{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:35MD76XKGAI2GVIRMWO4CP3WP4","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":"8e823fb6d04ce6a3e68442a18a14b8331045fa021c88cf2a2612293e0055531b","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-14T21:57:16Z","title_canon_sha256":"fa0e76bc21a31c57ea7d13e144c2fb77960d19c2e364d07acf5dad0e1d439a62"},"schema_version":"1.0","source":{"id":"2304.07407","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.07407","created_at":"2026-07-05T06:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"2304.07407v2","created_at":"2026-07-05T06:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07407","created_at":"2026-07-05T06:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"35MD76XKGAI2","created_at":"2026-07-05T06:07:38Z"},{"alias_kind":"pith_short_16","alias_value":"35MD76XKGAI2GVIR","created_at":"2026-07-05T06:07:38Z"},{"alias_kind":"pith_short_8","alias_value":"35MD76XK","created_at":"2026-07-05T06:07:38Z"}],"graph_snapshots":[{"event_id":"sha256:36d9b5901db6b710038b016ba2e66bfb20f7cd8eed1e99f97f819a22eccef7b8","target":"graph","created_at":"2026-07-05T06:07:38Z","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/2304.07407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Anil Aswani, Ilgin Dogan, Zuo-Jun Max Shen","cross_cats":["cs.AI","cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-14T21:57:16Z","title":"Repeated Principal-Agent Games with Unobserved Agent Rewards and Perfect-Knowledge Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07407","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:eeb7714b16caef8915bf414d3225a274ff4317e95462b25b781c148db74aff98","target":"record","created_at":"2026-07-05T06:07:38Z","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":"8e823fb6d04ce6a3e68442a18a14b8331045fa021c88cf2a2612293e0055531b","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-14T21:57:16Z","title_canon_sha256":"fa0e76bc21a31c57ea7d13e144c2fb77960d19c2e364d07acf5dad0e1d439a62"},"schema_version":"1.0","source":{"id":"2304.07407","kind":"arxiv","version":2}},"canonical_sha256":"df583ffaea3011a35511659dc13f767f1e37dd0b703d65e4d0d9e2ac4ffb924d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df583ffaea3011a35511659dc13f767f1e37dd0b703d65e4d0d9e2ac4ffb924d","first_computed_at":"2026-07-05T06:07:38.404247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:38.404247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1zp+AqT3nRxTUzShtURQxiC7wp5Aeu5KbOWAUcc/FFobFsNZG4JWJSXhKULELIYvGfQ9m9IiR2jKn9iUQeF7Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:38.404707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.07407","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeb7714b16caef8915bf414d3225a274ff4317e95462b25b781c148db74aff98","sha256:36d9b5901db6b710038b016ba2e66bfb20f7cd8eed1e99f97f819a22eccef7b8"],"state_sha256":"eba24db9507801d89d773b84d40a31325bcee1b859a6a1adb32cda0796a0a1e8"}