{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2RTV4HUGK2UCRMFZMQRS3MMRGI","short_pith_number":"pith:2RTV4HUG","canonical_record":{"source":{"id":"2502.06869","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T05:30:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c61ba44527af146cd95f2775717286f13f252f0484b074d3dfeb7139742cd67","abstract_canon_sha256":"3aa64232dd9349b75b386e9da465c9047fe66ba607aabc53dc090cdb59da4d2f"},"schema_version":"1.0"},"canonical_sha256":"d4675e1e8656a828b0b964232db1913233c9cad9dcb9b4bef5b6da4045e4b578","source":{"kind":"arxiv","id":"2502.06869","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06869","created_at":"2026-07-05T10:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06869v1","created_at":"2026-07-05T10:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06869","created_at":"2026-07-05T10:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"2RTV4HUGK2UC","created_at":"2026-07-05T10:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"2RTV4HUGK2UCRMFZ","created_at":"2026-07-05T10:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"2RTV4HUG","created_at":"2026-07-05T10:12:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2RTV4HUGK2UCRMFZMQRS3MMRGI","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06869","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T05:30:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c61ba44527af146cd95f2775717286f13f252f0484b074d3dfeb7139742cd67","abstract_canon_sha256":"3aa64232dd9349b75b386e9da465c9047fe66ba607aabc53dc090cdb59da4d2f"},"schema_version":"1.0"},"canonical_sha256":"d4675e1e8656a828b0b964232db1913233c9cad9dcb9b4bef5b6da4045e4b578","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:29.177889Z","signature_b64":"t63w9XLXtJ9BIAjcNvFZpXdGFyMh7/RWdas/dU7IKqaSZryCFnZvsfrzSR4tfOJKN293NxiIFjkHv7xkZg6eCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4675e1e8656a828b0b964232db1913233c9cad9dcb9b4bef5b6da4045e4b578","last_reissued_at":"2026-07-05T10:12:29.177403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:29.177403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06869","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":"2026-07-05T10:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QczyQze9irP7NdGbhxxxp2lH/Immtc5PnuNSBWA+2vamrZt0YM6L5rKG92pz6K3g8OuT1URPA3Z73TxPzJ2CAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:26:40.878806Z"},"content_sha256":"bec2477c3e445859773c3a7a98a710fb5973b65b867893a464cf2b11a93a46a8","schema_version":"1.0","event_id":"sha256:bec2477c3e445859773c3a7a98a710fb5973b65b867893a464cf2b11a93a46a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2RTV4HUGK2UCRMFZMQRS3MMRGI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Explainable Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiahao Yu, Xinyu Xing, Zelei Cheng","submitted_at":"2025-02-08T05:30:31Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making tasks across diverse domains, yet its reliance on black-box neural architectures hinders interpretability, trust, and deployment in high-stakes applications. Explainable Deep Reinforcement Learning (XRL) addresses these challenges by enhancing transparency through feature-level, state-level, dataset-level, and model-level explanation techniques. This survey provides a comprehensive review of XRL methods, evaluates their qualitative and quantitative assessment frameworks, and explores their role in p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06869","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/2502.06869/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":"2026-07-05T10:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9M6e1ipzNi4KV5/lNRvxDaMEMWkPyQjWdq/llTHDWKYs99Wwmja07VHFhqkg1144mb0PMqTugJ8JJZz4YQ2yDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:26:40.879737Z"},"content_sha256":"edd4381519735112b8041d405df55ce77cd8e1ce17a148a06f50e1136927bdc5","schema_version":"1.0","event_id":"sha256:edd4381519735112b8041d405df55ce77cd8e1ce17a148a06f50e1136927bdc5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2RTV4HUGK2UCRMFZMQRS3MMRGI/bundle.json","state_url":"https://pith.science/pith/2RTV4HUGK2UCRMFZMQRS3MMRGI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2RTV4HUGK2UCRMFZMQRS3MMRGI/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":"2026-08-07T18:26:40Z","links":{"resolver":"https://pith.science/pith/2RTV4HUGK2UCRMFZMQRS3MMRGI","bundle":"https://pith.science/pith/2RTV4HUGK2UCRMFZMQRS3MMRGI/bundle.json","state":"https://pith.science/pith/2RTV4HUGK2UCRMFZMQRS3MMRGI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2RTV4HUGK2UCRMFZMQRS3MMRGI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2RTV4HUGK2UCRMFZMQRS3MMRGI","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":"3aa64232dd9349b75b386e9da465c9047fe66ba607aabc53dc090cdb59da4d2f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T05:30:31Z","title_canon_sha256":"7c61ba44527af146cd95f2775717286f13f252f0484b074d3dfeb7139742cd67"},"schema_version":"1.0","source":{"id":"2502.06869","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06869","created_at":"2026-07-05T10:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06869v1","created_at":"2026-07-05T10:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06869","created_at":"2026-07-05T10:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"2RTV4HUGK2UC","created_at":"2026-07-05T10:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"2RTV4HUGK2UCRMFZ","created_at":"2026-07-05T10:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"2RTV4HUG","created_at":"2026-07-05T10:12:29Z"}],"graph_snapshots":[{"event_id":"sha256:edd4381519735112b8041d405df55ce77cd8e1ce17a148a06f50e1136927bdc5","target":"graph","created_at":"2026-07-05T10:12:29Z","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/2502.06869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making tasks across diverse domains, yet its reliance on black-box neural architectures hinders interpretability, trust, and deployment in high-stakes applications. Explainable Deep Reinforcement Learning (XRL) addresses these challenges by enhancing transparency through feature-level, state-level, dataset-level, and model-level explanation techniques. This survey provides a comprehensive review of XRL methods, evaluates their qualitative and quantitative assessment frameworks, and explores their role in p","authors_text":"Jiahao Yu, Xinyu Xing, Zelei Cheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T05:30:31Z","title":"A Survey on Explainable Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06869","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:bec2477c3e445859773c3a7a98a710fb5973b65b867893a464cf2b11a93a46a8","target":"record","created_at":"2026-07-05T10:12:29Z","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":"3aa64232dd9349b75b386e9da465c9047fe66ba607aabc53dc090cdb59da4d2f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T05:30:31Z","title_canon_sha256":"7c61ba44527af146cd95f2775717286f13f252f0484b074d3dfeb7139742cd67"},"schema_version":"1.0","source":{"id":"2502.06869","kind":"arxiv","version":1}},"canonical_sha256":"d4675e1e8656a828b0b964232db1913233c9cad9dcb9b4bef5b6da4045e4b578","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4675e1e8656a828b0b964232db1913233c9cad9dcb9b4bef5b6da4045e4b578","first_computed_at":"2026-07-05T10:12:29.177403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:29.177403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t63w9XLXtJ9BIAjcNvFZpXdGFyMh7/RWdas/dU7IKqaSZryCFnZvsfrzSR4tfOJKN293NxiIFjkHv7xkZg6eCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:29.177889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06869","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bec2477c3e445859773c3a7a98a710fb5973b65b867893a464cf2b11a93a46a8","sha256:edd4381519735112b8041d405df55ce77cd8e1ce17a148a06f50e1136927bdc5"],"state_sha256":"5cd4136083995371064cb03e4e899d306be738de543ce5e6d2ffdbf5cfdf0b9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r9AL2PrwimOiS2h2jHKGRTjn1pI3Zr9nEpqE/0tqHjs6IWEHER5pc7U3FHWAOAPVBEupIByfreAsf5By4ItfAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:26:40.886945Z","bundle_sha256":"158b456bb3098ffc25fc9fd51dedc4fddaf0eee9780e19e3b7e5b0565ab8596f"}}