{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NLNQ27NGEXSBZWSTH6RM4EKXVA","short_pith_number":"pith:NLNQ27NG","schema_version":"1.0","canonical_sha256":"6adb0d7da625e41cda533fa2ce1157a80d80e24042f3d1138f5e6ae6320f3342","source":{"kind":"arxiv","id":"2606.00561","version":1},"attestation_state":"computed","paper":{"title":"Interpretable Policy Distillation for Power Grid Topology Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksandra Dmitruka, Karlis Freivalds","submitted_at":"2026-05-30T06:32:55Z","abstract_excerpt":"Deep reinforcement learning (RL) offers a promising route to real-time power grid operation, yet large neural policies are costly to evaluate, hard to deploy on constrained hardware, and opaque to operators. We ask whether a Proximal Policy Optimization (PPO) agent for grid topology control can be compressed into compact tree-based surrogates without losing operational performance. A PPO teacher is trained on Grid2Op's standard 14-bus environment with a stability-oriented reward, using stress-focused data collection on critical, high-loading states. The policy is then distilled into a decision"},"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":"2606.00561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T06:32:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a31b7d7dc97f9c19417163705750fa6c331c9f512cdcfeff1b45296115b217fd","abstract_canon_sha256":"1554a2d73a755b814a8d6db6177db4bb10e9b823dbc79b444a579dc690aeed17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:58.313999Z","signature_b64":"8OljxedWtgXVPBL9G3DdG0ga3p1zH739WeyT1cX7ssYWl3YwUFaSz+P2OUS4pYKF6Sjs75G1o3ggfe3AelLlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6adb0d7da625e41cda533fa2ce1157a80d80e24042f3d1138f5e6ae6320f3342","last_reissued_at":"2026-06-02T01:03:58.313458Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:58.313458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Policy Distillation for Power Grid Topology Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksandra Dmitruka, Karlis Freivalds","submitted_at":"2026-05-30T06:32:55Z","abstract_excerpt":"Deep reinforcement learning (RL) offers a promising route to real-time power grid operation, yet large neural policies are costly to evaluate, hard to deploy on constrained hardware, and opaque to operators. We ask whether a Proximal Policy Optimization (PPO) agent for grid topology control can be compressed into compact tree-based surrogates without losing operational performance. A PPO teacher is trained on Grid2Op's standard 14-bus environment with a stability-oriented reward, using stress-focused data collection on critical, high-loading states. The policy is then distilled into a decision"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00561","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/2606.00561/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":"2606.00561","created_at":"2026-06-02T01:03:58.313543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00561v1","created_at":"2026-06-02T01:03:58.313543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00561","created_at":"2026-06-02T01:03:58.313543+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLNQ27NGEXSB","created_at":"2026-06-02T01:03:58.313543+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLNQ27NGEXSBZWST","created_at":"2026-06-02T01:03:58.313543+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLNQ27NG","created_at":"2026-06-02T01:03:58.313543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NLNQ27NGEXSBZWSTH6RM4EKXVA","json":"https://pith.science/pith/NLNQ27NGEXSBZWSTH6RM4EKXVA.json","graph_json":"https://pith.science/api/pith-number/NLNQ27NGEXSBZWSTH6RM4EKXVA/graph.json","events_json":"https://pith.science/api/pith-number/NLNQ27NGEXSBZWSTH6RM4EKXVA/events.json","paper":"https://pith.science/paper/NLNQ27NG"},"agent_actions":{"view_html":"https://pith.science/pith/NLNQ27NGEXSBZWSTH6RM4EKXVA","download_json":"https://pith.science/pith/NLNQ27NGEXSBZWSTH6RM4EKXVA.json","view_paper":"https://pith.science/paper/NLNQ27NG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00561&json=true","fetch_graph":"https://pith.science/api/pith-number/NLNQ27NGEXSBZWSTH6RM4EKXVA/graph.json","fetch_events":"https://pith.science/api/pith-number/NLNQ27NGEXSBZWSTH6RM4EKXVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLNQ27NGEXSBZWSTH6RM4EKXVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLNQ27NGEXSBZWSTH6RM4EKXVA/action/storage_attestation","attest_author":"https://pith.science/pith/NLNQ27NGEXSBZWSTH6RM4EKXVA/action/author_attestation","sign_citation":"https://pith.science/pith/NLNQ27NGEXSBZWSTH6RM4EKXVA/action/citation_signature","submit_replication":"https://pith.science/pith/NLNQ27NGEXSBZWSTH6RM4EKXVA/action/replication_record"}},"created_at":"2026-06-02T01:03:58.313543+00:00","updated_at":"2026-06-02T01:03:58.313543+00:00"}