{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LWY4SST7AUMTCJRHCNXTUPBDNZ","short_pith_number":"pith:LWY4SST7","schema_version":"1.0","canonical_sha256":"5db1c94a7f0519312627136f3a3c236e6dd0d5b405846f1a534454946a8ae793","source":{"kind":"arxiv","id":"2407.01458","version":2},"attestation_state":"computed","paper":{"title":"Contractual Reinforcement Learning: Pulling Arms with Invisible Hands","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","econ.TH"],"primary_cat":"cs.LG","authors_text":"Haifeng Xu, Huazheng Wang, Jibang Wu, Mengdi Wang, Siyu Chen","submitted_at":"2024-07-01T16:53:00Z","abstract_excerpt":"The agency problem emerges in today's large scale machine learning tasks, where the learners are unable to direct content creation or enforce data collection. In this work, we propose a theoretical framework for aligning economic interests of different stakeholders in the online learning problems through contract design. The problem, termed \\emph{contractual reinforcement learning}, naturally arises from the classic model of Markov decision processes, where a learning principal seeks to optimally influence the agent's action policy for their common interests through a set of payment rules cont"},"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":"2407.01458","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T16:53:00Z","cross_cats_sorted":["cs.AI","cs.GT","econ.TH"],"title_canon_sha256":"f69c05c88438e0c939c96eb465d8536c65ef88762345f53dc8b59c1234d2c87f","abstract_canon_sha256":"7ac61ba270ccac82f3d33740a3b98304da27531bfbd5e2654ae7cdeba8a58ddc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:22.097018Z","signature_b64":"lZca8OxlK21BbqfbG5nfAGWIQkLLp6x6YxdCs70IuetFuwhZcULuv0x/pyMk8cMJZ4ZZahk8I7++Ep7VO6YgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5db1c94a7f0519312627136f3a3c236e6dd0d5b405846f1a534454946a8ae793","last_reissued_at":"2026-07-05T08:39:22.096607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:22.096607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contractual Reinforcement Learning: Pulling Arms with Invisible Hands","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","econ.TH"],"primary_cat":"cs.LG","authors_text":"Haifeng Xu, Huazheng Wang, Jibang Wu, Mengdi Wang, Siyu Chen","submitted_at":"2024-07-01T16:53:00Z","abstract_excerpt":"The agency problem emerges in today's large scale machine learning tasks, where the learners are unable to direct content creation or enforce data collection. In this work, we propose a theoretical framework for aligning economic interests of different stakeholders in the online learning problems through contract design. The problem, termed \\emph{contractual reinforcement learning}, naturally arises from the classic model of Markov decision processes, where a learning principal seeks to optimally influence the agent's action policy for their common interests through a set of payment rules cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01458","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/2407.01458/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":"2407.01458","created_at":"2026-07-05T08:39:22.096661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01458v2","created_at":"2026-07-05T08:39:22.096661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01458","created_at":"2026-07-05T08:39:22.096661+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWY4SST7AUMT","created_at":"2026-07-05T08:39:22.096661+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWY4SST7AUMTCJRH","created_at":"2026-07-05T08:39:22.096661+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWY4SST7","created_at":"2026-07-05T08:39:22.096661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15636","citing_title":"The Power of Information for Intermediate States in Contract Design","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWY4SST7AUMTCJRHCNXTUPBDNZ","json":"https://pith.science/pith/LWY4SST7AUMTCJRHCNXTUPBDNZ.json","graph_json":"https://pith.science/api/pith-number/LWY4SST7AUMTCJRHCNXTUPBDNZ/graph.json","events_json":"https://pith.science/api/pith-number/LWY4SST7AUMTCJRHCNXTUPBDNZ/events.json","paper":"https://pith.science/paper/LWY4SST7"},"agent_actions":{"view_html":"https://pith.science/pith/LWY4SST7AUMTCJRHCNXTUPBDNZ","download_json":"https://pith.science/pith/LWY4SST7AUMTCJRHCNXTUPBDNZ.json","view_paper":"https://pith.science/paper/LWY4SST7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01458&json=true","fetch_graph":"https://pith.science/api/pith-number/LWY4SST7AUMTCJRHCNXTUPBDNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LWY4SST7AUMTCJRHCNXTUPBDNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWY4SST7AUMTCJRHCNXTUPBDNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWY4SST7AUMTCJRHCNXTUPBDNZ/action/storage_attestation","attest_author":"https://pith.science/pith/LWY4SST7AUMTCJRHCNXTUPBDNZ/action/author_attestation","sign_citation":"https://pith.science/pith/LWY4SST7AUMTCJRHCNXTUPBDNZ/action/citation_signature","submit_replication":"https://pith.science/pith/LWY4SST7AUMTCJRHCNXTUPBDNZ/action/replication_record"}},"created_at":"2026-07-05T08:39:22.096661+00:00","updated_at":"2026-07-05T08:39:22.096661+00:00"}