{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XZZLJ7VHFMFLUCACEQKQH3YTW4","short_pith_number":"pith:XZZLJ7VH","canonical_record":{"source":{"id":"1809.04232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-12T02:43:19Z","cross_cats_sorted":[],"title_canon_sha256":"5ef29bfc8eb72179e70180ce1d978164a38fe04bafad2fd3a8c4d2394efd5a62","abstract_canon_sha256":"7e70c414f669bed4c91c48ed893f44738a02a33a209b174441bd41792d6b06fa"},"schema_version":"1.0"},"canonical_sha256":"be72b4fea72b0aba0802241503ef13b7149f8d1846fb622ae57cf1e8c3f1426e","source":{"kind":"arxiv","id":"1809.04232","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04232","created_at":"2026-05-18T00:05:53Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04232v1","created_at":"2026-05-18T00:05:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04232","created_at":"2026-05-18T00:05:53Z"},{"alias_kind":"pith_short_12","alias_value":"XZZLJ7VHFMFL","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"XZZLJ7VHFMFLUCAC","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"XZZLJ7VH","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XZZLJ7VHFMFLUCACEQKQH3YTW4","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-12T02:43:19Z","cross_cats_sorted":[],"title_canon_sha256":"5ef29bfc8eb72179e70180ce1d978164a38fe04bafad2fd3a8c4d2394efd5a62","abstract_canon_sha256":"7e70c414f669bed4c91c48ed893f44738a02a33a209b174441bd41792d6b06fa"},"schema_version":"1.0"},"canonical_sha256":"be72b4fea72b0aba0802241503ef13b7149f8d1846fb622ae57cf1e8c3f1426e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:53.076091Z","signature_b64":"3IblvA41X5tcUfNJWMuXWOghPxHihbN14GBmzXmQXeredUjP4uvZfI4ZzAdUiLTOi6RpfZ6uO3ZpAAbgslCZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be72b4fea72b0aba0802241503ef13b7149f8d1846fb622ae57cf1e8c3f1426e","last_reissued_at":"2026-05-18T00:05:53.075447Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:53.075447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04232","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":"2026-05-18T00:05:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i9wjKA8vGbYsmQV109BQWgorELBcJwUM2uhkFivvQE5f7wPGObtA6TEy5/pyXRm4RTd/sBh+XlEWsZMQFtjmCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T19:08:19.867204Z"},"content_sha256":"6185fc6af18651e700fab20717b0392b54594a4de84fdb93297f22beec0dab68","schema_version":"1.0","event_id":"sha256:6185fc6af18651e700fab20717b0392b54594a4de84fdb93297f22beec0dab68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XZZLJ7VHFMFLUCACEQKQH3YTW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Exploration in Markov Decision Processes with Time-Variant Safety using Spatio-Temporal Gaussian Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akifumi Wachi, Asim Munawar, Hiroshi Kajino","submitted_at":"2018-09-12T02:43:19Z","abstract_excerpt":"In many real-world applications (e.g., planetary exploration, robot navigation), an autonomous agent must be able to explore a space with guaranteed safety. Most safe exploration algorithms in the field of reinforcement learning and robotics have been based on the assumption that the safety features are a priori known and time-invariant. This paper presents a learning algorithm called ST-SafeMDP for exploring Markov decision processes (MDPs) that is based on the assumption that the safety features are a priori unknown and time-variant. In this setting, the agent explores MDPs while constrainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04232","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":"2026-05-18T00:05:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dubLaM2f9x7AwCp4KqOsYSfIV62fpmj7DgULfsXt5RD5B4k9zSSUh7DfIXhzGd18K+VpisCxEAW2WYe/ebULCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T19:08:19.867617Z"},"content_sha256":"295d1281c84cae4cb67fd3a484b09c4b3def73a53a809f064f55b51cc97706db","schema_version":"1.0","event_id":"sha256:295d1281c84cae4cb67fd3a484b09c4b3def73a53a809f064f55b51cc97706db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4/bundle.json","state_url":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4/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":"2026-06-23T19:08:19Z","links":{"resolver":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4","bundle":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4/bundle.json","state":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XZZLJ7VHFMFLUCACEQKQH3YTW4","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":"7e70c414f669bed4c91c48ed893f44738a02a33a209b174441bd41792d6b06fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-12T02:43:19Z","title_canon_sha256":"5ef29bfc8eb72179e70180ce1d978164a38fe04bafad2fd3a8c4d2394efd5a62"},"schema_version":"1.0","source":{"id":"1809.04232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04232","created_at":"2026-05-18T00:05:53Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04232v1","created_at":"2026-05-18T00:05:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04232","created_at":"2026-05-18T00:05:53Z"},{"alias_kind":"pith_short_12","alias_value":"XZZLJ7VHFMFL","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"XZZLJ7VHFMFLUCAC","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"XZZLJ7VH","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:295d1281c84cae4cb67fd3a484b09c4b3def73a53a809f064f55b51cc97706db","target":"graph","created_at":"2026-05-18T00:05:53Z","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":"In many real-world applications (e.g., planetary exploration, robot navigation), an autonomous agent must be able to explore a space with guaranteed safety. Most safe exploration algorithms in the field of reinforcement learning and robotics have been based on the assumption that the safety features are a priori known and time-invariant. This paper presents a learning algorithm called ST-SafeMDP for exploring Markov decision processes (MDPs) that is based on the assumption that the safety features are a priori unknown and time-variant. In this setting, the agent explores MDPs while constrainin","authors_text":"Akifumi Wachi, Asim Munawar, Hiroshi Kajino","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-12T02:43:19Z","title":"Safe Exploration in Markov Decision Processes with Time-Variant Safety using Spatio-Temporal Gaussian Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04232","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":"sha256:6185fc6af18651e700fab20717b0392b54594a4de84fdb93297f22beec0dab68","target":"record","created_at":"2026-05-18T00:05:53Z","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":"7e70c414f669bed4c91c48ed893f44738a02a33a209b174441bd41792d6b06fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-12T02:43:19Z","title_canon_sha256":"5ef29bfc8eb72179e70180ce1d978164a38fe04bafad2fd3a8c4d2394efd5a62"},"schema_version":"1.0","source":{"id":"1809.04232","kind":"arxiv","version":1}},"canonical_sha256":"be72b4fea72b0aba0802241503ef13b7149f8d1846fb622ae57cf1e8c3f1426e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be72b4fea72b0aba0802241503ef13b7149f8d1846fb622ae57cf1e8c3f1426e","first_computed_at":"2026-05-18T00:05:53.075447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:53.075447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3IblvA41X5tcUfNJWMuXWOghPxHihbN14GBmzXmQXeredUjP4uvZfI4ZzAdUiLTOi6RpfZ6uO3ZpAAbgslCZBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:53.076091Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6185fc6af18651e700fab20717b0392b54594a4de84fdb93297f22beec0dab68","sha256:295d1281c84cae4cb67fd3a484b09c4b3def73a53a809f064f55b51cc97706db"],"state_sha256":"03e75778b1b21885f6ed6564f3d30de201367e2466a128342ef645344364761d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YxrhvtmPuCSR6r4UZQu25qhYl+gDpqYdcdJtxhOzLj4cPXGMm2lW61RTLKzum1vF0EKV28rC7L7dEc2CX6/WAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-23T19:08:19.869581Z","bundle_sha256":"65e29f87201d7f984e643e12dc59fb81200550149e65a258b8ec2893234387ae"}}