{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TWLZUNVNWGBJJG26ZUMNQ5XYI3","short_pith_number":"pith:TWLZUNVN","canonical_record":{"source":{"id":"1905.13562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T01:47:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"65bcf5aa91359f7e8b2c9e777d046da874813340b6d521ea815cbfcbc5659347","abstract_canon_sha256":"0e1461c813ef3f4f3fbb0537c5ce1436dfc8ab6cf830ccd03e0a541b9ec55689"},"schema_version":"1.0"},"canonical_sha256":"9d979a36adb182949b5ecd18d876f846f02e7beb913d899362d8277311713dda","source":{"kind":"arxiv","id":"1905.13562","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13562","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13562v1","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13562","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"TWLZUNVNWGBJ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TWLZUNVNWGBJJG26","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TWLZUNVN","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TWLZUNVNWGBJJG26ZUMNQ5XYI3","target":"record","payload":{"canonical_record":{"source":{"id":"1905.13562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T01:47:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"65bcf5aa91359f7e8b2c9e777d046da874813340b6d521ea815cbfcbc5659347","abstract_canon_sha256":"0e1461c813ef3f4f3fbb0537c5ce1436dfc8ab6cf830ccd03e0a541b9ec55689"},"schema_version":"1.0"},"canonical_sha256":"9d979a36adb182949b5ecd18d876f846f02e7beb913d899362d8277311713dda","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:34.553883Z","signature_b64":"9KMczrmGFxpbjXZkDngpRoidwnYxMhKOLJKcU/TREzknJLAppiJaKmT2+tGiPIkLktZPSGQqpgFc2qdwyRafAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d979a36adb182949b5ecd18d876f846f02e7beb913d899362d8277311713dda","last_reissued_at":"2026-05-17T23:44:34.553255Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:34.553255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.13562","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":"2026-05-17T23:44:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tfRvQAcRL9k/Igyh1BGu1j/mG9prxyRiqFqJ0s/iaExdvWnydwUwCa1T0gSmfrBNxD8jtnoOBz6Aqyas/lu9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T02:22:55.298533Z"},"content_sha256":"cfee0d2717493b57f5906a38e08b4c6a47f5bd5577f75e23734fb7458d614ffe","schema_version":"1.0","event_id":"sha256:cfee0d2717493b57f5906a38e08b4c6a47f5bd5577f75e23734fb7458d614ffe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TWLZUNVNWGBJJG26ZUMNQ5XYI3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Don't Forget Your Teacher: A Corrective Reinforcement Learning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lawrence V. Snyder, Majid Jahani, Martin Tak\\'a\\v{c}, Mohammadreza Nazari","submitted_at":"2019-05-30T01:47:18Z","abstract_excerpt":"Although reinforcement learning (RL) can provide reliable solutions in many settings, practitioners are often wary of the discrepancies between the RL solution and their status quo procedures. Therefore, they may be reluctant to adapt to the novel way of executing tasks proposed by RL. On the other hand, many real-world problems require relatively small adjustments from the status quo policies to achieve improved performance. Therefore, we propose a student-teacher RL mechanism in which the RL (the \"student\") learns to maximize its reward, subject to a constraint that bounds the difference bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13562","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":"2026-05-17T23:44:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7yM5xwqfbvIInU8x55B6zxB3fn64NJXi+UfXySMlk/ahrZwHMUeCQgCg7EkLAJyoVFwCm6bG2lS2TyoLZP8vDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T02:22:55.298905Z"},"content_sha256":"0dc7330898f9932a652b120b63bb700c1c957c1a8007397354ee012d95b31979","schema_version":"1.0","event_id":"sha256:0dc7330898f9932a652b120b63bb700c1c957c1a8007397354ee012d95b31979"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TWLZUNVNWGBJJG26ZUMNQ5XYI3/bundle.json","state_url":"https://pith.science/pith/TWLZUNVNWGBJJG26ZUMNQ5XYI3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TWLZUNVNWGBJJG26ZUMNQ5XYI3/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":"2026-06-30T02:22:55Z","links":{"resolver":"https://pith.science/pith/TWLZUNVNWGBJJG26ZUMNQ5XYI3","bundle":"https://pith.science/pith/TWLZUNVNWGBJJG26ZUMNQ5XYI3/bundle.json","state":"https://pith.science/pith/TWLZUNVNWGBJJG26ZUMNQ5XYI3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TWLZUNVNWGBJJG26ZUMNQ5XYI3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TWLZUNVNWGBJJG26ZUMNQ5XYI3","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":"0e1461c813ef3f4f3fbb0537c5ce1436dfc8ab6cf830ccd03e0a541b9ec55689","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T01:47:18Z","title_canon_sha256":"65bcf5aa91359f7e8b2c9e777d046da874813340b6d521ea815cbfcbc5659347"},"schema_version":"1.0","source":{"id":"1905.13562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13562","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13562v1","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13562","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"TWLZUNVNWGBJ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TWLZUNVNWGBJJG26","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TWLZUNVN","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:0dc7330898f9932a652b120b63bb700c1c957c1a8007397354ee012d95b31979","target":"graph","created_at":"2026-05-17T23:44:34Z","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":"Although reinforcement learning (RL) can provide reliable solutions in many settings, practitioners are often wary of the discrepancies between the RL solution and their status quo procedures. Therefore, they may be reluctant to adapt to the novel way of executing tasks proposed by RL. On the other hand, many real-world problems require relatively small adjustments from the status quo policies to achieve improved performance. Therefore, we propose a student-teacher RL mechanism in which the RL (the \"student\") learns to maximize its reward, subject to a constraint that bounds the difference bet","authors_text":"Lawrence V. Snyder, Majid Jahani, Martin Tak\\'a\\v{c}, Mohammadreza Nazari","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T01:47:18Z","title":"Don't Forget Your Teacher: A Corrective Reinforcement Learning Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13562","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:cfee0d2717493b57f5906a38e08b4c6a47f5bd5577f75e23734fb7458d614ffe","target":"record","created_at":"2026-05-17T23:44:34Z","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":"0e1461c813ef3f4f3fbb0537c5ce1436dfc8ab6cf830ccd03e0a541b9ec55689","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T01:47:18Z","title_canon_sha256":"65bcf5aa91359f7e8b2c9e777d046da874813340b6d521ea815cbfcbc5659347"},"schema_version":"1.0","source":{"id":"1905.13562","kind":"arxiv","version":1}},"canonical_sha256":"9d979a36adb182949b5ecd18d876f846f02e7beb913d899362d8277311713dda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d979a36adb182949b5ecd18d876f846f02e7beb913d899362d8277311713dda","first_computed_at":"2026-05-17T23:44:34.553255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:34.553255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9KMczrmGFxpbjXZkDngpRoidwnYxMhKOLJKcU/TREzknJLAppiJaKmT2+tGiPIkLktZPSGQqpgFc2qdwyRafAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:34.553883Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.13562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfee0d2717493b57f5906a38e08b4c6a47f5bd5577f75e23734fb7458d614ffe","sha256:0dc7330898f9932a652b120b63bb700c1c957c1a8007397354ee012d95b31979"],"state_sha256":"58f84c9431015b33fe17e40aa804fcb755f4394b6149ab2103b142d88d448311"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EN5PRen8V0b4Sr4MXinPNq4mD6NJtsnNE4ebLY4Tyc3ycSL+vPFXr45S26uVkSvCsWAMAR0AlfwOnMK1/6uJAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T02:22:55.301281Z","bundle_sha256":"12030a344ade81abe569e96e50a2ed513a255a79e455c4096af37a842358e8c1"}}