{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6CHV76HXMJU2RSFF3X6WSD6WNY","short_pith_number":"pith:6CHV76HX","canonical_record":{"source":{"id":"2103.08228","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-15T09:26:00Z","cross_cats_sorted":[],"title_canon_sha256":"ec19530a81e0c3ef01d1c2e3d52536b961843b95a265d5fb7acafa29a13e0cdc","abstract_canon_sha256":"40ab5abfdd9d8294b9085e448d1243d13359bd75624e6e6a4d9b98400f89d18c"},"schema_version":"1.0"},"canonical_sha256":"f08f5ff8f76269a8c8a5ddfd690fd66e0b3be035c0cb3be1287e1ac7f3beb902","source":{"kind":"arxiv","id":"2103.08228","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08228","created_at":"2026-07-05T02:23:29Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08228v2","created_at":"2026-07-05T02:23:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08228","created_at":"2026-07-05T02:23:29Z"},{"alias_kind":"pith_short_12","alias_value":"6CHV76HXMJU2","created_at":"2026-07-05T02:23:29Z"},{"alias_kind":"pith_short_16","alias_value":"6CHV76HXMJU2RSFF","created_at":"2026-07-05T02:23:29Z"},{"alias_kind":"pith_short_8","alias_value":"6CHV76HX","created_at":"2026-07-05T02:23:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6CHV76HXMJU2RSFF3X6WSD6WNY","target":"record","payload":{"canonical_record":{"source":{"id":"2103.08228","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-15T09:26:00Z","cross_cats_sorted":[],"title_canon_sha256":"ec19530a81e0c3ef01d1c2e3d52536b961843b95a265d5fb7acafa29a13e0cdc","abstract_canon_sha256":"40ab5abfdd9d8294b9085e448d1243d13359bd75624e6e6a4d9b98400f89d18c"},"schema_version":"1.0"},"canonical_sha256":"f08f5ff8f76269a8c8a5ddfd690fd66e0b3be035c0cb3be1287e1ac7f3beb902","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:23:29.399727Z","signature_b64":"XA1xPSdmBnT3Z2xXrFkmDqFUi7K/7dPCzWXtagHeF8Gv3yxqjb7lG3/AdsR/FNjT9FwXy/mGqTJeUeCFaL+ICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f08f5ff8f76269a8c8a5ddfd690fd66e0b3be035c0cb3be1287e1ac7f3beb902","last_reissued_at":"2026-07-05T02:23:29.399324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:23:29.399324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.08228","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:23:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XHoUh9UWk92GAij4zp+lq9Q6sE/BuGP4ec4iFBYWczDZ8UG+78Vzx6GQejc8LTS5p4fql82WYt/0zaXelnvCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:32:24.089651Z"},"content_sha256":"b900d7134bdef01a8a7f5ad6dd4ca018450f0cdf14e57e88b65acdde101ad7f7","schema_version":"1.0","event_id":"sha256:b900d7134bdef01a8a7f5ad6dd4ca018450f0cdf14e57e88b65acdde101ad7f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6CHV76HXMJU2RSFF3X6WSD6WNY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Symbolic Rules for Interpretable Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dong Li, Hankz Hankui Zhuo, Jianye Hao, Paul Weng, Wulong Liu, Yuzheng Zhuang, Zhihao Ma","submitted_at":"2021-03-15T09:26:00Z","abstract_excerpt":"Recent progress in deep reinforcement learning (DRL) can be largely attributed to the use of neural networks. However, this black-box approach fails to explain the learned policy in a human understandable way. To address this challenge and improve the transparency, we propose a Neural Symbolic Reinforcement Learning framework by introducing symbolic logic into DRL. This framework features a fertilization of reasoning and learning modules, enabling end-to-end learning with prior symbolic knowledge. Moreover, interpretability is achieved by extracting the logical rules learned by the reasoning m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08228","kind":"arxiv","version":2},"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/2103.08228/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":"2026-07-05T02:23:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"miTQEDD5gtw9LpKn1X7bdVfs2Xq6n7TcTU5hz/mc0CYpHjWSEGJW4Ih9yOwhhrFbrI8Nea+GUdukKwSVMRMxBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:32:24.090050Z"},"content_sha256":"d1cc80ee8a18d30bd425a392854042fdb6a04ffd0f651925bd655fa4eb4b6ea6","schema_version":"1.0","event_id":"sha256:d1cc80ee8a18d30bd425a392854042fdb6a04ffd0f651925bd655fa4eb4b6ea6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6CHV76HXMJU2RSFF3X6WSD6WNY/bundle.json","state_url":"https://pith.science/pith/6CHV76HXMJU2RSFF3X6WSD6WNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6CHV76HXMJU2RSFF3X6WSD6WNY/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":"2026-08-06T05:32:24Z","links":{"resolver":"https://pith.science/pith/6CHV76HXMJU2RSFF3X6WSD6WNY","bundle":"https://pith.science/pith/6CHV76HXMJU2RSFF3X6WSD6WNY/bundle.json","state":"https://pith.science/pith/6CHV76HXMJU2RSFF3X6WSD6WNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6CHV76HXMJU2RSFF3X6WSD6WNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6CHV76HXMJU2RSFF3X6WSD6WNY","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":"40ab5abfdd9d8294b9085e448d1243d13359bd75624e6e6a4d9b98400f89d18c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-15T09:26:00Z","title_canon_sha256":"ec19530a81e0c3ef01d1c2e3d52536b961843b95a265d5fb7acafa29a13e0cdc"},"schema_version":"1.0","source":{"id":"2103.08228","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08228","created_at":"2026-07-05T02:23:29Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08228v2","created_at":"2026-07-05T02:23:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08228","created_at":"2026-07-05T02:23:29Z"},{"alias_kind":"pith_short_12","alias_value":"6CHV76HXMJU2","created_at":"2026-07-05T02:23:29Z"},{"alias_kind":"pith_short_16","alias_value":"6CHV76HXMJU2RSFF","created_at":"2026-07-05T02:23:29Z"},{"alias_kind":"pith_short_8","alias_value":"6CHV76HX","created_at":"2026-07-05T02:23:29Z"}],"graph_snapshots":[{"event_id":"sha256:d1cc80ee8a18d30bd425a392854042fdb6a04ffd0f651925bd655fa4eb4b6ea6","target":"graph","created_at":"2026-07-05T02:23:29Z","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/2103.08228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in deep reinforcement learning (DRL) can be largely attributed to the use of neural networks. However, this black-box approach fails to explain the learned policy in a human understandable way. To address this challenge and improve the transparency, we propose a Neural Symbolic Reinforcement Learning framework by introducing symbolic logic into DRL. This framework features a fertilization of reasoning and learning modules, enabling end-to-end learning with prior symbolic knowledge. Moreover, interpretability is achieved by extracting the logical rules learned by the reasoning m","authors_text":"Dong Li, Hankz Hankui Zhuo, Jianye Hao, Paul Weng, Wulong Liu, Yuzheng Zhuang, Zhihao Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-15T09:26:00Z","title":"Learning Symbolic Rules for Interpretable Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08228","kind":"arxiv","version":2},"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:b900d7134bdef01a8a7f5ad6dd4ca018450f0cdf14e57e88b65acdde101ad7f7","target":"record","created_at":"2026-07-05T02:23:29Z","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":"40ab5abfdd9d8294b9085e448d1243d13359bd75624e6e6a4d9b98400f89d18c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-15T09:26:00Z","title_canon_sha256":"ec19530a81e0c3ef01d1c2e3d52536b961843b95a265d5fb7acafa29a13e0cdc"},"schema_version":"1.0","source":{"id":"2103.08228","kind":"arxiv","version":2}},"canonical_sha256":"f08f5ff8f76269a8c8a5ddfd690fd66e0b3be035c0cb3be1287e1ac7f3beb902","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f08f5ff8f76269a8c8a5ddfd690fd66e0b3be035c0cb3be1287e1ac7f3beb902","first_computed_at":"2026-07-05T02:23:29.399324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:23:29.399324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XA1xPSdmBnT3Z2xXrFkmDqFUi7K/7dPCzWXtagHeF8Gv3yxqjb7lG3/AdsR/FNjT9FwXy/mGqTJeUeCFaL+ICg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:23:29.399727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.08228","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b900d7134bdef01a8a7f5ad6dd4ca018450f0cdf14e57e88b65acdde101ad7f7","sha256:d1cc80ee8a18d30bd425a392854042fdb6a04ffd0f651925bd655fa4eb4b6ea6"],"state_sha256":"69bf51db94f8e305c13364e68c2a465c5cec283b7250b70a434bbe8ad6431d95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hrb9YiqBLOED2A5cRDeCX1z6WHzW52p1JwRsUtTmcHx8ugsbNrgblmjAXN36lxsXNBPo2GXKx94fNVl7qBThAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:32:24.094312Z","bundle_sha256":"8d08291fe86497d26627cee7acc5fbe4946af1d4b8f8b69f6b30a3bb9ccb4143"}}