{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BBKFCJWDMX7GX3RJ74OSHTXPLQ","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":"e8c519b285589b7cd67ddd427f8fd38008d87b7e8f561016aabb15c07068791d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-06T18:49:57Z","title_canon_sha256":"486e3c2458cda6b8a0960337ab911ade037cd7575567c77b63c93b3d259739b0"},"schema_version":"1.0","source":{"id":"2201.02185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.02185","created_at":"2026-07-05T03:46:30Z"},{"alias_kind":"arxiv_version","alias_value":"2201.02185v1","created_at":"2026-07-05T03:46:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02185","created_at":"2026-07-05T03:46:30Z"},{"alias_kind":"pith_short_12","alias_value":"BBKFCJWDMX7G","created_at":"2026-07-05T03:46:30Z"},{"alias_kind":"pith_short_16","alias_value":"BBKFCJWDMX7GX3RJ","created_at":"2026-07-05T03:46:30Z"},{"alias_kind":"pith_short_8","alias_value":"BBKFCJWD","created_at":"2026-07-05T03:46:30Z"}],"graph_snapshots":[{"event_id":"sha256:3e2252e3bdc0811e4cc9cf6cdcc8f2ab311a89367f3c827b29bef194ccb9791a","target":"graph","created_at":"2026-07-05T03:46:30Z","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/2201.02185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study reward design strategies for incentivizing a reinforcement learning agent to adopt a policy from a set of admissible policies. The goal of the reward designer is to modify the underlying reward function cost-efficiently while ensuring that any approximately optimal deterministic policy under the new reward function is admissible and performs well under the original reward function. This problem can be viewed as a dual to the problem of optimal reward poisoning attacks: instead of forcing an agent to adopt a specific policy, the reward designer incentivizes an agent to avoid taking act","authors_text":"Adish Singla, Goran Radanovic, Jiarui Gan, Kiarash Banihashem","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-06T18:49:57Z","title":"Admissible Policy Teaching through Reward Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02185","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":"sha256:600f3528516893d2b27202f1cd93415823cd48095c3d31f6118aa5ba19e281c1","target":"record","created_at":"2026-07-05T03:46:30Z","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":"e8c519b285589b7cd67ddd427f8fd38008d87b7e8f561016aabb15c07068791d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-06T18:49:57Z","title_canon_sha256":"486e3c2458cda6b8a0960337ab911ade037cd7575567c77b63c93b3d259739b0"},"schema_version":"1.0","source":{"id":"2201.02185","kind":"arxiv","version":1}},"canonical_sha256":"08545126c365fe6bee29ff1d23ceef5c11c8137d9ec416800e91b4a0e41c89ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08545126c365fe6bee29ff1d23ceef5c11c8137d9ec416800e91b4a0e41c89ae","first_computed_at":"2026-07-05T03:46:30.955530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:30.955530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CGsW+iIrxEv7p7sz0GatnPhlJCXfpvx+i7FeWQhNOPW29I5IY/Oewm9VHDgHD3CtTgYmg85BsWnIdFLX2ZHABA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:30.955952Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.02185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:600f3528516893d2b27202f1cd93415823cd48095c3d31f6118aa5ba19e281c1","sha256:3e2252e3bdc0811e4cc9cf6cdcc8f2ab311a89367f3c827b29bef194ccb9791a"],"state_sha256":"ae24924d9445f224ab34b844b34560160c5a4081db512376de36fe07e72fbca0"}