{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GACJN4TLJ3F3S7W66WPWMY4PA5","short_pith_number":"pith:GACJN4TL","canonical_record":{"source":{"id":"2107.04200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-09T04:24:40Z","cross_cats_sorted":[],"title_canon_sha256":"ea2cbd7f60f8774a229ac0a7583a12f9bbab46af6bb318b70de23d663bfeb486","abstract_canon_sha256":"87d40181690c3cbffd4ad851da3c8b9c51b2f8a190f7ab038dc0b8c0ee4f3ed5"},"schema_version":"1.0"},"canonical_sha256":"300496f26b4ecbb97edef59f66638f076a145a8873f2b3a11334fc666157a940","source":{"kind":"arxiv","id":"2107.04200","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.04200","created_at":"2026-07-05T02:56:30Z"},{"alias_kind":"arxiv_version","alias_value":"2107.04200v1","created_at":"2026-07-05T02:56:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04200","created_at":"2026-07-05T02:56:30Z"},{"alias_kind":"pith_short_12","alias_value":"GACJN4TLJ3F3","created_at":"2026-07-05T02:56:30Z"},{"alias_kind":"pith_short_16","alias_value":"GACJN4TLJ3F3S7W6","created_at":"2026-07-05T02:56:30Z"},{"alias_kind":"pith_short_8","alias_value":"GACJN4TL","created_at":"2026-07-05T02:56:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GACJN4TLJ3F3S7W66WPWMY4PA5","target":"record","payload":{"canonical_record":{"source":{"id":"2107.04200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-09T04:24:40Z","cross_cats_sorted":[],"title_canon_sha256":"ea2cbd7f60f8774a229ac0a7583a12f9bbab46af6bb318b70de23d663bfeb486","abstract_canon_sha256":"87d40181690c3cbffd4ad851da3c8b9c51b2f8a190f7ab038dc0b8c0ee4f3ed5"},"schema_version":"1.0"},"canonical_sha256":"300496f26b4ecbb97edef59f66638f076a145a8873f2b3a11334fc666157a940","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:30.641116Z","signature_b64":"AfaTBeMnJ62hhdYs1JUksjy8AnP0yDtK8iNl7OSmOcTPXDNrqu6UOxG25lSK5Xyv1E6MUN6KnRVxlJhRQWV9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"300496f26b4ecbb97edef59f66638f076a145a8873f2b3a11334fc666157a940","last_reissued_at":"2026-07-05T02:56:30.640724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:30.640724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.04200","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":"2026-07-05T02:56:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pnKbjrGCMrzq/OHtZnPUpO/4H2JJ0l1OlV7nEihSQjIo6h1GiJFOx6RHUgBfgTdbMa+cx/T0xKahHKn8ef6jAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T15:50:23.264249Z"},"content_sha256":"37be3c253198cd977622b4b54f5f6cd36eab5d06befe28d4e6d55e5f456a3842","schema_version":"1.0","event_id":"sha256:37be3c253198cd977622b4b54f5f6cd36eab5d06befe28d4e6d55e5f456a3842"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GACJN4TLJ3F3S7W66WPWMY4PA5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Exploration by Solving Early Terminated MDP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Dai, Bolei Zhou, Hao Sun, Jiadong Guo, Meng Fang, Zhenghao Peng, Ziping Xu","submitted_at":"2021-07-09T04:24:40Z","abstract_excerpt":"Safe exploration is crucial for the real-world application of reinforcement learning (RL). Previous works consider the safe exploration problem as Constrained Markov Decision Process (CMDP), where the policies are being optimized under constraints. However, when encountering any potential dangers, human tends to stop immediately and rarely learns to behave safely in danger. Motivated by human learning, we introduce a new approach to address safe RL problems under the framework of Early Terminated MDP (ET-MDP). We first define the ET-MDP as an unconstrained MDP with the same optimal value funct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04200","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/2107.04200/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":"2026-07-05T02:56:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oDP1YD3SSP1CshKHEv/IapgDolq3rEuap4yEG1oc2K4gSR45l/n8fvCeEgPEqbQQ+5GCMX6vK5YrbiTQQ9I5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T15:50:23.264631Z"},"content_sha256":"8180eb4bbb47d7c757cca995641c9fec22e11a82a6a01d69b183fb7a1bc13cde","schema_version":"1.0","event_id":"sha256:8180eb4bbb47d7c757cca995641c9fec22e11a82a6a01d69b183fb7a1bc13cde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GACJN4TLJ3F3S7W66WPWMY4PA5/bundle.json","state_url":"https://pith.science/pith/GACJN4TLJ3F3S7W66WPWMY4PA5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GACJN4TLJ3F3S7W66WPWMY4PA5/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":"2026-07-25T15:50:23Z","links":{"resolver":"https://pith.science/pith/GACJN4TLJ3F3S7W66WPWMY4PA5","bundle":"https://pith.science/pith/GACJN4TLJ3F3S7W66WPWMY4PA5/bundle.json","state":"https://pith.science/pith/GACJN4TLJ3F3S7W66WPWMY4PA5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GACJN4TLJ3F3S7W66WPWMY4PA5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GACJN4TLJ3F3S7W66WPWMY4PA5","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":"87d40181690c3cbffd4ad851da3c8b9c51b2f8a190f7ab038dc0b8c0ee4f3ed5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-09T04:24:40Z","title_canon_sha256":"ea2cbd7f60f8774a229ac0a7583a12f9bbab46af6bb318b70de23d663bfeb486"},"schema_version":"1.0","source":{"id":"2107.04200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.04200","created_at":"2026-07-05T02:56:30Z"},{"alias_kind":"arxiv_version","alias_value":"2107.04200v1","created_at":"2026-07-05T02:56:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04200","created_at":"2026-07-05T02:56:30Z"},{"alias_kind":"pith_short_12","alias_value":"GACJN4TLJ3F3","created_at":"2026-07-05T02:56:30Z"},{"alias_kind":"pith_short_16","alias_value":"GACJN4TLJ3F3S7W6","created_at":"2026-07-05T02:56:30Z"},{"alias_kind":"pith_short_8","alias_value":"GACJN4TL","created_at":"2026-07-05T02:56:30Z"}],"graph_snapshots":[{"event_id":"sha256:8180eb4bbb47d7c757cca995641c9fec22e11a82a6a01d69b183fb7a1bc13cde","target":"graph","created_at":"2026-07-05T02:56:30Z","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/2107.04200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe exploration is crucial for the real-world application of reinforcement learning (RL). Previous works consider the safe exploration problem as Constrained Markov Decision Process (CMDP), where the policies are being optimized under constraints. However, when encountering any potential dangers, human tends to stop immediately and rarely learns to behave safely in danger. Motivated by human learning, we introduce a new approach to address safe RL problems under the framework of Early Terminated MDP (ET-MDP). We first define the ET-MDP as an unconstrained MDP with the same optimal value funct","authors_text":"Bo Dai, Bolei Zhou, Hao Sun, Jiadong Guo, Meng Fang, Zhenghao Peng, Ziping Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-09T04:24:40Z","title":"Safe Exploration by Solving Early Terminated MDP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04200","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":"sha256:37be3c253198cd977622b4b54f5f6cd36eab5d06befe28d4e6d55e5f456a3842","target":"record","created_at":"2026-07-05T02:56:30Z","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":"87d40181690c3cbffd4ad851da3c8b9c51b2f8a190f7ab038dc0b8c0ee4f3ed5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-09T04:24:40Z","title_canon_sha256":"ea2cbd7f60f8774a229ac0a7583a12f9bbab46af6bb318b70de23d663bfeb486"},"schema_version":"1.0","source":{"id":"2107.04200","kind":"arxiv","version":1}},"canonical_sha256":"300496f26b4ecbb97edef59f66638f076a145a8873f2b3a11334fc666157a940","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"300496f26b4ecbb97edef59f66638f076a145a8873f2b3a11334fc666157a940","first_computed_at":"2026-07-05T02:56:30.640724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:56:30.640724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AfaTBeMnJ62hhdYs1JUksjy8AnP0yDtK8iNl7OSmOcTPXDNrqu6UOxG25lSK5Xyv1E6MUN6KnRVxlJhRQWV9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:56:30.641116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.04200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37be3c253198cd977622b4b54f5f6cd36eab5d06befe28d4e6d55e5f456a3842","sha256:8180eb4bbb47d7c757cca995641c9fec22e11a82a6a01d69b183fb7a1bc13cde"],"state_sha256":"ae8ee5e374294d9eac2922a9067009483b922fd08ea82d5606303894b7f3e9f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GP85WfY3ABrNlZ9233QL7wyK5dRIFxpUXEihwisQn23l+pu90R3C6z1O13QiUOsoNIOiihUDl+mhh7l/TMBODg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T15:50:23.266899Z","bundle_sha256":"d53d8174d390689317f0a6d122b2e709862d17dac156b262ab342e9ce6cc38d8"}}