{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NP4MKKXZLIL7UQP4OEVPI3EECR","short_pith_number":"pith:NP4MKKXZ","canonical_record":{"source":{"id":"1907.11971","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-07-27T20:05:52Z","cross_cats_sorted":[],"title_canon_sha256":"765edd69c2d9c73c63ba59f4e7e97030b85a2723a925009b07223eeb6af372b5","abstract_canon_sha256":"28c6de219b38ebc7e2291c67b0be2cf03c87ea60cbdcec1bf748210565a105f2"},"schema_version":"1.0"},"canonical_sha256":"6bf8c52af95a17fa41fc712af46c841454280286a74709a8661fd25f3612ed42","source":{"kind":"arxiv","id":"1907.11971","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11971","created_at":"2026-07-04T23:50:04Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11971v1","created_at":"2026-07-04T23:50:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11971","created_at":"2026-07-04T23:50:04Z"},{"alias_kind":"pith_short_12","alias_value":"NP4MKKXZLIL7","created_at":"2026-07-04T23:50:04Z"},{"alias_kind":"pith_short_16","alias_value":"NP4MKKXZLIL7UQP4","created_at":"2026-07-04T23:50:04Z"},{"alias_kind":"pith_short_8","alias_value":"NP4MKKXZ","created_at":"2026-07-04T23:50:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NP4MKKXZLIL7UQP4OEVPI3EECR","target":"record","payload":{"canonical_record":{"source":{"id":"1907.11971","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-07-27T20:05:52Z","cross_cats_sorted":[],"title_canon_sha256":"765edd69c2d9c73c63ba59f4e7e97030b85a2723a925009b07223eeb6af372b5","abstract_canon_sha256":"28c6de219b38ebc7e2291c67b0be2cf03c87ea60cbdcec1bf748210565a105f2"},"schema_version":"1.0"},"canonical_sha256":"6bf8c52af95a17fa41fc712af46c841454280286a74709a8661fd25f3612ed42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:50:04.189130Z","signature_b64":"aqXRqXEICrGm1aYstOXDt9BQ1R2eNT2cb5teEbwbMmIjd0lHr3X06qyb13bNvUcaLSN+014j50AtyVtikvYWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bf8c52af95a17fa41fc712af46c841454280286a74709a8661fd25f3612ed42","last_reissued_at":"2026-07-04T23:50:04.188682Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:50:04.188682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.11971","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":"2026-07-04T23:50:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Gg4jUGygUD0iq3pxSJzsCQD+rIUNRmeGwhblRgI33f0ceh3wnK46m6g0T9jJIeU5rwBy7BfAHJHeWsxSQ/kBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:34:21.107857Z"},"content_sha256":"8c851313245123c0266f959aa63b4d3ee224d4ffcdd6056c530cd0277db12fbf","schema_version":"1.0","event_id":"sha256:8c851313245123c0266f959aa63b4d3ee224d4ffcdd6056c530cd0277db12fbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NP4MKKXZLIL7UQP4OEVPI3EECR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Model-based Reinforcement Learning for Industry-near Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Morten Goodwin, Ole-Christoffer Granmo, Per-Arne Andersen","submitted_at":"2019-07-27T20:05:52Z","abstract_excerpt":"Deep reinforcement learning has over the past few years shown great potential in learning near-optimal control in complex simulated environments with little visible information. Rainbow (Q-Learning) and PPO (Policy Optimisation) have shown outstanding performance in a variety of tasks, including Atari 2600, MuJoCo, and Roboschool test suite. While these algorithms are fundamentally different, both suffer from high variance, low sample efficiency, and hyperparameter sensitivity that in practice, make these algorithms a no-go for critical operations in the industry.\n  On the other hand, model-ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11971","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/1907.11971/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":"2026-07-04T23:50:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1JjO4ZaqKWBBRkfvvycsSzikLRWN8oaZ0ZrcJvcYi7KZ1yC52O0yDVv4Y99vHbwCAX2rPoNHrkYnIDpoohRKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:34:21.108226Z"},"content_sha256":"38073ada73cdbb7c38be35efdb17d432694062bbbeec136247e189dbda7f1ec5","schema_version":"1.0","event_id":"sha256:38073ada73cdbb7c38be35efdb17d432694062bbbeec136247e189dbda7f1ec5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NP4MKKXZLIL7UQP4OEVPI3EECR/bundle.json","state_url":"https://pith.science/pith/NP4MKKXZLIL7UQP4OEVPI3EECR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NP4MKKXZLIL7UQP4OEVPI3EECR/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":"2026-07-07T11:34:21Z","links":{"resolver":"https://pith.science/pith/NP4MKKXZLIL7UQP4OEVPI3EECR","bundle":"https://pith.science/pith/NP4MKKXZLIL7UQP4OEVPI3EECR/bundle.json","state":"https://pith.science/pith/NP4MKKXZLIL7UQP4OEVPI3EECR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NP4MKKXZLIL7UQP4OEVPI3EECR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NP4MKKXZLIL7UQP4OEVPI3EECR","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":"28c6de219b38ebc7e2291c67b0be2cf03c87ea60cbdcec1bf748210565a105f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-07-27T20:05:52Z","title_canon_sha256":"765edd69c2d9c73c63ba59f4e7e97030b85a2723a925009b07223eeb6af372b5"},"schema_version":"1.0","source":{"id":"1907.11971","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11971","created_at":"2026-07-04T23:50:04Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11971v1","created_at":"2026-07-04T23:50:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11971","created_at":"2026-07-04T23:50:04Z"},{"alias_kind":"pith_short_12","alias_value":"NP4MKKXZLIL7","created_at":"2026-07-04T23:50:04Z"},{"alias_kind":"pith_short_16","alias_value":"NP4MKKXZLIL7UQP4","created_at":"2026-07-04T23:50:04Z"},{"alias_kind":"pith_short_8","alias_value":"NP4MKKXZ","created_at":"2026-07-04T23:50:04Z"}],"graph_snapshots":[{"event_id":"sha256:38073ada73cdbb7c38be35efdb17d432694062bbbeec136247e189dbda7f1ec5","target":"graph","created_at":"2026-07-04T23:50:04Z","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/1907.11971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning has over the past few years shown great potential in learning near-optimal control in complex simulated environments with little visible information. Rainbow (Q-Learning) and PPO (Policy Optimisation) have shown outstanding performance in a variety of tasks, including Atari 2600, MuJoCo, and Roboschool test suite. While these algorithms are fundamentally different, both suffer from high variance, low sample efficiency, and hyperparameter sensitivity that in practice, make these algorithms a no-go for critical operations in the industry.\n  On the other hand, model-ba","authors_text":"Morten Goodwin, Ole-Christoffer Granmo, Per-Arne Andersen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-07-27T20:05:52Z","title":"Towards Model-based Reinforcement Learning for Industry-near Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11971","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":"sha256:8c851313245123c0266f959aa63b4d3ee224d4ffcdd6056c530cd0277db12fbf","target":"record","created_at":"2026-07-04T23:50:04Z","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":"28c6de219b38ebc7e2291c67b0be2cf03c87ea60cbdcec1bf748210565a105f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-07-27T20:05:52Z","title_canon_sha256":"765edd69c2d9c73c63ba59f4e7e97030b85a2723a925009b07223eeb6af372b5"},"schema_version":"1.0","source":{"id":"1907.11971","kind":"arxiv","version":1}},"canonical_sha256":"6bf8c52af95a17fa41fc712af46c841454280286a74709a8661fd25f3612ed42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bf8c52af95a17fa41fc712af46c841454280286a74709a8661fd25f3612ed42","first_computed_at":"2026-07-04T23:50:04.188682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:50:04.188682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aqXRqXEICrGm1aYstOXDt9BQ1R2eNT2cb5teEbwbMmIjd0lHr3X06qyb13bNvUcaLSN+014j50AtyVtikvYWDA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:50:04.189130Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.11971","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c851313245123c0266f959aa63b4d3ee224d4ffcdd6056c530cd0277db12fbf","sha256:38073ada73cdbb7c38be35efdb17d432694062bbbeec136247e189dbda7f1ec5"],"state_sha256":"e998a33e31b3f891c22beb46e64dd0b745581cc0411dbb95945bbb2a3da80eaf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ibSq1L43GklOGMgWREBk5SgA3CRjBzT6m+1kqehUSkwbkzfEkAFxa+t30+MJavmeg+ghkdSAa7XpfLHTXcZ8Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:34:21.110175Z","bundle_sha256":"e635a19ae3caa155fc521fb9c3ede4ad61f14abb54b03a8aec12289fd7c41dad"}}