{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QVKAIGKRUNJVVE54WRSXIOTBH5","short_pith_number":"pith:QVKAIGKR","canonical_record":{"source":{"id":"1902.07015","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-19T12:20:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8d243e974787c7408134415263b13e1d26423283e23dc76b88d63835909b563d","abstract_canon_sha256":"9bc98df880d724b96ebb7f87ab2e78f121a82bb7521a20cb1512a7db5a40450c"},"schema_version":"1.0"},"canonical_sha256":"8554041951a3535a93bcb465743a613f54e4e74a52e3d12d8e002cf99f62f13d","source":{"kind":"arxiv","id":"1902.07015","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07015","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07015v2","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07015","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"QVKAIGKRUNJV","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QVKAIGKRUNJVVE54","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QVKAIGKR","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QVKAIGKRUNJVVE54WRSXIOTBH5","target":"record","payload":{"canonical_record":{"source":{"id":"1902.07015","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-19T12:20:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8d243e974787c7408134415263b13e1d26423283e23dc76b88d63835909b563d","abstract_canon_sha256":"9bc98df880d724b96ebb7f87ab2e78f121a82bb7521a20cb1512a7db5a40450c"},"schema_version":"1.0"},"canonical_sha256":"8554041951a3535a93bcb465743a613f54e4e74a52e3d12d8e002cf99f62f13d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:08.566676Z","signature_b64":"17Pk+Q+CR9JVfQB7qGlgWuLwH9b+fOmgoEJmY/kB7UZN6+Zet+GqBaIFOEQlQMf3OQg4zAWaMpsun1+uy1BICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8554041951a3535a93bcb465743a613f54e4e74a52e3d12d8e002cf99f62f13d","last_reissued_at":"2026-05-17T23:53:08.565971Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:08.565971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.07015","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GjLilV30T35yccCdl/8PqIy/VQJvzkpmbJzmUk40wMNAAwpTv3e0a26jk/Xxlue6QxNJ8zL2d0PVtJug1yicDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:57:05.745132Z"},"content_sha256":"57ab0c80a4504d9f0029da8b4205772fb49128afc53c9ade5f7eb55d8e745dc3","schema_version":"1.0","event_id":"sha256:57ab0c80a4504d9f0029da8b4205772fb49128afc53c9ade5f7eb55d8e745dc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QVKAIGKRUNJVVE54WRSXIOTBH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Generalisation in Continuous Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chenyang Zhao, Freek Stulp, Olivier Sigaud, Timothy M. Hospedales","submitted_at":"2019-02-19T12:20:36Z","abstract_excerpt":"Deep Reinforcement Learning has shown great success in a variety of control tasks. However, it is unclear how close we are to the vision of putting Deep RL into practice to solve real world problems. In particular, common practice in the field is to train policies on largely deterministic simulators and to evaluate algorithms through training performance alone, without a train/test distinction to ensure models generalise and are not overfitted. Moreover, it is not standard practice to check for generalisation under domain shift, although robustness to such system change between training and te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07015","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+lS+4gG8usVGkF++Ee3RZA6wEHq/FR/7ZJqZ6u7sc8dmMPOKg6MwFgSRiH+aDz6I0NQ5M4p1HuvLNMQecTU+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:57:05.745494Z"},"content_sha256":"37968989b6d22acc8bc8e6b6f32470d7c49981199fb83545ccd4e7f10eb5026a","schema_version":"1.0","event_id":"sha256:37968989b6d22acc8bc8e6b6f32470d7c49981199fb83545ccd4e7f10eb5026a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVKAIGKRUNJVVE54WRSXIOTBH5/bundle.json","state_url":"https://pith.science/pith/QVKAIGKRUNJVVE54WRSXIOTBH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVKAIGKRUNJVVE54WRSXIOTBH5/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":"2026-06-01T12:57:05Z","links":{"resolver":"https://pith.science/pith/QVKAIGKRUNJVVE54WRSXIOTBH5","bundle":"https://pith.science/pith/QVKAIGKRUNJVVE54WRSXIOTBH5/bundle.json","state":"https://pith.science/pith/QVKAIGKRUNJVVE54WRSXIOTBH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVKAIGKRUNJVVE54WRSXIOTBH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QVKAIGKRUNJVVE54WRSXIOTBH5","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":"9bc98df880d724b96ebb7f87ab2e78f121a82bb7521a20cb1512a7db5a40450c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-19T12:20:36Z","title_canon_sha256":"8d243e974787c7408134415263b13e1d26423283e23dc76b88d63835909b563d"},"schema_version":"1.0","source":{"id":"1902.07015","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07015","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07015v2","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07015","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"QVKAIGKRUNJV","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QVKAIGKRUNJVVE54","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QVKAIGKR","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:37968989b6d22acc8bc8e6b6f32470d7c49981199fb83545ccd4e7f10eb5026a","target":"graph","created_at":"2026-05-17T23:53:08Z","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"},"paper":{"abstract_excerpt":"Deep Reinforcement Learning has shown great success in a variety of control tasks. However, it is unclear how close we are to the vision of putting Deep RL into practice to solve real world problems. In particular, common practice in the field is to train policies on largely deterministic simulators and to evaluate algorithms through training performance alone, without a train/test distinction to ensure models generalise and are not overfitted. Moreover, it is not standard practice to check for generalisation under domain shift, although robustness to such system change between training and te","authors_text":"Chenyang Zhao, Freek Stulp, Olivier Sigaud, Timothy M. Hospedales","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-19T12:20:36Z","title":"Investigating Generalisation in Continuous Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07015","kind":"arxiv","version":2},"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":"sha256:57ab0c80a4504d9f0029da8b4205772fb49128afc53c9ade5f7eb55d8e745dc3","target":"record","created_at":"2026-05-17T23:53:08Z","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":"9bc98df880d724b96ebb7f87ab2e78f121a82bb7521a20cb1512a7db5a40450c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-19T12:20:36Z","title_canon_sha256":"8d243e974787c7408134415263b13e1d26423283e23dc76b88d63835909b563d"},"schema_version":"1.0","source":{"id":"1902.07015","kind":"arxiv","version":2}},"canonical_sha256":"8554041951a3535a93bcb465743a613f54e4e74a52e3d12d8e002cf99f62f13d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8554041951a3535a93bcb465743a613f54e4e74a52e3d12d8e002cf99f62f13d","first_computed_at":"2026-05-17T23:53:08.565971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:08.565971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"17Pk+Q+CR9JVfQB7qGlgWuLwH9b+fOmgoEJmY/kB7UZN6+Zet+GqBaIFOEQlQMf3OQg4zAWaMpsun1+uy1BICg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:08.566676Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.07015","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57ab0c80a4504d9f0029da8b4205772fb49128afc53c9ade5f7eb55d8e745dc3","sha256:37968989b6d22acc8bc8e6b6f32470d7c49981199fb83545ccd4e7f10eb5026a"],"state_sha256":"5baffead9b5a4749f55431cf65e674c45df476e3ff7baebe1f3a3543fd1a626d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WPf0Q9aFX6lGRRFLf7UaahRNXODKAay5MztyZJ4Am9czz5BPyUj32ZQ4zzAOyisEof3hvCbQbeRLG3xHyHliCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T12:57:05.748100Z","bundle_sha256":"ef75537f05da712a9a9fb575838018968deb2228524ee42e957d6030b1d9315b"}}