{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3UM7BWU4FCHVEOSSZV6BONRA7Y","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":"af640445e66a9b712ee95527abd371ad7a1fbc7d7f8d3e3c60c235dbb35cd523","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T14:39:17Z","title_canon_sha256":"b3d477a918ae315d26275a8c330c3d0f6af49e72bfd76caf5f92eb1bc3004a7a"},"schema_version":"1.0","source":{"id":"2503.23101","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23101","created_at":"2026-07-05T11:24:17Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23101v2","created_at":"2026-07-05T11:24:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23101","created_at":"2026-07-05T11:24:17Z"},{"alias_kind":"pith_short_12","alias_value":"3UM7BWU4FCHV","created_at":"2026-07-05T11:24:17Z"},{"alias_kind":"pith_short_16","alias_value":"3UM7BWU4FCHVEOSS","created_at":"2026-07-05T11:24:17Z"},{"alias_kind":"pith_short_8","alias_value":"3UM7BWU4","created_at":"2026-07-05T11:24:17Z"}],"graph_snapshots":[{"event_id":"sha256:382602facb04bb1d311020840c3f9ba83a3041100db9788961b9cda34434ca27","target":"graph","created_at":"2026-07-05T11:24:17Z","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/2503.23101/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) can provide adaptive and scalable controllers essential for power grid decarbonization. However, RL methods struggle with power grids' complex dynamics, long-horizon goals, and hard physical constraints. For these reasons, we present RL2Grid, a benchmark designed in collaboration with power system operators to accelerate progress in grid control and foster RL maturity. Built on RTE France's power simulation framework, RL2Grid standardizes tasks, state and action spaces, and reward structures for a systematic evaluation and comparison of RL algorithms. Moreover, we i","authors_text":"Antoine Marot, Benjamin Donnot, Cathy Wu, Christian Merz, Constance Crozier, Enrico Marchesini, Ian Dytham, Lars Schewe, Nico Westerbeck, Priya L. Donti","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T14:39:17Z","title":"RL2Grid: Benchmarking Reinforcement Learning in Power Grid Operations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23101","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:a1ac25c2d09625ab3ebeef0e9108a4fc854279c53b022f73d199cf55747cef3b","target":"record","created_at":"2026-07-05T11:24:17Z","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":"af640445e66a9b712ee95527abd371ad7a1fbc7d7f8d3e3c60c235dbb35cd523","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T14:39:17Z","title_canon_sha256":"b3d477a918ae315d26275a8c330c3d0f6af49e72bfd76caf5f92eb1bc3004a7a"},"schema_version":"1.0","source":{"id":"2503.23101","kind":"arxiv","version":2}},"canonical_sha256":"dd19f0da9c288f523a52cd7c173620fe0cabeecc854eeee9ad520c2c47c8c36f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd19f0da9c288f523a52cd7c173620fe0cabeecc854eeee9ad520c2c47c8c36f","first_computed_at":"2026-07-05T11:24:17.582744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:17.582744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/xq8mYovM/CYGoUgoD7eElfH1/8/C5bW6u4Ixtjikp/7WYv6vKlFKrds9OwLdBSFy5LcKs1DPoPypFhT0b7DCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:17.583265Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23101","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1ac25c2d09625ab3ebeef0e9108a4fc854279c53b022f73d199cf55747cef3b","sha256:382602facb04bb1d311020840c3f9ba83a3041100db9788961b9cda34434ca27"],"state_sha256":"7bdc1175ae4aec07fb30a9d2c504184e3edee44a0b79d784acfad2e86c6c46d3"}