{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MMREDEOUI3KRIWE3FGNG476NR3","short_pith_number":"pith:MMREDEOU","canonical_record":{"source":{"id":"1912.05663","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2019-12-10T17:50:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"55eb366f423d29c506a91360c565592069838f25eeaed785870b9cab6ded76b9","abstract_canon_sha256":"b3f5fb16039cd8504baf1d78661bc909605fe1ad5fb3d2878f2acf663dc825c8"},"schema_version":"1.0"},"canonical_sha256":"63224191d446d514589b299a6e7fcd8ec828b2ba281841d300cec733e7b90b34","source":{"kind":"arxiv","id":"1912.05663","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05663","created_at":"2026-07-05T00:40:26Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05663v2","created_at":"2026-07-05T00:40:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05663","created_at":"2026-07-05T00:40:26Z"},{"alias_kind":"pith_short_12","alias_value":"MMREDEOUI3KR","created_at":"2026-07-05T00:40:26Z"},{"alias_kind":"pith_short_16","alias_value":"MMREDEOUI3KRIWE3","created_at":"2026-07-05T00:40:26Z"},{"alias_kind":"pith_short_8","alias_value":"MMREDEOU","created_at":"2026-07-05T00:40:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MMREDEOUI3KRIWE3FGNG476NR3","target":"record","payload":{"canonical_record":{"source":{"id":"1912.05663","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2019-12-10T17:50:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"55eb366f423d29c506a91360c565592069838f25eeaed785870b9cab6ded76b9","abstract_canon_sha256":"b3f5fb16039cd8504baf1d78661bc909605fe1ad5fb3d2878f2acf663dc825c8"},"schema_version":"1.0"},"canonical_sha256":"63224191d446d514589b299a6e7fcd8ec828b2ba281841d300cec733e7b90b34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:26.908949Z","signature_b64":"3ZFho0XJ5eugY223xMCm+imh37nk1ZDZj6bGADcxQfT/1GQlXOmRxuLlieqDobI7ZDy/O/8mosIAJQF570W5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63224191d446d514589b299a6e7fcd8ec828b2ba281841d300cec733e7b90b34","last_reissued_at":"2026-07-05T00:40:26.908442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:26.908442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.05663","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:40:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9GOD2APTMrRJ2gwEFrzheIfakVeZiN3saPf3XrZC0rHLRGNUF+jofwS9T1yPm5HK3l7gGljesB5Y2jPePUv1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:59:24.982403Z"},"content_sha256":"793994d504195cd0aa77368468616d805eacadc532ab2fca6e490aa5acf08b29","schema_version":"1.0","event_id":"sha256:793994d504195cd0aa77368468616d805eacadc532ab2fca6e490aa5acf08b29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MMREDEOUI3KRIWE3FGNG476NR3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measuring the Reliability of Reinforcement Learning Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Anoop Korattikara, John Canny, Samuel Fishman, Sergio Guadarrama, Stephanie C.Y. Chan","submitted_at":"2019-12-10T17:50:33Z","abstract_excerpt":"Lack of reliability is a well-known issue for reinforcement learning (RL) algorithms. This problem has gained increasing attention in recent years, and efforts to improve it have grown substantially. To aid RL researchers and production users with the evaluation and improvement of reliability, we propose a set of metrics that quantitatively measure different aspects of reliability. In this work, we focus on variability and risk, both during training and after learning (on a fixed policy). We designed these metrics to be general-purpose, and we also designed complementary statistical tests to e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05663","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.05663/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:40:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OGlTtCFr6sb2I4+nBY6Whs+5GarwyTNjKbbuSDFHUjOIn3lbhD81dAxOmebM0wf8Dds8pIikzs8Q4/+Owy4eCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:59:24.982950Z"},"content_sha256":"ab0c6fe58988cbf2f0a8c65170875a040696dca70aaa5d087bdff57f877309f5","schema_version":"1.0","event_id":"sha256:ab0c6fe58988cbf2f0a8c65170875a040696dca70aaa5d087bdff57f877309f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MMREDEOUI3KRIWE3FGNG476NR3/bundle.json","state_url":"https://pith.science/pith/MMREDEOUI3KRIWE3FGNG476NR3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MMREDEOUI3KRIWE3FGNG476NR3/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":"2026-08-09T18:59:24Z","links":{"resolver":"https://pith.science/pith/MMREDEOUI3KRIWE3FGNG476NR3","bundle":"https://pith.science/pith/MMREDEOUI3KRIWE3FGNG476NR3/bundle.json","state":"https://pith.science/pith/MMREDEOUI3KRIWE3FGNG476NR3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MMREDEOUI3KRIWE3FGNG476NR3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MMREDEOUI3KRIWE3FGNG476NR3","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":"b3f5fb16039cd8504baf1d78661bc909605fe1ad5fb3d2878f2acf663dc825c8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2019-12-10T17:50:33Z","title_canon_sha256":"55eb366f423d29c506a91360c565592069838f25eeaed785870b9cab6ded76b9"},"schema_version":"1.0","source":{"id":"1912.05663","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05663","created_at":"2026-07-05T00:40:26Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05663v2","created_at":"2026-07-05T00:40:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05663","created_at":"2026-07-05T00:40:26Z"},{"alias_kind":"pith_short_12","alias_value":"MMREDEOUI3KR","created_at":"2026-07-05T00:40:26Z"},{"alias_kind":"pith_short_16","alias_value":"MMREDEOUI3KRIWE3","created_at":"2026-07-05T00:40:26Z"},{"alias_kind":"pith_short_8","alias_value":"MMREDEOU","created_at":"2026-07-05T00:40:26Z"}],"graph_snapshots":[{"event_id":"sha256:ab0c6fe58988cbf2f0a8c65170875a040696dca70aaa5d087bdff57f877309f5","target":"graph","created_at":"2026-07-05T00:40:26Z","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/1912.05663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lack of reliability is a well-known issue for reinforcement learning (RL) algorithms. This problem has gained increasing attention in recent years, and efforts to improve it have grown substantially. To aid RL researchers and production users with the evaluation and improvement of reliability, we propose a set of metrics that quantitatively measure different aspects of reliability. In this work, we focus on variability and risk, both during training and after learning (on a fixed policy). We designed these metrics to be general-purpose, and we also designed complementary statistical tests to e","authors_text":"Anoop Korattikara, John Canny, Samuel Fishman, Sergio Guadarrama, Stephanie C.Y. Chan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2019-12-10T17:50:33Z","title":"Measuring the Reliability of Reinforcement Learning Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05663","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":"sha256:793994d504195cd0aa77368468616d805eacadc532ab2fca6e490aa5acf08b29","target":"record","created_at":"2026-07-05T00:40:26Z","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":"b3f5fb16039cd8504baf1d78661bc909605fe1ad5fb3d2878f2acf663dc825c8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2019-12-10T17:50:33Z","title_canon_sha256":"55eb366f423d29c506a91360c565592069838f25eeaed785870b9cab6ded76b9"},"schema_version":"1.0","source":{"id":"1912.05663","kind":"arxiv","version":2}},"canonical_sha256":"63224191d446d514589b299a6e7fcd8ec828b2ba281841d300cec733e7b90b34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63224191d446d514589b299a6e7fcd8ec828b2ba281841d300cec733e7b90b34","first_computed_at":"2026-07-05T00:40:26.908442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:26.908442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ZFho0XJ5eugY223xMCm+imh37nk1ZDZj6bGADcxQfT/1GQlXOmRxuLlieqDobI7ZDy/O/8mosIAJQF570W5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:26.908949Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.05663","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:793994d504195cd0aa77368468616d805eacadc532ab2fca6e490aa5acf08b29","sha256:ab0c6fe58988cbf2f0a8c65170875a040696dca70aaa5d087bdff57f877309f5"],"state_sha256":"cb3a9668c2a1ab1667f90c2784bb26762a2a4d3cfaad4a2119730181182b6bfb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bRxxi6Tsng7xz+8oeO5LPwOmockc7DjmCwLjtmgwR22qB0rFOQThnh50RkBom2hM1uNi0EjH3P4xolTamUA0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:59:24.988323Z","bundle_sha256":"ba290bf6dfd104631b75cbcfc461fcfc594b1e4f1941a26a94f67e031e37205e"}}