{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:D4G5XA5WWYNKQP4FERGTFKE3UE","short_pith_number":"pith:D4G5XA5W","canonical_record":{"source":{"id":"1904.12901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-29T18:40:15Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"260e2a12b50bfa998c1ce83a6bfb8c517545e8a12ea204a55cd37b19c6c9c175","abstract_canon_sha256":"b78a3dd09ec5d4cb08ffa63aceb9bc1796ba3b89cace387de094635803efdaca"},"schema_version":"1.0"},"canonical_sha256":"1f0ddb83b6b61aa83f85244d32a89ba11216c72473b31490270c1346cba62604","source":{"kind":"arxiv","id":"1904.12901","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.12901","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"arxiv_version","alias_value":"1904.12901v1","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12901","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"pith_short_12","alias_value":"D4G5XA5WWYNK","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"D4G5XA5WWYNKQP4F","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"D4G5XA5W","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:D4G5XA5WWYNKQP4FERGTFKE3UE","target":"record","payload":{"canonical_record":{"source":{"id":"1904.12901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-29T18:40:15Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"260e2a12b50bfa998c1ce83a6bfb8c517545e8a12ea204a55cd37b19c6c9c175","abstract_canon_sha256":"b78a3dd09ec5d4cb08ffa63aceb9bc1796ba3b89cace387de094635803efdaca"},"schema_version":"1.0"},"canonical_sha256":"1f0ddb83b6b61aa83f85244d32a89ba11216c72473b31490270c1346cba62604","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:24.530185Z","signature_b64":"YHp2EiX0oiVyj9xfNEK0YhyKhUzbXfMvItrjqUCNmLNLNSlVA4Kni5PLE5rY9gzwVZNo8s+KRgGxosPub26hAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f0ddb83b6b61aa83f85244d32a89ba11216c72473b31490270c1346cba62604","last_reissued_at":"2026-05-17T23:47:24.529716Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:24.529716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.12901","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":"2026-05-17T23:47:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XRPARkyKat/m75iZFAJcz4PsmzMG/Jxc1isYNfvo3hJlXoYeJ/71Knr38VKUPoDaXEPM4C4bXSlF4MSKzLGDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:37:57.268252Z"},"content_sha256":"985fdb80d401f1a870fce8e02e4252e3728a3bc9ae278088c3a1490fd2f0e0ed","schema_version":"1.0","event_id":"sha256:985fdb80d401f1a870fce8e02e4252e3728a3bc9ae278088c3a1490fd2f0e0ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:D4G5XA5WWYNKQP4FERGTFKE3UE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Challenges of Real-World Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Mankowitz, Gabriel Dulac-Arnold, Todd Hester","submitted_at":"2019-04-29T18:40:15Z","abstract_excerpt":"Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research advances in RL are often hard to leverage in real-world systems due to a series of assumptions that are rarely satisfied in practice. We present a set of nine unique challenges that must be addressed to productionize RL to real world problems. For each of these challenges, we specify the exact meaning of the challenge, present some approaches from the literature, and specify some metrics for evaluating that challenge."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12901","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":"2026-05-17T23:47:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K/Msiy2XsKqtoVRqlhXoAaVw9fF61lNUgc6qX2J44sJaGfNvIEDfdRfMsehCu2nfBUjmAHGbxpdpIpaWU2byCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:37:57.268606Z"},"content_sha256":"ba3ca62c9e8e1b9442babc5730cdc8d5bfcb8d6daa104d583875709ff4826461","schema_version":"1.0","event_id":"sha256:ba3ca62c9e8e1b9442babc5730cdc8d5bfcb8d6daa104d583875709ff4826461"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D4G5XA5WWYNKQP4FERGTFKE3UE/bundle.json","state_url":"https://pith.science/pith/D4G5XA5WWYNKQP4FERGTFKE3UE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D4G5XA5WWYNKQP4FERGTFKE3UE/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":"2026-07-07T13:37:57Z","links":{"resolver":"https://pith.science/pith/D4G5XA5WWYNKQP4FERGTFKE3UE","bundle":"https://pith.science/pith/D4G5XA5WWYNKQP4FERGTFKE3UE/bundle.json","state":"https://pith.science/pith/D4G5XA5WWYNKQP4FERGTFKE3UE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D4G5XA5WWYNKQP4FERGTFKE3UE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:D4G5XA5WWYNKQP4FERGTFKE3UE","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":"b78a3dd09ec5d4cb08ffa63aceb9bc1796ba3b89cace387de094635803efdaca","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-29T18:40:15Z","title_canon_sha256":"260e2a12b50bfa998c1ce83a6bfb8c517545e8a12ea204a55cd37b19c6c9c175"},"schema_version":"1.0","source":{"id":"1904.12901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.12901","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"arxiv_version","alias_value":"1904.12901v1","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12901","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"pith_short_12","alias_value":"D4G5XA5WWYNK","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"D4G5XA5WWYNKQP4F","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"D4G5XA5W","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:ba3ca62c9e8e1b9442babc5730cdc8d5bfcb8d6daa104d583875709ff4826461","target":"graph","created_at":"2026-05-17T23:47:24Z","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":"Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research advances in RL are often hard to leverage in real-world systems due to a series of assumptions that are rarely satisfied in practice. We present a set of nine unique challenges that must be addressed to productionize RL to real world problems. For each of these challenges, we specify the exact meaning of the challenge, present some approaches from the literature, and specify some metrics for evaluating that challenge.","authors_text":"Daniel Mankowitz, Gabriel Dulac-Arnold, Todd Hester","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-29T18:40:15Z","title":"Challenges of Real-World Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12901","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":"sha256:985fdb80d401f1a870fce8e02e4252e3728a3bc9ae278088c3a1490fd2f0e0ed","target":"record","created_at":"2026-05-17T23:47:24Z","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":"b78a3dd09ec5d4cb08ffa63aceb9bc1796ba3b89cace387de094635803efdaca","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-29T18:40:15Z","title_canon_sha256":"260e2a12b50bfa998c1ce83a6bfb8c517545e8a12ea204a55cd37b19c6c9c175"},"schema_version":"1.0","source":{"id":"1904.12901","kind":"arxiv","version":1}},"canonical_sha256":"1f0ddb83b6b61aa83f85244d32a89ba11216c72473b31490270c1346cba62604","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f0ddb83b6b61aa83f85244d32a89ba11216c72473b31490270c1346cba62604","first_computed_at":"2026-05-17T23:47:24.529716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:24.529716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YHp2EiX0oiVyj9xfNEK0YhyKhUzbXfMvItrjqUCNmLNLNSlVA4Kni5PLE5rY9gzwVZNo8s+KRgGxosPub26hAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:24.530185Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.12901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:985fdb80d401f1a870fce8e02e4252e3728a3bc9ae278088c3a1490fd2f0e0ed","sha256:ba3ca62c9e8e1b9442babc5730cdc8d5bfcb8d6daa104d583875709ff4826461"],"state_sha256":"8d2871df372b915f6af8a0d5c16038382f35e2c13dfc2f0ce7d244d282e479a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ubUkufCrSFvPKwlIWBYUpJoPS9+XQpLTiTCBJErzkBi/R/wA6TeUlvNgwNPyg4/UNI6dHALiEHw/nXuFxggiDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:37:57.270494Z","bundle_sha256":"750dd2a427e6082ba7570be501f50bd547218227840b66bd03211e4321aa19e7"}}