{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DTK5AH6XOZMP3FIIENZJPK6ERL","short_pith_number":"pith:DTK5AH6X","canonical_record":{"source":{"id":"1802.06139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-16T21:55:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"10b2d559f269c29ed07324f8ec91122fc43bfe2276e24a966984a4c83ee25e5c","abstract_canon_sha256":"b63c4c11fde6d7e345e39cac1d67468572c912a73f424d14f995a0929ca4cdc8"},"schema_version":"1.0"},"canonical_sha256":"1cd5d01fd77658fd9508237297abc48af7f735fec7646e3535b13d1cf5cc8041","source":{"kind":"arxiv","id":"1802.06139","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06139","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06139v1","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06139","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"pith_short_12","alias_value":"DTK5AH6XOZMP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DTK5AH6XOZMP3FII","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DTK5AH6X","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DTK5AH6XOZMP3FIIENZJPK6ERL","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-16T21:55:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"10b2d559f269c29ed07324f8ec91122fc43bfe2276e24a966984a4c83ee25e5c","abstract_canon_sha256":"b63c4c11fde6d7e345e39cac1d67468572c912a73f424d14f995a0929ca4cdc8"},"schema_version":"1.0"},"canonical_sha256":"1cd5d01fd77658fd9508237297abc48af7f735fec7646e3535b13d1cf5cc8041","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:08.901286Z","signature_b64":"al18FN4Bjewwrnaqq9eNKG3k3c/jp60tDjVyTyPk2KMfBlGp9jkQoiYON/6zBpkuNQxay0JxJUcnRijSSPyAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cd5d01fd77658fd9508237297abc48af7f735fec7646e3535b13d1cf5cc8041","last_reissued_at":"2026-05-18T00:12:08.900566Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:08.900566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06139","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":"2026-05-18T00:12:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TQOliRWXVM61q5OfIiEyrfjdeTzmauOmb/RzoNYjmaPstZjWqliznACclbjn9ATMeRYqAf7VA88xXXyGZ856Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:46:49.827237Z"},"content_sha256":"f26c475ef42f3c2b3c8bd4016132ba1e494ad462c09ead52890e7bda19d22df8","schema_version":"1.0","event_id":"sha256:f26c475ef42f3c2b3c8bd4016132ba1e494ad462c09ead52890e7bda19d22df8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DTK5AH6XOZMP3FIIENZJPK6ERL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reactive Reinforcement Learning in Asynchronous Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jaden B. Travnik, Kory W. Mathewson, Patrick M. Pilarski, Richard S. Sutton","submitted_at":"2018-02-16T21:55:01Z","abstract_excerpt":"The relationship between a reinforcement learning (RL) agent and an asynchronous environment is often ignored. Frequently used models of the interaction between an agent and its environment, such as Markov Decision Processes (MDP) or Semi-Markov Decision Processes (SMDP), do not capture the fact that, in an asynchronous environment, the state of the environment may change during computation performed by the agent. In an asynchronous environment, minimizing reaction time---the time it takes for an agent to react to an observation---also minimizes the time in which the state of the environment m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06139","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":"2026-05-18T00:12:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x2g/yqssCay7vZvbElUNllHMt5Z4MG1+bpxKDPj8+bMTbENthtqCbGYi0OLa0lnDt0AJA+UY/cOvLcLzxiiVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:46:49.827613Z"},"content_sha256":"1f7ff5de7b1eef59fe42dc6d1129ac2e70d1026aadcf9364d8093cdf41ddfb6f","schema_version":"1.0","event_id":"sha256:1f7ff5de7b1eef59fe42dc6d1129ac2e70d1026aadcf9364d8093cdf41ddfb6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DTK5AH6XOZMP3FIIENZJPK6ERL/bundle.json","state_url":"https://pith.science/pith/DTK5AH6XOZMP3FIIENZJPK6ERL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DTK5AH6XOZMP3FIIENZJPK6ERL/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":"2026-06-01T04:46:49Z","links":{"resolver":"https://pith.science/pith/DTK5AH6XOZMP3FIIENZJPK6ERL","bundle":"https://pith.science/pith/DTK5AH6XOZMP3FIIENZJPK6ERL/bundle.json","state":"https://pith.science/pith/DTK5AH6XOZMP3FIIENZJPK6ERL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DTK5AH6XOZMP3FIIENZJPK6ERL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DTK5AH6XOZMP3FIIENZJPK6ERL","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":"b63c4c11fde6d7e345e39cac1d67468572c912a73f424d14f995a0929ca4cdc8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-16T21:55:01Z","title_canon_sha256":"10b2d559f269c29ed07324f8ec91122fc43bfe2276e24a966984a4c83ee25e5c"},"schema_version":"1.0","source":{"id":"1802.06139","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06139","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06139v1","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06139","created_at":"2026-05-18T00:12:08Z"},{"alias_kind":"pith_short_12","alias_value":"DTK5AH6XOZMP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DTK5AH6XOZMP3FII","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DTK5AH6X","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:1f7ff5de7b1eef59fe42dc6d1129ac2e70d1026aadcf9364d8093cdf41ddfb6f","target":"graph","created_at":"2026-05-18T00:12:08Z","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":"The relationship between a reinforcement learning (RL) agent and an asynchronous environment is often ignored. Frequently used models of the interaction between an agent and its environment, such as Markov Decision Processes (MDP) or Semi-Markov Decision Processes (SMDP), do not capture the fact that, in an asynchronous environment, the state of the environment may change during computation performed by the agent. In an asynchronous environment, minimizing reaction time---the time it takes for an agent to react to an observation---also minimizes the time in which the state of the environment m","authors_text":"Jaden B. Travnik, Kory W. Mathewson, Patrick M. Pilarski, Richard S. Sutton","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-16T21:55:01Z","title":"Reactive Reinforcement Learning in Asynchronous Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06139","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:f26c475ef42f3c2b3c8bd4016132ba1e494ad462c09ead52890e7bda19d22df8","target":"record","created_at":"2026-05-18T00:12:08Z","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":"b63c4c11fde6d7e345e39cac1d67468572c912a73f424d14f995a0929ca4cdc8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-16T21:55:01Z","title_canon_sha256":"10b2d559f269c29ed07324f8ec91122fc43bfe2276e24a966984a4c83ee25e5c"},"schema_version":"1.0","source":{"id":"1802.06139","kind":"arxiv","version":1}},"canonical_sha256":"1cd5d01fd77658fd9508237297abc48af7f735fec7646e3535b13d1cf5cc8041","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cd5d01fd77658fd9508237297abc48af7f735fec7646e3535b13d1cf5cc8041","first_computed_at":"2026-05-18T00:12:08.900566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:08.900566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"al18FN4Bjewwrnaqq9eNKG3k3c/jp60tDjVyTyPk2KMfBlGp9jkQoiYON/6zBpkuNQxay0JxJUcnRijSSPyAAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:08.901286Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06139","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f26c475ef42f3c2b3c8bd4016132ba1e494ad462c09ead52890e7bda19d22df8","sha256:1f7ff5de7b1eef59fe42dc6d1129ac2e70d1026aadcf9364d8093cdf41ddfb6f"],"state_sha256":"7449261a5188eb4299f94acc68969298c62147d9971fdab4ab44a41c4b42f7e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nUP3CpbaOku4POH8Xcr4bVUrvdkGlWxeXeSdAmcbWz3W0WIEbSZuxOOX0ryW2vAvTNHYVFbeDB14/aocoja/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T04:46:49.829662Z","bundle_sha256":"59601585d5dce84de23e3a6abb38ee03c8e7df1ade96ca6c6137597f08bd08d3"}}