{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4BIRRFLBVSCPSR57JZUCKBINOZ","short_pith_number":"pith:4BIRRFLB","schema_version":"1.0","canonical_sha256":"e051189561ac84f947bf4e6825050d7666d56d1ba047aa30993a56c7b50cdc04","source":{"kind":"arxiv","id":"2211.06665","version":6},"attestation_state":"computed","paper":{"title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Huiqiong Wang, Jie Song, Kaixuan Chen, Mingli Song, Shunyu Liu, Yang Zhou, Yunpeng Qing","submitted_at":"2022-11-12T13:52:06Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.06665","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-12T13:52:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7bb937d5d2ad3fb979aa990aab5e7dc92850a835b3cc8e325721ff30657ffda","abstract_canon_sha256":"8bf6f3e567f8a5bc400dd789fabb12988c5bdd2b3aa67154b891851dfae9b606"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:16.920345Z","signature_b64":"ofd/lYAMbrJ2wM5+tPy4dCOka8IltWXAr2axNmgmVvYBDypupNMpGTaJXCeajiX1Q6uYW2YZnatFjCS5v/ZyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e051189561ac84f947bf4e6825050d7666d56d1ba047aa30993a56c7b50cdc04","last_reissued_at":"2026-07-05T12:01:16.919871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:16.919871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Huiqiong Wang, Jie Song, Kaixuan Chen, Mingli Song, Shunyu Liu, Yang Zhou, Yunpeng Qing","submitted_at":"2022-11-12T13:52:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06665","kind":"arxiv","version":6},"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/2211.06665/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.06665","created_at":"2026-07-05T12:01:16.919930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.06665v6","created_at":"2026-07-05T12:01:16.919930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06665","created_at":"2026-07-05T12:01:16.919930+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BIRRFLBVSCP","created_at":"2026-07-05T12:01:16.919930+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BIRRFLBVSCPSR57","created_at":"2026-07-05T12:01:16.919930+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BIRRFLB","created_at":"2026-07-05T12:01:16.919930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24622","citing_title":"Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22447","citing_title":"A Differentiable Atari VCS:A Complex, Fully Known Ground Truth for Explainable AI","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05762","citing_title":"BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4BIRRFLBVSCPSR57JZUCKBINOZ","json":"https://pith.science/pith/4BIRRFLBVSCPSR57JZUCKBINOZ.json","graph_json":"https://pith.science/api/pith-number/4BIRRFLBVSCPSR57JZUCKBINOZ/graph.json","events_json":"https://pith.science/api/pith-number/4BIRRFLBVSCPSR57JZUCKBINOZ/events.json","paper":"https://pith.science/paper/4BIRRFLB"},"agent_actions":{"view_html":"https://pith.science/pith/4BIRRFLBVSCPSR57JZUCKBINOZ","download_json":"https://pith.science/pith/4BIRRFLBVSCPSR57JZUCKBINOZ.json","view_paper":"https://pith.science/paper/4BIRRFLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.06665&json=true","fetch_graph":"https://pith.science/api/pith-number/4BIRRFLBVSCPSR57JZUCKBINOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4BIRRFLBVSCPSR57JZUCKBINOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BIRRFLBVSCPSR57JZUCKBINOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BIRRFLBVSCPSR57JZUCKBINOZ/action/storage_attestation","attest_author":"https://pith.science/pith/4BIRRFLBVSCPSR57JZUCKBINOZ/action/author_attestation","sign_citation":"https://pith.science/pith/4BIRRFLBVSCPSR57JZUCKBINOZ/action/citation_signature","submit_replication":"https://pith.science/pith/4BIRRFLBVSCPSR57JZUCKBINOZ/action/replication_record"}},"created_at":"2026-07-05T12:01:16.919930+00:00","updated_at":"2026-07-05T12:01:16.919930+00:00"}