{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4P7QGLYKW3VGQGOPK6BMLC4XOO","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":"fb28e97d1da8a4abcf3dbf66f92c89de0a180f131e6c14a89fdaed17865567bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-29T09:36:36Z","title_canon_sha256":"2712eb77ec4256057ef76ba91f578add8b7e62b68d7a3276a33c8f71bc757e84"},"schema_version":"1.0","source":{"id":"2106.15200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.15200","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"arxiv_version","alias_value":"2106.15200v1","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15200","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"pith_short_12","alias_value":"4P7QGLYKW3VG","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"pith_short_16","alias_value":"4P7QGLYKW3VGQGOP","created_at":"2026-07-05T02:53:14Z"},{"alias_kind":"pith_short_8","alias_value":"4P7QGLYK","created_at":"2026-07-05T02:53:14Z"}],"graph_snapshots":[{"event_id":"sha256:740e01631c3017666f2524e7af0f88b2e94d4cc27c0fa465c348790f29498321","target":"graph","created_at":"2026-07-05T02:53:14Z","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/2106.15200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Maintaining the stability of the modern power grid is becoming increasingly difficult due to fluctuating power consumption, unstable power supply coming from renewable energies, and unpredictable accidents such as man-made and natural disasters. As the operation on the power grid must consider its impact on future stability, reinforcement learning (RL) has been employed to provide sequential decision-making in power grid management. However, existing methods have not considered the environmental constraints. As a result, the learned policy has risk of selecting actions that violate the constra","authors_text":"Bo Zhou, Fan Wang, Hao Tian, Hongsheng Zeng, Kejiao Li, Yuecheng Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-29T09:36:36Z","title":"Action Set Based Policy Optimization for Safe Power Grid Management"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15200","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":"sha256:5460e6df1d3b945193b2d91aa9eeef5db551592f7ff5e309e8743677026bc18c","target":"record","created_at":"2026-07-05T02:53:14Z","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":"fb28e97d1da8a4abcf3dbf66f92c89de0a180f131e6c14a89fdaed17865567bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-29T09:36:36Z","title_canon_sha256":"2712eb77ec4256057ef76ba91f578add8b7e62b68d7a3276a33c8f71bc757e84"},"schema_version":"1.0","source":{"id":"2106.15200","kind":"arxiv","version":1}},"canonical_sha256":"e3ff032f0ab6ea6819cf5782c58b9773961eedb8abf5b2448cd4d500fd4c085f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3ff032f0ab6ea6819cf5782c58b9773961eedb8abf5b2448cd4d500fd4c085f","first_computed_at":"2026-07-05T02:53:14.704308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:53:14.704308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q7RP5M+Iu+CG99UNL4FwL4oRNDo9BLpi8olLFR3EvjbISAsu2GKPh50OIBzlyafhr3MNQYjvSU/841Bg6r0IAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:53:14.704791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.15200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5460e6df1d3b945193b2d91aa9eeef5db551592f7ff5e309e8743677026bc18c","sha256:740e01631c3017666f2524e7af0f88b2e94d4cc27c0fa465c348790f29498321"],"state_sha256":"cba9edf5c3bacd72770743ba8a314b4f91efcec37478903940e3327a8b9a9dde"}