{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LWY4SST7AUMTCJRHCNXTUPBDNZ","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":"7ac61ba270ccac82f3d33740a3b98304da27531bfbd5e2654ae7cdeba8a58ddc","cross_cats_sorted":["cs.AI","cs.GT","econ.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T16:53:00Z","title_canon_sha256":"f69c05c88438e0c939c96eb465d8536c65ef88762345f53dc8b59c1234d2c87f"},"schema_version":"1.0","source":{"id":"2407.01458","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01458","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01458v2","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01458","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"LWY4SST7AUMT","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"LWY4SST7AUMTCJRH","created_at":"2026-07-05T08:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"LWY4SST7","created_at":"2026-07-05T08:39:22Z"}],"graph_snapshots":[{"event_id":"sha256:7086500a1cfee699635d3748df63577c8007772a4fd3254b52ac10c0f63b05d6","target":"graph","created_at":"2026-07-05T08:39:22Z","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/2407.01458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haifeng Xu, Huazheng Wang, Jibang Wu, Mengdi Wang, Siyu Chen","cross_cats":["cs.AI","cs.GT","econ.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T16:53:00Z","title":"Contractual Reinforcement Learning: Pulling Arms with Invisible Hands"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01458","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:d4269b92108ae575c75dcc7fb5e4b8d7fcaa00542fdf9927c6ee7276deec87d9","target":"record","created_at":"2026-07-05T08:39:22Z","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":"7ac61ba270ccac82f3d33740a3b98304da27531bfbd5e2654ae7cdeba8a58ddc","cross_cats_sorted":["cs.AI","cs.GT","econ.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T16:53:00Z","title_canon_sha256":"f69c05c88438e0c939c96eb465d8536c65ef88762345f53dc8b59c1234d2c87f"},"schema_version":"1.0","source":{"id":"2407.01458","kind":"arxiv","version":2}},"canonical_sha256":"5db1c94a7f0519312627136f3a3c236e6dd0d5b405846f1a534454946a8ae793","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5db1c94a7f0519312627136f3a3c236e6dd0d5b405846f1a534454946a8ae793","first_computed_at":"2026-07-05T08:39:22.096607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:22.096607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lZca8OxlK21BbqfbG5nfAGWIQkLLp6x6YxdCs70IuetFuwhZcULuv0x/pyMk8cMJZ4ZZahk8I7++Ep7VO6YgCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:22.097018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01458","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4269b92108ae575c75dcc7fb5e4b8d7fcaa00542fdf9927c6ee7276deec87d9","sha256:7086500a1cfee699635d3748df63577c8007772a4fd3254b52ac10c0f63b05d6"],"state_sha256":"e1fafcfd6825e45cb86f32a35a019c9550465a73aaafceeebb7d7552b8adf82e"}