{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MU7SFV3WXGSHQOE4YP4ZA4XM5Y","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":"f075986f0573d0dedfb1bc2c775811d1ab4cd74f5dde42bb8528a88e3329f587","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T14:09:29Z","title_canon_sha256":"af4026aab6465a2d2f85600cca9bd299fa1a8c542c2375b82854bcb6de1b81cc"},"schema_version":"1.0","source":{"id":"2606.07550","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07550","created_at":"2026-06-09T00:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07550v1","created_at":"2026-06-09T00:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07550","created_at":"2026-06-09T00:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"MU7SFV3WXGSH","created_at":"2026-06-09T00:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"MU7SFV3WXGSHQOE4","created_at":"2026-06-09T00:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"MU7SFV3W","created_at":"2026-06-09T00:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:b9571fdfb404d94fbda40de1e6e3b93b3013d767135cbe769ff1ccad476a527c","target":"graph","created_at":"2026-06-09T00:04:42Z","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/2606.07550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) offers a promising route for developing plasma controllers from historical tokamak data, since online trial-and-error on real devices is costly and risky. However, progress in this direction remains difficult to measure due to the lack of a standardized offline RL benchmark for realistic multi-actuator, long-horizon plasma control problems in nuclear fusion. We introduce RL4F, an Offline Reinforcement Learning Benchmark for Plasma Control in Nuclear Fusion, providing closed-loop evaluation environments and baseline comparisons across four full-profile tracki","authors_text":"Aravind Venugopal, Haomin Bao, Jeff Schneider, Jiayu Chen, Rohit Sonker, Xiaoyan Hu, Yang Fu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T14:09:29Z","title":"Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07550","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":"sha256:34383715f7abed386766d79265354fdeeb6714b4358d3caadaa8d80d8f44863b","target":"record","created_at":"2026-06-09T00:04:42Z","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":"f075986f0573d0dedfb1bc2c775811d1ab4cd74f5dde42bb8528a88e3329f587","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T14:09:29Z","title_canon_sha256":"af4026aab6465a2d2f85600cca9bd299fa1a8c542c2375b82854bcb6de1b81cc"},"schema_version":"1.0","source":{"id":"2606.07550","kind":"arxiv","version":1}},"canonical_sha256":"653f22d776b9a478389cc3f99072ecee3ac6536d347b631080632d5acb18b9a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"653f22d776b9a478389cc3f99072ecee3ac6536d347b631080632d5acb18b9a1","first_computed_at":"2026-06-09T00:04:42.716115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T00:04:42.716115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y30qvuKMF82yCMkwi36bNhNe/Y4HF3meSZsB3Gl0vWcLG0JLx0FQkHuYS7ZscPZ5zqYnk8+zfoWnytjOpT6/Dg==","signature_status":"signed_v1","signed_at":"2026-06-09T00:04:42.716718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07550","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34383715f7abed386766d79265354fdeeb6714b4358d3caadaa8d80d8f44863b","sha256:b9571fdfb404d94fbda40de1e6e3b93b3013d767135cbe769ff1ccad476a527c"],"state_sha256":"665f025e7ee2f65e2b174a4365998680fb9bd343c764091bddeb71e3f9e2e1ed"}