{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NISVINTPEG44HOWYBLGRR5QH42","short_pith_number":"pith:NISVINTP","schema_version":"1.0","canonical_sha256":"6a2554366f21b9c3bad80acd18f607e697309c396beeb385e637b27a6a0c99fa","source":{"kind":"arxiv","id":"2406.01575","version":2},"attestation_state":"computed","paper":{"title":"Contextual Bilevel Reinforcement Learning for Incentive Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Andreas Krause, Barna Pasztor, Giorgia Ramponi, Vinzenz Thoma, Yifan Hu","submitted_at":"2024-06-03T17:54:39Z","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"},"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":"2406.01575","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-03T17:54:39Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"45982e1b2a1b6137b306eeebd0eb9a0b5d7026131de93286e1a08bb3a78f3986","abstract_canon_sha256":"2b820e18b23aa3081c4b3ec909f49a192f4b25df920a00a18d4128b3a1bbeefc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:49.757729Z","signature_b64":"h6Cpl9zr+29By1BSTFNE1yYMcjwQrkL2hRr8IMFTQ9x8ofTq2qaQWSOtMkjYxLwBW7vRTCjZCaiUweOiPDZSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a2554366f21b9c3bad80acd18f607e697309c396beeb385e637b27a6a0c99fa","last_reissued_at":"2026-07-05T09:45:49.757224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:49.757224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Bilevel Reinforcement Learning for Incentive Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Andreas Krause, Barna Pasztor, Giorgia Ramponi, Vinzenz Thoma, Yifan Hu","submitted_at":"2024-06-03T17:54:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01575","kind":"arxiv","version":2},"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/2406.01575/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":"2406.01575","created_at":"2026-07-05T09:45:49.757286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01575v2","created_at":"2026-07-05T09:45:49.757286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01575","created_at":"2026-07-05T09:45:49.757286+00:00"},{"alias_kind":"pith_short_12","alias_value":"NISVINTPEG44","created_at":"2026-07-05T09:45:49.757286+00:00"},{"alias_kind":"pith_short_16","alias_value":"NISVINTPEG44HOWY","created_at":"2026-07-05T09:45:49.757286+00:00"},{"alias_kind":"pith_short_8","alias_value":"NISVINTP","created_at":"2026-07-05T09:45:49.757286+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09429","citing_title":"ADAGE: A generic two-layer framework for adaptive agent based modelling","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NISVINTPEG44HOWYBLGRR5QH42","json":"https://pith.science/pith/NISVINTPEG44HOWYBLGRR5QH42.json","graph_json":"https://pith.science/api/pith-number/NISVINTPEG44HOWYBLGRR5QH42/graph.json","events_json":"https://pith.science/api/pith-number/NISVINTPEG44HOWYBLGRR5QH42/events.json","paper":"https://pith.science/paper/NISVINTP"},"agent_actions":{"view_html":"https://pith.science/pith/NISVINTPEG44HOWYBLGRR5QH42","download_json":"https://pith.science/pith/NISVINTPEG44HOWYBLGRR5QH42.json","view_paper":"https://pith.science/paper/NISVINTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01575&json=true","fetch_graph":"https://pith.science/api/pith-number/NISVINTPEG44HOWYBLGRR5QH42/graph.json","fetch_events":"https://pith.science/api/pith-number/NISVINTPEG44HOWYBLGRR5QH42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NISVINTPEG44HOWYBLGRR5QH42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NISVINTPEG44HOWYBLGRR5QH42/action/storage_attestation","attest_author":"https://pith.science/pith/NISVINTPEG44HOWYBLGRR5QH42/action/author_attestation","sign_citation":"https://pith.science/pith/NISVINTPEG44HOWYBLGRR5QH42/action/citation_signature","submit_replication":"https://pith.science/pith/NISVINTPEG44HOWYBLGRR5QH42/action/replication_record"}},"created_at":"2026-07-05T09:45:49.757286+00:00","updated_at":"2026-07-05T09:45:49.757286+00:00"}