{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OZPPKI72UWIGJGUSSWOS3TIGR7","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":"5087876b120f276d3d52d87c75ed0766ab8d3887de66ee284e5230c08fa41dd8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T13:54:08Z","title_canon_sha256":"05b133cf895a67276690d33253230f4322eb4f694045cc10daadb0836c953cc4"},"schema_version":"1.0","source":{"id":"2605.15960","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15960","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15960v2","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15960","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"OZPPKI72UWIG","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"OZPPKI72UWIGJGUS","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"OZPPKI72","created_at":"2026-05-20T00:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:571bf0383ba66f2451a7600dcd077b6f47bb4c013a2e38c6ce4082a362a44a63","target":"graph","created_at":"2026-05-20T00:05:47Z","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/2605.15960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy should be strictly preferred over another while the environment's true transition model implies the reverse. We analogize our definition with a prior characterization of reward hacking but show that the associated proof of inevitability does not transfer to exploitation. To overcome this obstruction, we develop a general theory of reward hacking and model exploitation that proves that exploitation is essentially unavoidable on large policy sets a","authors_text":"David Abel, Esmeralda S. Whitammer, Logan Mondal Bhamidipaty, Mykel J. Kochenderfer, Subramanian Ramamoorthy","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T13:54:08Z","title":"Imperfect World Models are Exploitable"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15960","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":"sha256:3da351ef069e1c96af2b0decfcae706a4d536cc9f7d783c91e682384a26d2573","target":"record","created_at":"2026-05-20T00:05:47Z","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":"5087876b120f276d3d52d87c75ed0766ab8d3887de66ee284e5230c08fa41dd8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T13:54:08Z","title_canon_sha256":"05b133cf895a67276690d33253230f4322eb4f694045cc10daadb0836c953cc4"},"schema_version":"1.0","source":{"id":"2605.15960","kind":"arxiv","version":2}},"canonical_sha256":"765ef523faa590649a92959d2dcd068feba96220ebcb9895911f42d7ce234927","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"765ef523faa590649a92959d2dcd068feba96220ebcb9895911f42d7ce234927","first_computed_at":"2026-05-20T00:05:47.970574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:47.970574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/LRq2DFpmA3CjEJar9j0yVnh5neepcFpr27/FpsO5N7abC5C34TiRqSqxIFwX6XXMU6DGKRlOWMFSHbh5WE0Bg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:47.971146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15960","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3da351ef069e1c96af2b0decfcae706a4d536cc9f7d783c91e682384a26d2573","sha256:571bf0383ba66f2451a7600dcd077b6f47bb4c013a2e38c6ce4082a362a44a63"],"state_sha256":"e10dc67592fc5cd5a4eb92424816729318aa8b49d6382dfe453effbac4e79456"}