{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RESBRZIKNQECHMGCYYFLAHQSTN","short_pith_number":"pith:RESBRZIK","schema_version":"1.0","canonical_sha256":"892418e50a6c0823b0c2c60ab01e129b6b3edf87821bb8484150f3e50475620c","source":{"kind":"arxiv","id":"2403.03811","version":1},"attestation_state":"computed","paper":{"title":"Incentivized Learning in Principal-Agent Bandit Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alain Durmus, Antoine Scheid, Aymeric Capitaine, Daniil Tiapkin, El Mahdi El Mhamdi, Eric Moulines, Etienne Boursier, Michael I. Jordan","submitted_at":"2024-03-06T16:00:46Z","abstract_excerpt":"This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent. The principal and the agent have misaligned objectives and the choice of action is only left to the agent. However, the principal can influence the agent's decisions by offering incentives which add up to his rewards. The principal aims to iteratively learn an incentive policy to maximize her own total utility. This framework extends usual bandit problems and is motivated by several practical applications, such as healthcare or ecological taxation, where tra"},"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":"2403.03811","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-03-06T16:00:46Z","cross_cats_sorted":["cs.GT","cs.LG"],"title_canon_sha256":"6bc4a2ea3fa16b3127c0ba023395b735a1188b4b758373a826a5b386baddb1b3","abstract_canon_sha256":"2e88f54364b5144ccc2f9d821c144735d7e8423f45f7bcf072f96ff011cafda6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:01.753068Z","signature_b64":"k44dssGORMFSISDLTsU3hauTsbKlfHAqhJLLcv6IH7QV6Jy5cTs8jHuPZYeTHS7w1acTPks/2qQnwfeQmPvqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"892418e50a6c0823b0c2c60ab01e129b6b3edf87821bb8484150f3e50475620c","last_reissued_at":"2026-07-05T07:53:01.752590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:01.752590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incentivized Learning in Principal-Agent Bandit Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alain Durmus, Antoine Scheid, Aymeric Capitaine, Daniil Tiapkin, El Mahdi El Mhamdi, Eric Moulines, Etienne Boursier, Michael I. Jordan","submitted_at":"2024-03-06T16:00:46Z","abstract_excerpt":"This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent. The principal and the agent have misaligned objectives and the choice of action is only left to the agent. However, the principal can influence the agent's decisions by offering incentives which add up to his rewards. The principal aims to iteratively learn an incentive policy to maximize her own total utility. This framework extends usual bandit problems and is motivated by several practical applications, such as healthcare or ecological taxation, where tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03811","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/2403.03811/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":"2403.03811","created_at":"2026-07-05T07:53:01.752648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03811v1","created_at":"2026-07-05T07:53:01.752648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03811","created_at":"2026-07-05T07:53:01.752648+00:00"},{"alias_kind":"pith_short_12","alias_value":"RESBRZIKNQEC","created_at":"2026-07-05T07:53:01.752648+00:00"},{"alias_kind":"pith_short_16","alias_value":"RESBRZIKNQECHMGC","created_at":"2026-07-05T07:53:01.752648+00:00"},{"alias_kind":"pith_short_8","alias_value":"RESBRZIK","created_at":"2026-07-05T07:53:01.752648+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/RESBRZIKNQECHMGCYYFLAHQSTN","json":"https://pith.science/pith/RESBRZIKNQECHMGCYYFLAHQSTN.json","graph_json":"https://pith.science/api/pith-number/RESBRZIKNQECHMGCYYFLAHQSTN/graph.json","events_json":"https://pith.science/api/pith-number/RESBRZIKNQECHMGCYYFLAHQSTN/events.json","paper":"https://pith.science/paper/RESBRZIK"},"agent_actions":{"view_html":"https://pith.science/pith/RESBRZIKNQECHMGCYYFLAHQSTN","download_json":"https://pith.science/pith/RESBRZIKNQECHMGCYYFLAHQSTN.json","view_paper":"https://pith.science/paper/RESBRZIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03811&json=true","fetch_graph":"https://pith.science/api/pith-number/RESBRZIKNQECHMGCYYFLAHQSTN/graph.json","fetch_events":"https://pith.science/api/pith-number/RESBRZIKNQECHMGCYYFLAHQSTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RESBRZIKNQECHMGCYYFLAHQSTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RESBRZIKNQECHMGCYYFLAHQSTN/action/storage_attestation","attest_author":"https://pith.science/pith/RESBRZIKNQECHMGCYYFLAHQSTN/action/author_attestation","sign_citation":"https://pith.science/pith/RESBRZIKNQECHMGCYYFLAHQSTN/action/citation_signature","submit_replication":"https://pith.science/pith/RESBRZIKNQECHMGCYYFLAHQSTN/action/replication_record"}},"created_at":"2026-07-05T07:53:01.752648+00:00","updated_at":"2026-07-05T07:53:01.752648+00:00"}