dc010f1dd620c2fd9cb26ed743690db76c5","abstract_canon_sha256":"2311d2c1f9c7b47d9516703ff319e0cba2bac1424021cb5bd6c033eb91d65b58"},"schema_version":"1.0"},"canonical_sha256":"ce2f044f8f8f67cf6a5f88a5dc4cc928f5270ec52565eda1708830b8ceb67ec0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:18.729891Z","signature_b64":"xoXVFn02S/62uPV/Xss7dUy7n4oZl9Az1JC4BlAkNSfqC6BkjRqhYrzmjjMtTrYZg0zbvA1cZWP+hO7wgn4BAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce2f044f8f8f67cf6a5f88a5dc4cc928f5270ec52565eda1708830b8ceb67ec0","last_reissued_at":"2026-07-05T01:09:18.729408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:18.729408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.05990","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"spE+ijgz16yLpVEVLEfYrHM/pqoqZ4jH8VmpVFw2ItSPtNltS8LZeyjJipgRohi9aUmwKE9gYrw+VtgMOP5kDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:12:06.957937Z"},"content_sha256":"ed66e74c2a95f485b8bb9e65f389c1308cd3a22969a3a7dd16dc5584428870af","schema_version":"1.0","event_id":"sha256:ed66e74c2a95f485b8bb9e65f389c1308cd3a22969a3a7dd16dc5584428870af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZYXQIT4PR5T462S7RCS5YTGJFD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anton Raichuk, L\\'eonard Hussenot, Manu Orsini, Marcin Andrychowicz, Marcin Michalski, Matthieu Geist, Olivier Bachem, Olivier Pietquin, Piotr Sta\\'nczyk, Raphael Marinier, Sertan Girgin, Sylvain Gelly","submitted_at":"2020-06-10T17:59:03Z","abstract_excerpt":"In recent years, on-policy reinforcement learning (RL) has been successfully applied to many different continuous control tasks. While RL algorithms are often conceptually simple, their state-of-the-art implementations take numerous low- and high-level design decisions that strongly affect the performance of the resulting agents. Those choices are usually not extensively discussed in the literature, leading to discrepancy between published descriptions of algorithms and their implementations. This makes it hard to attribute progress in RL and slows down overall progress [Engstrom'20]. As a ste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05990","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/2006.05990/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":"2026-07-05T01:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GtiowF4/fP6tS5uw53AmkCJJwJvg/38OpX6u6XJgdLXJInuC807lhVfAJYcDtCfywuKKSO/yWCf7BnxbMJ/nAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:12:06.958461Z"},"content_sha256":"958c79bcebb7951f355f0a8bfd3e766dbe71dd21a49adc57dadd716144c903e0","schema_version":"1.0","event_id":"sha256:958c79bcebb7951f355f0a8bfd3e766dbe71dd21a49adc57dadd716144c903e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYXQIT4PR5T462S7RCS5YTGJFD/bundle.json","state_url":"https://pith.science/pith/ZYXQIT4PR5T462S7RCS5YTGJFD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYXQIT4PR5T462S7RCS5YTGJFD/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":"2026-08-19T21:12:06Z","links":{"resolver":"https://pith.science/pith/ZYXQIT4PR5T462S7RCS5YTGJFD","bundle":"https://pith.science/pith/ZYXQIT4PR5T462S7RCS5YTGJFD/bundle.json","state":"https://pith.science/pith/ZYXQIT4PR5T462S7RCS5YTGJFD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYXQIT4PR5T462S7RCS5YTGJFD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZYXQIT4PR5T462S7RCS5YTGJFD","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":"2311d2c1f9c7b47d9516703ff319e0cba2bac1424021cb5bd6c033eb91d65b58","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T17:59:03Z","title_canon_sha256":"4af9e13ef012a5295aab85ec338c0dc010f1dd620c2fd9cb26ed743690db76c5"},"schema_version":"1.0","source":{"id":"2006.05990","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05990","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05990v1","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05990","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZYXQIT4PR5T4","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZYXQIT4PR5T462S7","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZYXQIT4P","created_at":"2026-07-05T01:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:958c79bcebb7951f355f0a8bfd3e766dbe71dd21a49adc57dadd716144c903e0","target":"graph","created_at":"2026-07-05T01:09:18Z","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/2006.05990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, on-policy reinforcement learning (RL) has been successfully applied to many different continuous control tasks. While RL algorithms are often conceptually simple, their state-of-the-art implementations take numerous low- and high-level design decisions that strongly affect the performance of the resulting agents. Those choices are usually not extensively discussed in the literature, leading to discrepancy between published descriptions of algorithms and their implementations. This makes it hard to attribute progress in RL and slows down overall progress [Engstrom'20]. As a ste","authors_text":"Anton Raichuk, L\\'eonard Hussenot, Manu Orsini, Marcin Andrychowicz, Marcin Michalski, Matthieu Geist, Olivier Bachem, Olivier Pietquin, Piotr Sta\\'nczyk, Raphael Marinier, Sertan Girgin, Sylvain Gelly","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T17:59:03Z","title":"What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05990","kind":"arxiv","version":1},"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:ed66e74c2a95f485b8bb9e65f389c1308cd3a22969a3a7dd16dc5584428870af","target":"record","created_at":"2026-07-05T01:09:18Z","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":"2311d2c1f9c7b47d9516703ff319e0cba2bac1424021cb5bd6c033eb91d65b58","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T17:59:03Z","title_canon_sha256":"4af9e13ef012a5295aab85ec338c0dc010f1dd620c2fd9cb26ed743690db76c5"},"schema_version":"1.0","source":{"id":"2006.05990","kind":"arxiv","version":1}},"canonical_sha256":"ce2f044f8f8f67cf6a5f88a5dc4cc928f5270ec52565eda1708830b8ceb67ec0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce2f044f8f8f67cf6a5f88a5dc4cc928f5270ec52565eda1708830b8ceb67ec0","first_computed_at":"2026-07-05T01:09:18.729408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:18.729408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xoXVFn02S/62uPV/Xss7dUy7n4oZl9Az1JC4BlAkNSfqC6BkjRqhYrzmjjMtTrYZg0zbvA1cZWP+hO7wgn4BAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:18.729891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.05990","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed66e74c2a95f485b8bb9e65f389c1308cd3a22969a3a7dd16dc5584428870af","sha256:958c79bcebb7951f355f0a8bfd3e766dbe71dd21a49adc57dadd716144c903e0"],"state_sha256":"1c9167ae1832341da20230d00d6c69e82acc3fd20dd98283f493e37695a1c937"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uXr0HtgFftOH2zVAXN9PUdTaovJc26hD4oj0B3U2+Fer+se6ygAHNv4cb9G7PJUpN+vdqlBptb69T1nP9DmPDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T21:12:06.962944Z","bundle_sha256":"8bbc034c8336578abe0906264b3f8f2cd9acbdb21ef250953afad9c1559d49ab"}}