{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JPDI6MBPINCWXBPL26RP5DXNLT","short_pith_number":"pith:JPDI6MBP","canonical_record":{"source":{"id":"1805.08966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T05:30:17Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"34ac03c4f30ba48d8eda8ebcf91f09d338b30796a74374fe46469a2707943b8e","abstract_canon_sha256":"9d1126d9a61f7525407306e0e312cbdeda47680587b3b2a9304af97a7191cd75"},"schema_version":"1.0"},"canonical_sha256":"4bc68f302f43456b85ebd7a2fe8eed5cd9623d79f40d261e65cff7f4dce29d15","source":{"kind":"arxiv","id":"1805.08966","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08966","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08966v1","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08966","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"JPDI6MBPINCW","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JPDI6MBPINCWXBPL","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JPDI6MBP","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JPDI6MBPINCWXBPL26RP5DXNLT","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T05:30:17Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"34ac03c4f30ba48d8eda8ebcf91f09d338b30796a74374fe46469a2707943b8e","abstract_canon_sha256":"9d1126d9a61f7525407306e0e312cbdeda47680587b3b2a9304af97a7191cd75"},"schema_version":"1.0"},"canonical_sha256":"4bc68f302f43456b85ebd7a2fe8eed5cd9623d79f40d261e65cff7f4dce29d15","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:08.907958Z","signature_b64":"i/cgpAulOtl+jBStzaZzq+BEbIvxOIFY+AR5XydNW5pzxIV+cNOQitsWWLDIKl0MzYcp4IsaKYdpXhHh6HWUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bc68f302f43456b85ebd7a2fe8eed5cd9623d79f40d261e65cff7f4dce29d15","last_reissued_at":"2026-05-18T00:15:08.907540Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:08.907540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08966","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GSjRCu4b2sH/rCqPvZWE/Qoo6gHJRAWkHl3SPk8Gm1966EHYjlEIsacSTsrN5GMVqBmT8nHMPjSsTHyLEbxnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T13:19:43.806011Z"},"content_sha256":"38c629c1f504e9914dec6370cf63ccad96446392ff733fac3b14ca341c329b86","schema_version":"1.0","event_id":"sha256:38c629c1f504e9914dec6370cf63ccad96446392ff733fac3b14ca341c329b86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JPDI6MBPINCWXBPL26RP5DXNLT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovering Blind Spots in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Debadeepta Dey, Ece Kamar, Eric Horvitz, Julie Shah, Ramya Ramakrishnan","submitted_at":"2018-05-23T05:30:17Z","abstract_excerpt":"Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult to discover because the agent cannot predict them a priori. We propose using oracle feedback to learn a predictive model of these blind spots to reduce costly errors in real-world applications. We focus on blind spots in reinforcement learning (RL) that occur due to incomplete state representation: The agent does not have the appropriate features to represent the true state of the world and thus cannot distinguish among nume"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08966","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PQQqv8WJ+S2rN5negGVXkHQmJ77KYgIMIyi1O+BuGp4bdZTEkNQcmfvx5w8TFrd5BlIJEOH8aSt/IkS07Pm2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T13:19:43.806722Z"},"content_sha256":"6a141941c379ef7b33e83ab0028ce780f99a3b49f0f429d94dd5ddf7bf8483a5","schema_version":"1.0","event_id":"sha256:6a141941c379ef7b33e83ab0028ce780f99a3b49f0f429d94dd5ddf7bf8483a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JPDI6MBPINCWXBPL26RP5DXNLT/bundle.json","state_url":"https://pith.science/pith/JPDI6MBPINCWXBPL26RP5DXNLT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JPDI6MBPINCWXBPL26RP5DXNLT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T13:19:43Z","links":{"resolver":"https://pith.science/pith/JPDI6MBPINCWXBPL26RP5DXNLT","bundle":"https://pith.science/pith/JPDI6MBPINCWXBPL26RP5DXNLT/bundle.json","state":"https://pith.science/pith/JPDI6MBPINCWXBPL26RP5DXNLT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JPDI6MBPINCWXBPL26RP5DXNLT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JPDI6MBPINCWXBPL26RP5DXNLT","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":"9d1126d9a61f7525407306e0e312cbdeda47680587b3b2a9304af97a7191cd75","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T05:30:17Z","title_canon_sha256":"34ac03c4f30ba48d8eda8ebcf91f09d338b30796a74374fe46469a2707943b8e"},"schema_version":"1.0","source":{"id":"1805.08966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08966","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08966v1","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08966","created_at":"2026-05-18T00:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"JPDI6MBPINCW","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JPDI6MBPINCWXBPL","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JPDI6MBP","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:6a141941c379ef7b33e83ab0028ce780f99a3b49f0f429d94dd5ddf7bf8483a5","target":"graph","created_at":"2026-05-18T00:15:08Z","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"},"paper":{"abstract_excerpt":"Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult to discover because the agent cannot predict them a priori. We propose using oracle feedback to learn a predictive model of these blind spots to reduce costly errors in real-world applications. We focus on blind spots in reinforcement learning (RL) that occur due to incomplete state representation: The agent does not have the appropriate features to represent the true state of the world and thus cannot distinguish among nume","authors_text":"Debadeepta Dey, Ece Kamar, Eric Horvitz, Julie Shah, Ramya Ramakrishnan","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T05:30:17Z","title":"Discovering Blind Spots in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08966","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":"sha256:38c629c1f504e9914dec6370cf63ccad96446392ff733fac3b14ca341c329b86","target":"record","created_at":"2026-05-18T00:15:08Z","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":"9d1126d9a61f7525407306e0e312cbdeda47680587b3b2a9304af97a7191cd75","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T05:30:17Z","title_canon_sha256":"34ac03c4f30ba48d8eda8ebcf91f09d338b30796a74374fe46469a2707943b8e"},"schema_version":"1.0","source":{"id":"1805.08966","kind":"arxiv","version":1}},"canonical_sha256":"4bc68f302f43456b85ebd7a2fe8eed5cd9623d79f40d261e65cff7f4dce29d15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bc68f302f43456b85ebd7a2fe8eed5cd9623d79f40d261e65cff7f4dce29d15","first_computed_at":"2026-05-18T00:15:08.907540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:08.907540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i/cgpAulOtl+jBStzaZzq+BEbIvxOIFY+AR5XydNW5pzxIV+cNOQitsWWLDIKl0MzYcp4IsaKYdpXhHh6HWUCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:08.907958Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38c629c1f504e9914dec6370cf63ccad96446392ff733fac3b14ca341c329b86","sha256:6a141941c379ef7b33e83ab0028ce780f99a3b49f0f429d94dd5ddf7bf8483a5"],"state_sha256":"de1994050d1d880a78e887b796171ea57223d22b7f7bc3b0c8b900096a3cc9fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DkOfXjgKO3Vsg9zR2menHSBFHoHl9kBWhdGU9efIA+q24EosWWAKJhm4r94Y1NeJQ4kk8O4EpFaqo2ZBtKxzAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T13:19:43.810506Z","bundle_sha256":"0acef223a75a55d37298fe9b14c74a7b9152bf38ded4e872ed62b2434624db2a"}}