{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:35MD76XKGAI2GVIRMWO4CP3WP4","short_pith_number":"pith:35MD76XK","schema_version":"1.0","canonical_sha256":"df583ffaea3011a35511659dc13f767f1e37dd0b703d65e4d0d9e2ac4ffb924d","source":{"kind":"arxiv","id":"2304.07407","version":2},"attestation_state":"computed","paper":{"title":"Repeated Principal-Agent Games with Unobserved Agent Rewards and Perfect-Knowledge Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anil Aswani, Ilgin Dogan, Zuo-Jun Max Shen","submitted_at":"2023-04-14T21:57:16Z","abstract_excerpt":"Motivated by a number of real-world applications from domains like healthcare and sustainable transportation, in this paper we study a scenario of repeated principal-agent games within a multi-armed bandit (MAB) framework, where: the principal gives a different incentive for each bandit arm, the agent picks a bandit arm to maximize its own expected reward plus incentive, and the principal observes which arm is chosen and receives a reward (different than that of the agent) for the chosen arm. Designing policies for the principal is challenging because the principal cannot directly observe the "},"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":"2304.07407","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-14T21:57:16Z","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"title_canon_sha256":"fa0e76bc21a31c57ea7d13e144c2fb77960d19c2e364d07acf5dad0e1d439a62","abstract_canon_sha256":"8e823fb6d04ce6a3e68442a18a14b8331045fa021c88cf2a2612293e0055531b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:38.404707Z","signature_b64":"1zp+AqT3nRxTUzShtURQxiC7wp5Aeu5KbOWAUcc/FFobFsNZG4JWJSXhKULELIYvGfQ9m9IiR2jKn9iUQeF7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df583ffaea3011a35511659dc13f767f1e37dd0b703d65e4d0d9e2ac4ffb924d","last_reissued_at":"2026-07-05T06:07:38.404247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:38.404247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Repeated Principal-Agent Games with Unobserved Agent Rewards and Perfect-Knowledge Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anil Aswani, Ilgin Dogan, Zuo-Jun Max Shen","submitted_at":"2023-04-14T21:57:16Z","abstract_excerpt":"Motivated by a number of real-world applications from domains like healthcare and sustainable transportation, in this paper we study a scenario of repeated principal-agent games within a multi-armed bandit (MAB) framework, where: the principal gives a different incentive for each bandit arm, the agent picks a bandit arm to maximize its own expected reward plus incentive, and the principal observes which arm is chosen and receives a reward (different than that of the agent) for the chosen arm. Designing policies for the principal is challenging because the principal cannot directly observe the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07407","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/2304.07407/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":"2304.07407","created_at":"2026-07-05T06:07:38.404358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.07407v2","created_at":"2026-07-05T06:07:38.404358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07407","created_at":"2026-07-05T06:07:38.404358+00:00"},{"alias_kind":"pith_short_12","alias_value":"35MD76XKGAI2","created_at":"2026-07-05T06:07:38.404358+00:00"},{"alias_kind":"pith_short_16","alias_value":"35MD76XKGAI2GVIR","created_at":"2026-07-05T06:07:38.404358+00:00"},{"alias_kind":"pith_short_8","alias_value":"35MD76XK","created_at":"2026-07-05T06:07:38.404358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00158","citing_title":"Moral Hazard in LTI Dynamics: A Hypothesis Testing Approach","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35MD76XKGAI2GVIRMWO4CP3WP4","json":"https://pith.science/pith/35MD76XKGAI2GVIRMWO4CP3WP4.json","graph_json":"https://pith.science/api/pith-number/35MD76XKGAI2GVIRMWO4CP3WP4/graph.json","events_json":"https://pith.science/api/pith-number/35MD76XKGAI2GVIRMWO4CP3WP4/events.json","paper":"https://pith.science/paper/35MD76XK"},"agent_actions":{"view_html":"https://pith.science/pith/35MD76XKGAI2GVIRMWO4CP3WP4","download_json":"https://pith.science/pith/35MD76XKGAI2GVIRMWO4CP3WP4.json","view_paper":"https://pith.science/paper/35MD76XK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.07407&json=true","fetch_graph":"https://pith.science/api/pith-number/35MD76XKGAI2GVIRMWO4CP3WP4/graph.json","fetch_events":"https://pith.science/api/pith-number/35MD76XKGAI2GVIRMWO4CP3WP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35MD76XKGAI2GVIRMWO4CP3WP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35MD76XKGAI2GVIRMWO4CP3WP4/action/storage_attestation","attest_author":"https://pith.science/pith/35MD76XKGAI2GVIRMWO4CP3WP4/action/author_attestation","sign_citation":"https://pith.science/pith/35MD76XKGAI2GVIRMWO4CP3WP4/action/citation_signature","submit_replication":"https://pith.science/pith/35MD76XKGAI2GVIRMWO4CP3WP4/action/replication_record"}},"created_at":"2026-07-05T06:07:38.404358+00:00","updated_at":"2026-07-05T06:07:38.404358+00:00"}