{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:67VZN2FPAXK3P3EISABSIW4RZK","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":"4fc0be05e82e9a5f421af9b188c09eb3fade98c4f1edd435f2417e94fcd96795","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2024-10-17T13:09:08Z","title_canon_sha256":"204ee6a4796a3db74b73d9ec4b34cc1e7adaf529af1274900849437b7ccf915d"},"schema_version":"1.0","source":{"id":"2410.13520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13520","created_at":"2026-07-05T09:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13520v1","created_at":"2026-07-05T09:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13520","created_at":"2026-07-05T09:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"67VZN2FPAXK3","created_at":"2026-07-05T09:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"67VZN2FPAXK3P3EI","created_at":"2026-07-05T09:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"67VZN2FP","created_at":"2026-07-05T09:22:02Z"}],"graph_snapshots":[{"event_id":"sha256:7d94b75aa3f3608058a04c51e6febd8e9889c67bd76f87a8cf38b8a4d9d7a12c","target":"graph","created_at":"2026-07-05T09:22:02Z","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/2410.13520/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study principal-agent problems where a farsighted agent takes costly actions in an MDP. The core challenge in these settings is that agent's actions are hidden to the principal, who can only observe their outcomes, namely state transitions and their associated rewards. Thus, the principal's goal is to devise a policy that incentives the agent to take actions leading to desirable outcomes. This is accomplished by committing to a payment scheme (a.k.a. contract) at each step, specifying a monetary transfer from the principal to the agent for every possible outcome. Interestingly, we show that","authors_text":"Alberto Marchesi, Francesco Bacchiocchi, Matteo Bollini, Matteo Castiglioni, Nicola Gatti","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2024-10-17T13:09:08Z","title":"Contracting With a Reinforcement Learning Agent by Playing Trick or Treat"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13520","kind":"arxiv","version":1},"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":"sha256:3f77c621b542fab37777572431822dc8f0923d570f96260285db00a7523ea9ca","target":"record","created_at":"2026-07-05T09:22:02Z","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":"4fc0be05e82e9a5f421af9b188c09eb3fade98c4f1edd435f2417e94fcd96795","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2024-10-17T13:09:08Z","title_canon_sha256":"204ee6a4796a3db74b73d9ec4b34cc1e7adaf529af1274900849437b7ccf915d"},"schema_version":"1.0","source":{"id":"2410.13520","kind":"arxiv","version":1}},"canonical_sha256":"f7eb96e8af05d5b7ec889003245b91caaef47f09adeb7e0d52f1bd3ce1f3d92b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7eb96e8af05d5b7ec889003245b91caaef47f09adeb7e0d52f1bd3ce1f3d92b","first_computed_at":"2026-07-05T09:22:02.169972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:02.169972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z58OG8Y/qTgDQ+cZbcctSGXLgHa7NeNX0WLYxkShWAvGBO2yKnnfm9Mz4C2O1xc/figGFPTElZFCixMjbUuaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:02.170366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f77c621b542fab37777572431822dc8f0923d570f96260285db00a7523ea9ca","sha256:7d94b75aa3f3608058a04c51e6febd8e9889c67bd76f87a8cf38b8a4d9d7a12c"],"state_sha256":"bd2d5c9845bdfccdc77e27230f0b77490ae6126e96a7be1c1a3af174a5b43471"}