{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:364JZSBF4MZXCONKUSKHX3JQI7","short_pith_number":"pith:364JZSBF","canonical_record":{"source":{"id":"1809.05630","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-15T01:34:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"26954da707bafd3f4825f621f189f0e35cf87c32d84e887df884796f5e4dfaca","abstract_canon_sha256":"363a650baabf92e90a79783f9de1b2b9593cd73777e77bfbf0aeaee4e53cecab"},"schema_version":"1.0"},"canonical_sha256":"dfb89cc825e3337139aaa4947bed3047cbac339b172821b0380e89e8b2c57c41","source":{"kind":"arxiv","id":"1809.05630","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.05630","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"arxiv_version","alias_value":"1809.05630v2","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05630","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"pith_short_12","alias_value":"364JZSBF4MZX","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"364JZSBF4MZXCONK","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"364JZSBF","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:364JZSBF4MZXCONKUSKHX3JQI7","target":"record","payload":{"canonical_record":{"source":{"id":"1809.05630","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-15T01:34:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"26954da707bafd3f4825f621f189f0e35cf87c32d84e887df884796f5e4dfaca","abstract_canon_sha256":"363a650baabf92e90a79783f9de1b2b9593cd73777e77bfbf0aeaee4e53cecab"},"schema_version":"1.0"},"canonical_sha256":"dfb89cc825e3337139aaa4947bed3047cbac339b172821b0380e89e8b2c57c41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:39.272611Z","signature_b64":"B4VhZGpQqbmE8MIBzCnjH33kTwej/Tf/bYBMiATmJwb5m89FXdPWV1ozaNsM+WzsjYtMlyYEN6yI1dv0iYjrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfb89cc825e3337139aaa4947bed3047cbac339b172821b0380e89e8b2c57c41","last_reissued_at":"2026-05-18T00:00:39.272117Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:39.272117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.05630","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":"2026-05-18T00:00:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o4qX8HJkJ3FUUNIibdsPB+W0XrS0lFvXu0JK4V0ylPAinlLgUrsv4Ml+lkVmmrb4lwFnCMBp1SFXSB1dOGJRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:13:11.676151Z"},"content_sha256":"ee0a6b1d32b69fdb13435a8bf324355717570002bbe0ae62c152557d00330799","schema_version":"1.0","event_id":"sha256:ee0a6b1d32b69fdb13435a8bf324355717570002bbe0ae62c152557d00330799"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:364JZSBF4MZXCONKUSKHX3JQI7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Better Interpretability in Deep Q-Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Katia Sycara, Raghuram Mandyam Annasamy","submitted_at":"2018-09-15T01:34:27Z","abstract_excerpt":"Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these networks seem to learn, are far behind. In this paper we propose an interpretable neural network architecture for Q-learning which provides a global explanation of the model's behavior using key-value memories, attention and reconstructible embeddings. With a directed exploration strategy, our model can reach training rewards comparable to the state-of-the-ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05630","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":""},"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":"2026-05-18T00:00:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"srpVo/0Ya/9E26WrY35dX5XaVwXqrJLzSZsC5tz9Anu/It/dUZ4zfc6Qr2HaHTdjwUBaTeQ/1CHrZ/vdyakzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:13:11.676832Z"},"content_sha256":"dc2f6a1927bed45f4439f8b5815406bdcd132b81c95af97289f55ca8187c709c","schema_version":"1.0","event_id":"sha256:dc2f6a1927bed45f4439f8b5815406bdcd132b81c95af97289f55ca8187c709c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/364JZSBF4MZXCONKUSKHX3JQI7/bundle.json","state_url":"https://pith.science/pith/364JZSBF4MZXCONKUSKHX3JQI7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/364JZSBF4MZXCONKUSKHX3JQI7/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":"2026-05-27T20:13:11Z","links":{"resolver":"https://pith.science/pith/364JZSBF4MZXCONKUSKHX3JQI7","bundle":"https://pith.science/pith/364JZSBF4MZXCONKUSKHX3JQI7/bundle.json","state":"https://pith.science/pith/364JZSBF4MZXCONKUSKHX3JQI7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/364JZSBF4MZXCONKUSKHX3JQI7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:364JZSBF4MZXCONKUSKHX3JQI7","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":"363a650baabf92e90a79783f9de1b2b9593cd73777e77bfbf0aeaee4e53cecab","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-15T01:34:27Z","title_canon_sha256":"26954da707bafd3f4825f621f189f0e35cf87c32d84e887df884796f5e4dfaca"},"schema_version":"1.0","source":{"id":"1809.05630","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.05630","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"arxiv_version","alias_value":"1809.05630v2","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05630","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"pith_short_12","alias_value":"364JZSBF4MZX","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"364JZSBF4MZXCONK","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"364JZSBF","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:dc2f6a1927bed45f4439f8b5815406bdcd132b81c95af97289f55ca8187c709c","target":"graph","created_at":"2026-05-18T00:00:39Z","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"},"paper":{"abstract_excerpt":"Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these networks seem to learn, are far behind. In this paper we propose an interpretable neural network architecture for Q-learning which provides a global explanation of the model's behavior using key-value memories, attention and reconstructible embeddings. With a directed exploration strategy, our model can reach training rewards comparable to the state-of-the-ar","authors_text":"Katia Sycara, Raghuram Mandyam Annasamy","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-15T01:34:27Z","title":"Towards Better Interpretability in Deep Q-Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05630","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:ee0a6b1d32b69fdb13435a8bf324355717570002bbe0ae62c152557d00330799","target":"record","created_at":"2026-05-18T00:00:39Z","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":"363a650baabf92e90a79783f9de1b2b9593cd73777e77bfbf0aeaee4e53cecab","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-15T01:34:27Z","title_canon_sha256":"26954da707bafd3f4825f621f189f0e35cf87c32d84e887df884796f5e4dfaca"},"schema_version":"1.0","source":{"id":"1809.05630","kind":"arxiv","version":2}},"canonical_sha256":"dfb89cc825e3337139aaa4947bed3047cbac339b172821b0380e89e8b2c57c41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfb89cc825e3337139aaa4947bed3047cbac339b172821b0380e89e8b2c57c41","first_computed_at":"2026-05-18T00:00:39.272117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:39.272117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B4VhZGpQqbmE8MIBzCnjH33kTwej/Tf/bYBMiATmJwb5m89FXdPWV1ozaNsM+WzsjYtMlyYEN6yI1dv0iYjrDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:39.272611Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.05630","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee0a6b1d32b69fdb13435a8bf324355717570002bbe0ae62c152557d00330799","sha256:dc2f6a1927bed45f4439f8b5815406bdcd132b81c95af97289f55ca8187c709c"],"state_sha256":"f653cc7a26fe2ad01ba509bf5604c21fc312f6c0b6d5f6a8cd7cbdd63bed3846"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y84tS2XTTTf7yA/jOnthvOpJWxqO5mW9FKMNbZvXDWM1EpGQB8rBZjkPsgavefz+MkrK2DtWJWDuMQSYHGCYBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T20:13:11.680446Z","bundle_sha256":"d8e602eda118d1bcede6760362e4d86e6634dcf8a532a12ed8909cdcb46e9e39"}}