{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MU7SFV3WXGSHQOE4YP4ZA4XM5Y","short_pith_number":"pith:MU7SFV3W","canonical_record":{"source":{"id":"2606.07550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T14:09:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af4026aab6465a2d2f85600cca9bd299fa1a8c542c2375b82854bcb6de1b81cc","abstract_canon_sha256":"f075986f0573d0dedfb1bc2c775811d1ab4cd74f5dde42bb8528a88e3329f587"},"schema_version":"1.0"},"canonical_sha256":"653f22d776b9a478389cc3f99072ecee3ac6536d347b631080632d5acb18b9a1","source":{"kind":"arxiv","id":"2606.07550","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MU7SFV3WXGSHQOE4YP4ZA4XM5Y","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T14:09:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af4026aab6465a2d2f85600cca9bd299fa1a8c542c2375b82854bcb6de1b81cc","abstract_canon_sha256":"f075986f0573d0dedfb1bc2c775811d1ab4cd74f5dde42bb8528a88e3329f587"},"schema_version":"1.0"},"canonical_sha256":"653f22d776b9a478389cc3f99072ecee3ac6536d347b631080632d5acb18b9a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:42.716718Z","signature_b64":"Y30qvuKMF82yCMkwi36bNhNe/Y4HF3meSZsB3Gl0vWcLG0JLx0FQkHuYS7ZscPZ5zqYnk8+zfoWnytjOpT6/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"653f22d776b9a478389cc3f99072ecee3ac6536d347b631080632d5acb18b9a1","last_reissued_at":"2026-06-09T00:04:42.716115Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:42.716115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07550","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":"2026-06-09T00:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OMD1nlHtG5zFqI06Zm5iQjRyZGp/uRsOVbboVLanFGRuC+V/8KZglu22wsNelK9khL7nwO3nWVqEAUHMh5bgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T18:14:53.450990Z"},"content_sha256":"34383715f7abed386766d79265354fdeeb6714b4358d3caadaa8d80d8f44863b","schema_version":"1.0","event_id":"sha256:34383715f7abed386766d79265354fdeeb6714b4358d3caadaa8d80d8f44863b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MU7SFV3WXGSHQOE4YP4ZA4XM5Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aravind Venugopal, Haomin Bao, Jeff Schneider, Jiayu Chen, Rohit Sonker, Xiaoyan Hu, Yang Fu","submitted_at":"2026-05-19T14:09:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07550","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/2606.07550/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":"2026-06-09T00:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XMA/Vi/vUktIaRXrgX1CLXf53a4F5MYcR27s7kgZpnWljH0EPzDM53LS/eig7VFLCKqGiu9Ck6srCBIOGSQWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T18:14:53.451378Z"},"content_sha256":"b9571fdfb404d94fbda40de1e6e3b93b3013d767135cbe769ff1ccad476a527c","schema_version":"1.0","event_id":"sha256:b9571fdfb404d94fbda40de1e6e3b93b3013d767135cbe769ff1ccad476a527c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MU7SFV3WXGSHQOE4YP4ZA4XM5Y/bundle.json","state_url":"https://pith.science/pith/MU7SFV3WXGSHQOE4YP4ZA4XM5Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MU7SFV3WXGSHQOE4YP4ZA4XM5Y/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":"2026-07-03T18:14:53Z","links":{"resolver":"https://pith.science/pith/MU7SFV3WXGSHQOE4YP4ZA4XM5Y","bundle":"https://pith.science/pith/MU7SFV3WXGSHQOE4YP4ZA4XM5Y/bundle.json","state":"https://pith.science/pith/MU7SFV3WXGSHQOE4YP4ZA4XM5Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MU7SFV3WXGSHQOE4YP4ZA4XM5Y/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e/EBMrX4WsY1aVAON4+o7csXfHTL69c3jLSsyp2QUerXFB5k6G2RyiTtwKwwmdmSxBY8fhzwj1fvP2F7Dl0QDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T18:14:53.453400Z","bundle_sha256":"6314d0e71fed7b717cfa54ee76e6687b416f99ef075ae20133d749cf3af1cd09"}}