{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NISVINTPEG44HOWYBLGRR5QH42","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":"2b820e18b23aa3081c4b3ec909f49a192f4b25df920a00a18d4128b3a1bbeefc","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-03T17:54:39Z","title_canon_sha256":"45982e1b2a1b6137b306eeebd0eb9a0b5d7026131de93286e1a08bb3a78f3986"},"schema_version":"1.0","source":{"id":"2406.01575","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01575","created_at":"2026-07-05T09:45:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01575v2","created_at":"2026-07-05T09:45:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01575","created_at":"2026-07-05T09:45:49Z"},{"alias_kind":"pith_short_12","alias_value":"NISVINTPEG44","created_at":"2026-07-05T09:45:49Z"},{"alias_kind":"pith_short_16","alias_value":"NISVINTPEG44HOWY","created_at":"2026-07-05T09:45:49Z"},{"alias_kind":"pith_short_8","alias_value":"NISVINTP","created_at":"2026-07-05T09:45:49Z"}],"graph_snapshots":[{"event_id":"sha256:fc7a0fb04cfef33e98a83ff286e2aabcc8187a50aeb5488e83151e3a3fb160e2","target":"graph","created_at":"2026-07-05T09:45:49Z","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/2406.01575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The optimal policy in various real-world strategic decision-making problems depends both on the environmental configuration and exogenous events. For these settings, we introduce Contextual Bilevel Reinforcement Learning (CB-RL), a stochastic bilevel decision-making model, where the lower level consists of solving a contextual Markov Decision Process (CMDP). CB-RL can be viewed as a Stackelberg Game where the leader and a random context beyond the leader's control together decide the setup of many MDPs that potentially multiple followers best respond to. This framework extends beyond tradition","authors_text":"Andreas Krause, Barna Pasztor, Giorgia Ramponi, Vinzenz Thoma, Yifan Hu","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-03T17:54:39Z","title":"Contextual Bilevel Reinforcement Learning for Incentive Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01575","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:daaa46da5166640cc781f3b7bfcee994262d7a0224fbd762d4c6e6b50fde46c6","target":"record","created_at":"2026-07-05T09:45:49Z","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":"2b820e18b23aa3081c4b3ec909f49a192f4b25df920a00a18d4128b3a1bbeefc","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-03T17:54:39Z","title_canon_sha256":"45982e1b2a1b6137b306eeebd0eb9a0b5d7026131de93286e1a08bb3a78f3986"},"schema_version":"1.0","source":{"id":"2406.01575","kind":"arxiv","version":2}},"canonical_sha256":"6a2554366f21b9c3bad80acd18f607e697309c396beeb385e637b27a6a0c99fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a2554366f21b9c3bad80acd18f607e697309c396beeb385e637b27a6a0c99fa","first_computed_at":"2026-07-05T09:45:49.757224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:49.757224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h6Cpl9zr+29By1BSTFNE1yYMcjwQrkL2hRr8IMFTQ9x8ofTq2qaQWSOtMkjYxLwBW7vRTCjZCaiUweOiPDZSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:49.757729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01575","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:daaa46da5166640cc781f3b7bfcee994262d7a0224fbd762d4c6e6b50fde46c6","sha256:fc7a0fb04cfef33e98a83ff286e2aabcc8187a50aeb5488e83151e3a3fb160e2"],"state_sha256":"f24b1fe67980a189653db1b1865eb14a60b92ea8b0e0f384337c28a3034bcf9f"}