{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3GY45U5OGLXDCSCGCKKUJZ7QP4","short_pith_number":"pith:3GY45U5O","canonical_record":{"source":{"id":"2307.11546","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.plasm-ph","submitted_at":"2023-07-21T12:47:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c3d9e8adcef849c8773cc345fd46287b9091b29c45ab53a864e07c6e7a1c355","abstract_canon_sha256":"86ddd8953ef42595c5e20e28143bffa90fca3d396e0341157890fcec6dac0145"},"schema_version":"1.0"},"canonical_sha256":"d9b1ced3ae32ee314846129544e7f07f157d75dde7fb034f04611c310b9d3867","source":{"kind":"arxiv","id":"2307.11546","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.11546","created_at":"2026-07-05T06:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"2307.11546v2","created_at":"2026-07-05T06:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11546","created_at":"2026-07-05T06:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"3GY45U5OGLXD","created_at":"2026-07-05T06:57:24Z"},{"alias_kind":"pith_short_16","alias_value":"3GY45U5OGLXDCSCG","created_at":"2026-07-05T06:57:24Z"},{"alias_kind":"pith_short_8","alias_value":"3GY45U5O","created_at":"2026-07-05T06:57:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3GY45U5OGLXDCSCGCKKUJZ7QP4","target":"record","payload":{"canonical_record":{"source":{"id":"2307.11546","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.plasm-ph","submitted_at":"2023-07-21T12:47:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c3d9e8adcef849c8773cc345fd46287b9091b29c45ab53a864e07c6e7a1c355","abstract_canon_sha256":"86ddd8953ef42595c5e20e28143bffa90fca3d396e0341157890fcec6dac0145"},"schema_version":"1.0"},"canonical_sha256":"d9b1ced3ae32ee314846129544e7f07f157d75dde7fb034f04611c310b9d3867","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:24.830146Z","signature_b64":"WPej2TjynyixYAR56A1JbZxNCF7+as4QaEKzn9bk1isICSMR65NajOcPxz7ipb7R2t2KjFe5+gKvEJSb0+ipCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9b1ced3ae32ee314846129544e7f07f157d75dde7fb034f04611c310b9d3867","last_reissued_at":"2026-07-05T06:57:24.829681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:24.829681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.11546","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":"2026-07-05T06:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ue0kNNyejeIWaVfRNgpIunUuLTF9Ls2rnKDG9b8gmkYdOHICQSjiZjMzHmSyQ6ulyrSYXl6uyBnx7S7hS53yCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:13:12.716271Z"},"content_sha256":"e262f76de41e39db2fefb3c82d61cdc88b81fb257c188e2fa194fcacc363a909","schema_version":"1.0","event_id":"sha256:e262f76de41e39db2fefb3c82d61cdc88b81fb257c188e2fa194fcacc363a909"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3GY45U5OGLXDCSCGCKKUJZ7QP4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards practical reinforcement learning for tokamak magnetic control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.plasm-ph","authors_text":"Andrea Huber, Andrea Michi, Brendan D. Tracey, Cosmin Paduraru, Craig Donner, Cristian Galperti, Daniel J. Mankowitz, Federico Felici, Ian Davies, Jonas Buchli, Jonathan Evens, Martin Riedmiller, Michael Neunert, Nevena Lazic, Paula Kurylowicz, The TCV Team, Timo Ewalds, Yuri Chervonyi","submitted_at":"2023-07-21T12:47:28Z","abstract_excerpt":"Reinforcement learning (RL) has shown promising results for real-time control systems, including the domain of plasma magnetic control. However, there are still significant drawbacks compared to traditional feedback control approaches for magnetic confinement. In this work, we address key drawbacks of the RL method; achieving higher control accuracy for desired plasma properties, reducing the steady-state error, and decreasing the required time to learn new tasks. We build on top of \\cite{degrave2022magnetic}, and present algorithmic improvements to the agent architecture and training procedur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11546","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.11546/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":"2026-07-05T06:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yNXKZt1ASQwzUjOcHAxjJr9z5d+HEpPvsGMq2LZy34GmLgYlRTc3Whn4hqntTxiUOT6Okl9xB456RG983s3YCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:13:12.716937Z"},"content_sha256":"5780764b614e0cc97c5c2d3ba73dca2bbc3864259e1374d144aab7350fa63bc8","schema_version":"1.0","event_id":"sha256:5780764b614e0cc97c5c2d3ba73dca2bbc3864259e1374d144aab7350fa63bc8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GY45U5OGLXDCSCGCKKUJZ7QP4/bundle.json","state_url":"https://pith.science/pith/3GY45U5OGLXDCSCGCKKUJZ7QP4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GY45U5OGLXDCSCGCKKUJZ7QP4/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":"2026-07-05T14:13:12Z","links":{"resolver":"https://pith.science/pith/3GY45U5OGLXDCSCGCKKUJZ7QP4","bundle":"https://pith.science/pith/3GY45U5OGLXDCSCGCKKUJZ7QP4/bundle.json","state":"https://pith.science/pith/3GY45U5OGLXDCSCGCKKUJZ7QP4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GY45U5OGLXDCSCGCKKUJZ7QP4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3GY45U5OGLXDCSCGCKKUJZ7QP4","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":"86ddd8953ef42595c5e20e28143bffa90fca3d396e0341157890fcec6dac0145","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.plasm-ph","submitted_at":"2023-07-21T12:47:28Z","title_canon_sha256":"9c3d9e8adcef849c8773cc345fd46287b9091b29c45ab53a864e07c6e7a1c355"},"schema_version":"1.0","source":{"id":"2307.11546","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.11546","created_at":"2026-07-05T06:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"2307.11546v2","created_at":"2026-07-05T06:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11546","created_at":"2026-07-05T06:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"3GY45U5OGLXD","created_at":"2026-07-05T06:57:24Z"},{"alias_kind":"pith_short_16","alias_value":"3GY45U5OGLXDCSCG","created_at":"2026-07-05T06:57:24Z"},{"alias_kind":"pith_short_8","alias_value":"3GY45U5O","created_at":"2026-07-05T06:57:24Z"}],"graph_snapshots":[{"event_id":"sha256:5780764b614e0cc97c5c2d3ba73dca2bbc3864259e1374d144aab7350fa63bc8","target":"graph","created_at":"2026-07-05T06:57:24Z","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/2307.11546/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has shown promising results for real-time control systems, including the domain of plasma magnetic control. However, there are still significant drawbacks compared to traditional feedback control approaches for magnetic confinement. In this work, we address key drawbacks of the RL method; achieving higher control accuracy for desired plasma properties, reducing the steady-state error, and decreasing the required time to learn new tasks. We build on top of \\cite{degrave2022magnetic}, and present algorithmic improvements to the agent architecture and training procedur","authors_text":"Andrea Huber, Andrea Michi, Brendan D. Tracey, Cosmin Paduraru, Craig Donner, Cristian Galperti, Daniel J. Mankowitz, Federico Felici, Ian Davies, Jonas Buchli, Jonathan Evens, Martin Riedmiller, Michael Neunert, Nevena Lazic, Paula Kurylowicz, The TCV Team, Timo Ewalds, Yuri Chervonyi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.plasm-ph","submitted_at":"2023-07-21T12:47:28Z","title":"Towards practical reinforcement learning for tokamak magnetic control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11546","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:e262f76de41e39db2fefb3c82d61cdc88b81fb257c188e2fa194fcacc363a909","target":"record","created_at":"2026-07-05T06:57:24Z","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":"86ddd8953ef42595c5e20e28143bffa90fca3d396e0341157890fcec6dac0145","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.plasm-ph","submitted_at":"2023-07-21T12:47:28Z","title_canon_sha256":"9c3d9e8adcef849c8773cc345fd46287b9091b29c45ab53a864e07c6e7a1c355"},"schema_version":"1.0","source":{"id":"2307.11546","kind":"arxiv","version":2}},"canonical_sha256":"d9b1ced3ae32ee314846129544e7f07f157d75dde7fb034f04611c310b9d3867","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9b1ced3ae32ee314846129544e7f07f157d75dde7fb034f04611c310b9d3867","first_computed_at":"2026-07-05T06:57:24.829681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:24.829681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WPej2TjynyixYAR56A1JbZxNCF7+as4QaEKzn9bk1isICSMR65NajOcPxz7ipb7R2t2KjFe5+gKvEJSb0+ipCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:24.830146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.11546","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e262f76de41e39db2fefb3c82d61cdc88b81fb257c188e2fa194fcacc363a909","sha256:5780764b614e0cc97c5c2d3ba73dca2bbc3864259e1374d144aab7350fa63bc8"],"state_sha256":"e5c6891f971a65ec71976de6a08d04d7d796ee80af046b1aa7ce3dde8a4afe51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"72hIBwun6MCdO9X4a0A7eBPOO12XWSvAWcbXRf0aEVgVqDvqhLpVzFzimrOr9dktiT2C+OFWkqD7OFQ4s9n9Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:13:12.720526Z","bundle_sha256":"52c7ed6e97f89880bb8dc00debf4551ba58336475442f8daa1ace227b938f0d5"}}