{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7Q2O5LJK3B3IAEXDHX2YZAJRZB","short_pith_number":"pith:7Q2O5LJK","canonical_record":{"source":{"id":"1806.07692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-20T12:29:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a0c3bcc568fa88dc17d7bfe10371be023f5bba420edd6d0cce8f2f1e492f21e1","abstract_canon_sha256":"9ef4c7a5d1a75a38d5bc494554ce4c7f850093ca3c9479f689e436fa54cf47d4"},"schema_version":"1.0"},"canonical_sha256":"fc34eead2ad8768012e33df58c8131c86bb2893c8084efb80e5bb7c1fbea293b","source":{"kind":"arxiv","id":"1806.07692","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.07692","created_at":"2026-05-18T00:12:46Z"},{"alias_kind":"arxiv_version","alias_value":"1806.07692v1","created_at":"2026-05-18T00:12:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07692","created_at":"2026-05-18T00:12:46Z"},{"alias_kind":"pith_short_12","alias_value":"7Q2O5LJK3B3I","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7Q2O5LJK3B3IAEXD","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7Q2O5LJK","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7Q2O5LJK3B3IAEXDHX2YZAJRZB","target":"record","payload":{"canonical_record":{"source":{"id":"1806.07692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-20T12:29:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a0c3bcc568fa88dc17d7bfe10371be023f5bba420edd6d0cce8f2f1e492f21e1","abstract_canon_sha256":"9ef4c7a5d1a75a38d5bc494554ce4c7f850093ca3c9479f689e436fa54cf47d4"},"schema_version":"1.0"},"canonical_sha256":"fc34eead2ad8768012e33df58c8131c86bb2893c8084efb80e5bb7c1fbea293b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:46.989151Z","signature_b64":"rcwpgrPmMdFGl/Fnbl6025FwXVHRxsgq2Rux4kT0IrmUhlOjKkJ4D+fM+sXe4Hi5h/goFV14ITtPjUH4qKsQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc34eead2ad8768012e33df58c8131c86bb2893c8084efb80e5bb7c1fbea293b","last_reissued_at":"2026-05-18T00:12:46.988702Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:46.988702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.07692","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":"2026-05-18T00:12:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j9ub4j7gE+D/ITgJn1lD63RSWragyP9xGKxNg2Hc64a6VyAghEod5BvcYIo4aSR5JQvYKpeRBdZOGO5vJHWJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:07:06.181363Z"},"content_sha256":"cdd45e751d3f65db13775d4d1d83fa535151e4db3b583c4783d52ff245060666","schema_version":"1.0","event_id":"sha256:cdd45e751d3f65db13775d4d1d83fa535151e4db3b583c4783d52ff245060666"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7Q2O5LJK3B3IAEXDHX2YZAJRZB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning using Augmented Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jack Shannon, Marek Grzes","submitted_at":"2018-06-20T12:29:14Z","abstract_excerpt":"Neural networks allow Q-learning reinforcement learning agents such as deep Q-networks (DQN) to approximate complex mappings from state spaces to value functions. However, this also brings drawbacks when compared to other function approximators such as tile coding or their generalisations, radial basis functions (RBF) because they introduce instability due to the side effect of globalised updates present in neural networks. This instability does not even vanish in neural networks that do not have any hidden layers. In this paper, we show that simple modifications to the structure of the neural"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.07692","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":""},"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":"2026-05-18T00:12:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQOyxIQDsjAJ7SJZxuQRJROIxUrFicrJ1linOu2mo2knwB7QjZHmG2+xGJzfTKbzzCrjPQtzkJMyg0xnMK3+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:07:06.181717Z"},"content_sha256":"6ec647b673df1a8f537558a3f0ac245935da0098f0b4ef795ec21a3013aa8358","schema_version":"1.0","event_id":"sha256:6ec647b673df1a8f537558a3f0ac245935da0098f0b4ef795ec21a3013aa8358"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7Q2O5LJK3B3IAEXDHX2YZAJRZB/bundle.json","state_url":"https://pith.science/pith/7Q2O5LJK3B3IAEXDHX2YZAJRZB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7Q2O5LJK3B3IAEXDHX2YZAJRZB/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":"2026-05-28T20:07:06Z","links":{"resolver":"https://pith.science/pith/7Q2O5LJK3B3IAEXDHX2YZAJRZB","bundle":"https://pith.science/pith/7Q2O5LJK3B3IAEXDHX2YZAJRZB/bundle.json","state":"https://pith.science/pith/7Q2O5LJK3B3IAEXDHX2YZAJRZB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7Q2O5LJK3B3IAEXDHX2YZAJRZB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7Q2O5LJK3B3IAEXDHX2YZAJRZB","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":"9ef4c7a5d1a75a38d5bc494554ce4c7f850093ca3c9479f689e436fa54cf47d4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-20T12:29:14Z","title_canon_sha256":"a0c3bcc568fa88dc17d7bfe10371be023f5bba420edd6d0cce8f2f1e492f21e1"},"schema_version":"1.0","source":{"id":"1806.07692","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.07692","created_at":"2026-05-18T00:12:46Z"},{"alias_kind":"arxiv_version","alias_value":"1806.07692v1","created_at":"2026-05-18T00:12:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07692","created_at":"2026-05-18T00:12:46Z"},{"alias_kind":"pith_short_12","alias_value":"7Q2O5LJK3B3I","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7Q2O5LJK3B3IAEXD","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7Q2O5LJK","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:6ec647b673df1a8f537558a3f0ac245935da0098f0b4ef795ec21a3013aa8358","target":"graph","created_at":"2026-05-18T00:12:46Z","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":"Neural networks allow Q-learning reinforcement learning agents such as deep Q-networks (DQN) to approximate complex mappings from state spaces to value functions. However, this also brings drawbacks when compared to other function approximators such as tile coding or their generalisations, radial basis functions (RBF) because they introduce instability due to the side effect of globalised updates present in neural networks. This instability does not even vanish in neural networks that do not have any hidden layers. In this paper, we show that simple modifications to the structure of the neural","authors_text":"Jack Shannon, Marek Grzes","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-20T12:29:14Z","title":"Reinforcement Learning using Augmented Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.07692","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:cdd45e751d3f65db13775d4d1d83fa535151e4db3b583c4783d52ff245060666","target":"record","created_at":"2026-05-18T00:12:46Z","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":"9ef4c7a5d1a75a38d5bc494554ce4c7f850093ca3c9479f689e436fa54cf47d4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-20T12:29:14Z","title_canon_sha256":"a0c3bcc568fa88dc17d7bfe10371be023f5bba420edd6d0cce8f2f1e492f21e1"},"schema_version":"1.0","source":{"id":"1806.07692","kind":"arxiv","version":1}},"canonical_sha256":"fc34eead2ad8768012e33df58c8131c86bb2893c8084efb80e5bb7c1fbea293b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc34eead2ad8768012e33df58c8131c86bb2893c8084efb80e5bb7c1fbea293b","first_computed_at":"2026-05-18T00:12:46.988702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:46.988702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rcwpgrPmMdFGl/Fnbl6025FwXVHRxsgq2Rux4kT0IrmUhlOjKkJ4D+fM+sXe4Hi5h/goFV14ITtPjUH4qKsQCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:46.989151Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.07692","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdd45e751d3f65db13775d4d1d83fa535151e4db3b583c4783d52ff245060666","sha256:6ec647b673df1a8f537558a3f0ac245935da0098f0b4ef795ec21a3013aa8358"],"state_sha256":"352070704f67f43656cecd6076e344b304c0241e8281db644e4548817940200d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/nn5Fz3f4WMudD+4zxUduhhOiB9JdN1z3ihue4TjrBnip6YWq4kmgNAU2vuznA0KntTHvsyTNY1abRyLqJ35DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T20:07:06.183687Z","bundle_sha256":"398a363bff25b581fad90c0c42bedb0adbc44416d462ee0625be5af476284577"}}