{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QTIXWV6HQIF2IJJG3G447XGO27","short_pith_number":"pith:QTIXWV6H","canonical_record":{"source":{"id":"2008.06626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-15T02:20:23Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"bed14228450d6ec407ecce2365811cfbea0abf45ad4f01cfa834100b3a6db3db","abstract_canon_sha256":"0cd805bdd64cad93ca9050d4f3e9d5fc444afd3a24b133888ea379ac9d161564"},"schema_version":"1.0"},"canonical_sha256":"84d17b57c7820ba42526d9b9cfdcced7ee2506a0b9071af7f50bddb1c031079c","source":{"kind":"arxiv","id":"2008.06626","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.06626","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"arxiv_version","alias_value":"2008.06626v1","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06626","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"pith_short_12","alias_value":"QTIXWV6HQIF2","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"QTIXWV6HQIF2IJJG","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"QTIXWV6H","created_at":"2026-07-05T01:27:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QTIXWV6HQIF2IJJG3G447XGO27","target":"record","payload":{"canonical_record":{"source":{"id":"2008.06626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-15T02:20:23Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"bed14228450d6ec407ecce2365811cfbea0abf45ad4f01cfa834100b3a6db3db","abstract_canon_sha256":"0cd805bdd64cad93ca9050d4f3e9d5fc444afd3a24b133888ea379ac9d161564"},"schema_version":"1.0"},"canonical_sha256":"84d17b57c7820ba42526d9b9cfdcced7ee2506a0b9071af7f50bddb1c031079c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:30.298401Z","signature_b64":"QWwxCuaPr6cHilK+dZ2X/50x3aJGSfL9/83N7byM4/Oe5V0zUT1LqDX3hyDyM95tl89YjYkvp1SlfqCDShVRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84d17b57c7820ba42526d9b9cfdcced7ee2506a0b9071af7f50bddb1c031079c","last_reissued_at":"2026-07-05T01:27:30.297986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:30.297986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.06626","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":"2026-07-05T01:27:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sVlbjS726chbaYMzavmjdtUJM4OQ4xlXFoNdqRAYej8NLNZmX+C8pD8+xk1RceWwIrb6ZgqqX+dFnkKE0ObyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:13:52.948482Z"},"content_sha256":"a83759ee98a096d3908e90b264a446b77277cf1276d51436c649794d01cd4012","schema_version":"1.0","event_id":"sha256:a83759ee98a096d3908e90b264a446b77277cf1276d51436c649794d01cd4012"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QTIXWV6HQIF2IJJG3G447XGO27","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning in Constrained Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Akifumi Wachi, Yanan Sui","submitted_at":"2020-08-15T02:20:23Z","abstract_excerpt":"Safe reinforcement learning has been a promising approach for optimizing the policy of an agent that operates in safety-critical applications. In this paper, we propose an algorithm, SNO-MDP, that explores and optimizes Markov decision processes under unknown safety constraints. Specifically, we take a stepwise approach for optimizing safety and cumulative reward. In our method, the agent first learns safety constraints by expanding the safe region, and then optimizes the cumulative reward in the certified safe region. We provide theoretical guarantees on both the satisfaction of the safety co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06626","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.06626/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":"2026-07-05T01:27:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rmHPpgQen5OZlxXNHBd3Y0or1QHdAetx5cW2WMF99xvHZq6NHhF+978T8M2X1UImtnv7g6HLGPsOPVrqRqW3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:13:52.949005Z"},"content_sha256":"fd1092da3b37d6e8e811a0814fd9dbb06661df30497e8109692ed51d3b80b845","schema_version":"1.0","event_id":"sha256:fd1092da3b37d6e8e811a0814fd9dbb06661df30497e8109692ed51d3b80b845"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QTIXWV6HQIF2IJJG3G447XGO27/bundle.json","state_url":"https://pith.science/pith/QTIXWV6HQIF2IJJG3G447XGO27/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QTIXWV6HQIF2IJJG3G447XGO27/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":"2026-08-09T13:13:52Z","links":{"resolver":"https://pith.science/pith/QTIXWV6HQIF2IJJG3G447XGO27","bundle":"https://pith.science/pith/QTIXWV6HQIF2IJJG3G447XGO27/bundle.json","state":"https://pith.science/pith/QTIXWV6HQIF2IJJG3G447XGO27/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QTIXWV6HQIF2IJJG3G447XGO27/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QTIXWV6HQIF2IJJG3G447XGO27","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":"0cd805bdd64cad93ca9050d4f3e9d5fc444afd3a24b133888ea379ac9d161564","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-15T02:20:23Z","title_canon_sha256":"bed14228450d6ec407ecce2365811cfbea0abf45ad4f01cfa834100b3a6db3db"},"schema_version":"1.0","source":{"id":"2008.06626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.06626","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"arxiv_version","alias_value":"2008.06626v1","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06626","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"pith_short_12","alias_value":"QTIXWV6HQIF2","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"QTIXWV6HQIF2IJJG","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"QTIXWV6H","created_at":"2026-07-05T01:27:30Z"}],"graph_snapshots":[{"event_id":"sha256:fd1092da3b37d6e8e811a0814fd9dbb06661df30497e8109692ed51d3b80b845","target":"graph","created_at":"2026-07-05T01:27:30Z","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/2008.06626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe reinforcement learning has been a promising approach for optimizing the policy of an agent that operates in safety-critical applications. In this paper, we propose an algorithm, SNO-MDP, that explores and optimizes Markov decision processes under unknown safety constraints. Specifically, we take a stepwise approach for optimizing safety and cumulative reward. In our method, the agent first learns safety constraints by expanding the safe region, and then optimizes the cumulative reward in the certified safe region. We provide theoretical guarantees on both the satisfaction of the safety co","authors_text":"Akifumi Wachi, Yanan Sui","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-15T02:20:23Z","title":"Safe Reinforcement Learning in Constrained Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06626","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:a83759ee98a096d3908e90b264a446b77277cf1276d51436c649794d01cd4012","target":"record","created_at":"2026-07-05T01:27:30Z","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":"0cd805bdd64cad93ca9050d4f3e9d5fc444afd3a24b133888ea379ac9d161564","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-15T02:20:23Z","title_canon_sha256":"bed14228450d6ec407ecce2365811cfbea0abf45ad4f01cfa834100b3a6db3db"},"schema_version":"1.0","source":{"id":"2008.06626","kind":"arxiv","version":1}},"canonical_sha256":"84d17b57c7820ba42526d9b9cfdcced7ee2506a0b9071af7f50bddb1c031079c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84d17b57c7820ba42526d9b9cfdcced7ee2506a0b9071af7f50bddb1c031079c","first_computed_at":"2026-07-05T01:27:30.297986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:30.297986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QWwxCuaPr6cHilK+dZ2X/50x3aJGSfL9/83N7byM4/Oe5V0zUT1LqDX3hyDyM95tl89YjYkvp1SlfqCDShVRAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:30.298401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.06626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a83759ee98a096d3908e90b264a446b77277cf1276d51436c649794d01cd4012","sha256:fd1092da3b37d6e8e811a0814fd9dbb06661df30497e8109692ed51d3b80b845"],"state_sha256":"f789262a2e7532ffebeaaa456c9fb413a3f33780b17d7fce045a0a9d6cfc8cc7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kiTqgi2RnHHahXdPoI+mvdot36AsVpM9Q46shJiaI2zW9kYzWH4sets9kcQM4E+kqC8DkEiQ9Hgsd4WCrsvJCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:13:52.954015Z","bundle_sha256":"9db91afd724d8d881cdadf4d4cdc59ce1497a81e17ecd232dacce9dcdd17f386"}}