{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4BIRRFLBVSCPSR57JZUCKBINOZ","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":"8bf6f3e567f8a5bc400dd789fabb12988c5bdd2b3aa67154b891851dfae9b606","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-12T13:52:06Z","title_canon_sha256":"d7bb937d5d2ad3fb979aa990aab5e7dc92850a835b3cc8e325721ff30657ffda"},"schema_version":"1.0","source":{"id":"2211.06665","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06665","created_at":"2026-07-05T12:01:16Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06665v6","created_at":"2026-07-05T12:01:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06665","created_at":"2026-07-05T12:01:16Z"},{"alias_kind":"pith_short_12","alias_value":"4BIRRFLBVSCP","created_at":"2026-07-05T12:01:16Z"},{"alias_kind":"pith_short_16","alias_value":"4BIRRFLBVSCPSR57","created_at":"2026-07-05T12:01:16Z"},{"alias_kind":"pith_short_8","alias_value":"4BIRRFLB","created_at":"2026-07-05T12:01:16Z"}],"graph_snapshots":[{"event_id":"sha256:5f1284e03874425ec3677be1e6d96797d04d0c7ec62a2eccfb035c873e6420fd","target":"graph","created_at":"2026-07-05T12:01:16Z","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/2211.06665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of deep learning, Deep RL (DRL) has witnessed great success over a wide spectrum of complex control tasks. Despite the encouraging results achieved, the deep neural network-based backbone is widely deemed as a black box that impedes practitioners to trust and employ trained agents in realistic scenarios where high security and reliability are essential. To alleviate this issue, a large volume of literature devoted to she","authors_text":"Huiqiong Wang, Jie Song, Kaixuan Chen, Mingli Song, Shunyu Liu, Yang Zhou, Yunpeng Qing","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-12T13:52:06Z","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06665","kind":"arxiv","version":6},"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:ad0e09edee7aafe1186f7a37b48ee1da841eb6b89919680e24f02e593bfec187","target":"record","created_at":"2026-07-05T12:01:16Z","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":"8bf6f3e567f8a5bc400dd789fabb12988c5bdd2b3aa67154b891851dfae9b606","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-12T13:52:06Z","title_canon_sha256":"d7bb937d5d2ad3fb979aa990aab5e7dc92850a835b3cc8e325721ff30657ffda"},"schema_version":"1.0","source":{"id":"2211.06665","kind":"arxiv","version":6}},"canonical_sha256":"e051189561ac84f947bf4e6825050d7666d56d1ba047aa30993a56c7b50cdc04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e051189561ac84f947bf4e6825050d7666d56d1ba047aa30993a56c7b50cdc04","first_computed_at":"2026-07-05T12:01:16.919871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:16.919871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ofd/lYAMbrJ2wM5+tPy4dCOka8IltWXAr2axNmgmVvYBDypupNMpGTaJXCeajiX1Q6uYW2YZnatFjCS5v/ZyBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:16.920345Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.06665","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad0e09edee7aafe1186f7a37b48ee1da841eb6b89919680e24f02e593bfec187","sha256:5f1284e03874425ec3677be1e6d96797d04d0c7ec62a2eccfb035c873e6420fd"],"state_sha256":"b68e2970f672ea8e0915185f6cd993cd89159452f3bd8ad965afc0181aa2beb5"}