{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EOAROZ6QDZXXRBVGEIHPARTKSC","short_pith_number":"pith:EOAROZ6Q","canonical_record":{"source":{"id":"1805.11447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T13:34:39Z","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"title_canon_sha256":"1a46a5ade1d0480c033da7adf4a072281f47b507bd3a204fff100620da7e3c0f","abstract_canon_sha256":"2278822d512fe29fc7ee54f76880a9321c007fef2cd2499a59e117f7182aaa16"},"schema_version":"1.0"},"canonical_sha256":"23811767d01e6f7886a6220ef0466a909fc1124c404beea583099a265e092985","source":{"kind":"arxiv","id":"1805.11447","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11447","created_at":"2026-05-18T00:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11447v1","created_at":"2026-05-18T00:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11447","created_at":"2026-05-18T00:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"EOAROZ6QDZXX","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EOAROZ6QDZXXRBVG","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EOAROZ6Q","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EOAROZ6QDZXXRBVGEIHPARTKSC","target":"record","payload":{"canonical_record":{"source":{"id":"1805.11447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T13:34:39Z","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"title_canon_sha256":"1a46a5ade1d0480c033da7adf4a072281f47b507bd3a204fff100620da7e3c0f","abstract_canon_sha256":"2278822d512fe29fc7ee54f76880a9321c007fef2cd2499a59e117f7182aaa16"},"schema_version":"1.0"},"canonical_sha256":"23811767d01e6f7886a6220ef0466a909fc1124c404beea583099a265e092985","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:42.528736Z","signature_b64":"89AG303iJ/fU+UNlKW6pA5R+DneBxLpriAwpesCLjVKh+4g9sLTKZBG8zGee95GQO0HLpRQzS66C6UwAzeLzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23811767d01e6f7886a6220ef0466a909fc1124c404beea583099a265e092985","last_reissued_at":"2026-05-18T00:14:42.528201Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:42.528201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.11447","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":"2026-05-18T00:14:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N1AW1a8px+9pdUFOhJWpADUb7Dnskw7fOd7ca0ey5UnaZ0ILIP9HuA4JJimiRG8Xc7kN6rQdfBWp2YivJYFhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T03:51:25.451033Z"},"content_sha256":"bffde120df58a0ec103b4334d45a5c8918e75ea89cfb4d3f9361ba9ee71d0a33","schema_version":"1.0","event_id":"sha256:bffde120df58a0ec103b4334d45a5c8918e75ea89cfb4d3f9361ba9ee71d0a33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EOAROZ6QDZXXRBVGEIHPARTKSC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Virtuously Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Maurer, El Mahdi El Mhamdi, Henrik Aslund, Rachid Guerraoui","submitted_at":"2018-05-29T13:34:39Z","abstract_excerpt":"We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the optimal policy in the limit, and the probability of escaping a dangerous situation created by the adversary. So far, the work on safely interruptible agents has assumed a perfect perception of the agent about its environment (no adversary), and therefore implicitly set the second probability to zero, by explicitly seeking a value of one for the first probability. We show that (1)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11447","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":"2026-05-18T00:14:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DF+w7dmt/SXEvl4svp0kpiSIqcQ+DKJBGzdmNvolRoW4KdbMiWu+D2fTCaEYeIPZ8D5pK0X37+KauLR2HNpeCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T03:51:25.451777Z"},"content_sha256":"672bdbad8d4b61978eaa477198c3c33c2bf2f7964c7f44f0a4587eea4294af17","schema_version":"1.0","event_id":"sha256:672bdbad8d4b61978eaa477198c3c33c2bf2f7964c7f44f0a4587eea4294af17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EOAROZ6QDZXXRBVGEIHPARTKSC/bundle.json","state_url":"https://pith.science/pith/EOAROZ6QDZXXRBVGEIHPARTKSC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EOAROZ6QDZXXRBVGEIHPARTKSC/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":"2026-06-10T03:51:25Z","links":{"resolver":"https://pith.science/pith/EOAROZ6QDZXXRBVGEIHPARTKSC","bundle":"https://pith.science/pith/EOAROZ6QDZXXRBVGEIHPARTKSC/bundle.json","state":"https://pith.science/pith/EOAROZ6QDZXXRBVGEIHPARTKSC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EOAROZ6QDZXXRBVGEIHPARTKSC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EOAROZ6QDZXXRBVGEIHPARTKSC","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":"2278822d512fe29fc7ee54f76880a9321c007fef2cd2499a59e117f7182aaa16","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T13:34:39Z","title_canon_sha256":"1a46a5ade1d0480c033da7adf4a072281f47b507bd3a204fff100620da7e3c0f"},"schema_version":"1.0","source":{"id":"1805.11447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11447","created_at":"2026-05-18T00:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11447v1","created_at":"2026-05-18T00:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11447","created_at":"2026-05-18T00:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"EOAROZ6QDZXX","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EOAROZ6QDZXXRBVG","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EOAROZ6Q","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:672bdbad8d4b61978eaa477198c3c33c2bf2f7964c7f44f0a4587eea4294af17","target":"graph","created_at":"2026-05-18T00:14:42Z","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":"We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the optimal policy in the limit, and the probability of escaping a dangerous situation created by the adversary. So far, the work on safely interruptible agents has assumed a perfect perception of the agent about its environment (no adversary), and therefore implicitly set the second probability to zero, by explicitly seeking a value of one for the first probability. We show that (1)","authors_text":"Alexandre Maurer, El Mahdi El Mhamdi, Henrik Aslund, Rachid Guerraoui","cross_cats":["cs.AI","cs.GT","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T13:34:39Z","title":"Virtuously Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11447","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:bffde120df58a0ec103b4334d45a5c8918e75ea89cfb4d3f9361ba9ee71d0a33","target":"record","created_at":"2026-05-18T00:14:42Z","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":"2278822d512fe29fc7ee54f76880a9321c007fef2cd2499a59e117f7182aaa16","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T13:34:39Z","title_canon_sha256":"1a46a5ade1d0480c033da7adf4a072281f47b507bd3a204fff100620da7e3c0f"},"schema_version":"1.0","source":{"id":"1805.11447","kind":"arxiv","version":1}},"canonical_sha256":"23811767d01e6f7886a6220ef0466a909fc1124c404beea583099a265e092985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23811767d01e6f7886a6220ef0466a909fc1124c404beea583099a265e092985","first_computed_at":"2026-05-18T00:14:42.528201Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:42.528201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"89AG303iJ/fU+UNlKW6pA5R+DneBxLpriAwpesCLjVKh+4g9sLTKZBG8zGee95GQO0HLpRQzS66C6UwAzeLzCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:42.528736Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.11447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bffde120df58a0ec103b4334d45a5c8918e75ea89cfb4d3f9361ba9ee71d0a33","sha256:672bdbad8d4b61978eaa477198c3c33c2bf2f7964c7f44f0a4587eea4294af17"],"state_sha256":"6fc6b3ddb75b803640cc9ad8016f30b96932adf7cdd1be1cc359e634ab55c30c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UsjboCLiwjGF1mCQc7tRLipcJzNG5UaikRSg6nGmjpccScTZrDkAChUJxK4lgpio34fbw9oC7vwzD9bBPUBACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T03:51:25.456151Z","bundle_sha256":"8d3287594167667ae195fbe98117c3a094556ca0152fea869ff20165665adbd6"}}