{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4P7QGLYKW3VGQGOPK6BMLC4XOO","short_pith_number":"pith:4P7QGLYK","schema_version":"1.0","canonical_sha256":"e3ff032f0ab6ea6819cf5782c58b9773961eedb8abf5b2448cd4d500fd4c085f","source":{"kind":"arxiv","id":"2106.15200","version":1},"attestation_state":"computed","paper":{"title":"Action Set Based Policy Optimization for Safe Power Grid Management","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Zhou, Fan Wang, Hao Tian, Hongsheng Zeng, Kejiao Li, Yuecheng Liu","submitted_at":"2021-06-29T09:36:36Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.15200","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-29T09:36:36Z","cross_cats_sorted":[],"title_canon_sha256":"2712eb77ec4256057ef76ba91f578add8b7e62b68d7a3276a33c8f71bc757e84","abstract_canon_sha256":"fb28e97d1da8a4abcf3dbf66f92c89de0a180f131e6c14a89fdaed17865567bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:53:14.704791Z","signature_b64":"q7RP5M+Iu+CG99UNL4FwL4oRNDo9BLpi8olLFR3EvjbISAsu2GKPh50OIBzlyafhr3MNQYjvSU/841Bg6r0IAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3ff032f0ab6ea6819cf5782c58b9773961eedb8abf5b2448cd4d500fd4c085f","last_reissued_at":"2026-07-05T02:53:14.704308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:53:14.704308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action Set Based Policy Optimization for Safe Power Grid Management","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Zhou, Fan Wang, Hao Tian, Hongsheng Zeng, Kejiao Li, Yuecheng Liu","submitted_at":"2021-06-29T09:36:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15200","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/2106.15200/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.15200","created_at":"2026-07-05T02:53:14.704373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15200v1","created_at":"2026-07-05T02:53:14.704373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15200","created_at":"2026-07-05T02:53:14.704373+00:00"},{"alias_kind":"pith_short_12","alias_value":"4P7QGLYKW3VG","created_at":"2026-07-05T02:53:14.704373+00:00"},{"alias_kind":"pith_short_16","alias_value":"4P7QGLYKW3VGQGOP","created_at":"2026-07-05T02:53:14.704373+00:00"},{"alias_kind":"pith_short_8","alias_value":"4P7QGLYK","created_at":"2026-07-05T02:53:14.704373+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00561","citing_title":"Interpretable Policy Distillation for Power Grid Topology Control","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4P7QGLYKW3VGQGOPK6BMLC4XOO","json":"https://pith.science/pith/4P7QGLYKW3VGQGOPK6BMLC4XOO.json","graph_json":"https://pith.science/api/pith-number/4P7QGLYKW3VGQGOPK6BMLC4XOO/graph.json","events_json":"https://pith.science/api/pith-number/4P7QGLYKW3VGQGOPK6BMLC4XOO/events.json","paper":"https://pith.science/paper/4P7QGLYK"},"agent_actions":{"view_html":"https://pith.science/pith/4P7QGLYKW3VGQGOPK6BMLC4XOO","download_json":"https://pith.science/pith/4P7QGLYKW3VGQGOPK6BMLC4XOO.json","view_paper":"https://pith.science/paper/4P7QGLYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15200&json=true","fetch_graph":"https://pith.science/api/pith-number/4P7QGLYKW3VGQGOPK6BMLC4XOO/graph.json","fetch_events":"https://pith.science/api/pith-number/4P7QGLYKW3VGQGOPK6BMLC4XOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4P7QGLYKW3VGQGOPK6BMLC4XOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4P7QGLYKW3VGQGOPK6BMLC4XOO/action/storage_attestation","attest_author":"https://pith.science/pith/4P7QGLYKW3VGQGOPK6BMLC4XOO/action/author_attestation","sign_citation":"https://pith.science/pith/4P7QGLYKW3VGQGOPK6BMLC4XOO/action/citation_signature","submit_replication":"https://pith.science/pith/4P7QGLYKW3VGQGOPK6BMLC4XOO/action/replication_record"}},"created_at":"2026-07-05T02:53:14.704373+00:00","updated_at":"2026-07-05T02:53:14.704373+00:00"}