{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DKN4OM7LLXZGQEL6UZCIKZFBJK","short_pith_number":"pith:DKN4OM7L","canonical_record":{"source":{"id":"1804.02464","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-06T21:43:13Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"eaceef616300362cd89247fc1cc452455d794d61b2fe868b3241ad23ea89cde7","abstract_canon_sha256":"f741d460b1e1416674f3f1d62fec4e13bd12fad7feabe8b35ab985903cd359cb"},"schema_version":"1.0"},"canonical_sha256":"1a9bc733eb5df268117ea6448564a14a88ed2e91e285dc0a6d211642442d3075","source":{"kind":"arxiv","id":"1804.02464","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02464","created_at":"2026-05-18T00:09:25Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02464v3","created_at":"2026-05-18T00:09:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02464","created_at":"2026-05-18T00:09:25Z"},{"alias_kind":"pith_short_12","alias_value":"DKN4OM7LLXZG","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DKN4OM7LLXZGQEL6","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DKN4OM7L","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DKN4OM7LLXZGQEL6UZCIKZFBJK","target":"record","payload":{"canonical_record":{"source":{"id":"1804.02464","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-06T21:43:13Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"eaceef616300362cd89247fc1cc452455d794d61b2fe868b3241ad23ea89cde7","abstract_canon_sha256":"f741d460b1e1416674f3f1d62fec4e13bd12fad7feabe8b35ab985903cd359cb"},"schema_version":"1.0"},"canonical_sha256":"1a9bc733eb5df268117ea6448564a14a88ed2e91e285dc0a6d211642442d3075","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:25.319801Z","signature_b64":"lJzcv5f1zitTGRTyP6D9rnkYMvHjfwTiAI9NDEGdj95Bn58SvNBsdLclsQ5he3vV5V/ysGH10D//edGK//8yAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a9bc733eb5df268117ea6448564a14a88ed2e91e285dc0a6d211642442d3075","last_reissued_at":"2026-05-18T00:09:25.319303Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:25.319303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.02464","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:09:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mVMccvvlsGNMv2MK65rewpxGLeHObCxLN4CeRJfmFMjJeUhLZGjzneUQ4wSR29q7yZCA5GwQ0RBNNKW6bOuhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:12:23.345137Z"},"content_sha256":"0db0295f0151dd83a7a5b8153012a78d8efedf1247fdeb7c9a17fe0ebcc097a1","schema_version":"1.0","event_id":"sha256:0db0295f0151dd83a7a5b8153012a78d8efedf1247fdeb7c9a17fe0ebcc097a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DKN4OM7LLXZGQEL6UZCIKZFBJK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Differentiable plasticity: training plastic neural networks with backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Jeff Clune, Kenneth O. Stanley, Thomas Miconi","submitted_at":"2018-04-06T21:43:13Z","abstract_excerpt":"How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by evolution to produce efficient lifelong learning. We show that plasticity, just like connection weights, can be optimized by gradient descent in large (millions of parameters) recurrent networks with Hebbian plastic connections. First, recurrent plastic networks with more than two million parameters can be trained to memorize and reconstruct sets of novel, hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02464","kind":"arxiv","version":3},"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":"2026-05-18T00:09:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EEqoVoGevKhtg4rfqH5QhNyIdqjVr8UgwuiibL17Y/fZk+iII4DNbx61R9oUFhVlZglfWsoX1fWP5P8S07WPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:12:23.345802Z"},"content_sha256":"f778d91c8b776528e3abfadd0e7f02dfe7318b6c95aaf6645afd00b067369153","schema_version":"1.0","event_id":"sha256:f778d91c8b776528e3abfadd0e7f02dfe7318b6c95aaf6645afd00b067369153"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKN4OM7LLXZGQEL6UZCIKZFBJK/bundle.json","state_url":"https://pith.science/pith/DKN4OM7LLXZGQEL6UZCIKZFBJK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKN4OM7LLXZGQEL6UZCIKZFBJK/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":"2026-05-29T19:12:23Z","links":{"resolver":"https://pith.science/pith/DKN4OM7LLXZGQEL6UZCIKZFBJK","bundle":"https://pith.science/pith/DKN4OM7LLXZGQEL6UZCIKZFBJK/bundle.json","state":"https://pith.science/pith/DKN4OM7LLXZGQEL6UZCIKZFBJK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKN4OM7LLXZGQEL6UZCIKZFBJK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DKN4OM7LLXZGQEL6UZCIKZFBJK","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":"f741d460b1e1416674f3f1d62fec4e13bd12fad7feabe8b35ab985903cd359cb","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-06T21:43:13Z","title_canon_sha256":"eaceef616300362cd89247fc1cc452455d794d61b2fe868b3241ad23ea89cde7"},"schema_version":"1.0","source":{"id":"1804.02464","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02464","created_at":"2026-05-18T00:09:25Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02464v3","created_at":"2026-05-18T00:09:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02464","created_at":"2026-05-18T00:09:25Z"},{"alias_kind":"pith_short_12","alias_value":"DKN4OM7LLXZG","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DKN4OM7LLXZGQEL6","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DKN4OM7L","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:f778d91c8b776528e3abfadd0e7f02dfe7318b6c95aaf6645afd00b067369153","target":"graph","created_at":"2026-05-18T00:09:25Z","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":"How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by evolution to produce efficient lifelong learning. We show that plasticity, just like connection weights, can be optimized by gradient descent in large (millions of parameters) recurrent networks with Hebbian plastic connections. First, recurrent plastic networks with more than two million parameters can be trained to memorize and reconstruct sets of novel, hig","authors_text":"Jeff Clune, Kenneth O. Stanley, Thomas Miconi","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-06T21:43:13Z","title":"Differentiable plasticity: training plastic neural networks with backpropagation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02464","kind":"arxiv","version":3},"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":"sha256:0db0295f0151dd83a7a5b8153012a78d8efedf1247fdeb7c9a17fe0ebcc097a1","target":"record","created_at":"2026-05-18T00:09:25Z","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":"f741d460b1e1416674f3f1d62fec4e13bd12fad7feabe8b35ab985903cd359cb","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-06T21:43:13Z","title_canon_sha256":"eaceef616300362cd89247fc1cc452455d794d61b2fe868b3241ad23ea89cde7"},"schema_version":"1.0","source":{"id":"1804.02464","kind":"arxiv","version":3}},"canonical_sha256":"1a9bc733eb5df268117ea6448564a14a88ed2e91e285dc0a6d211642442d3075","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a9bc733eb5df268117ea6448564a14a88ed2e91e285dc0a6d211642442d3075","first_computed_at":"2026-05-18T00:09:25.319303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:25.319303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lJzcv5f1zitTGRTyP6D9rnkYMvHjfwTiAI9NDEGdj95Bn58SvNBsdLclsQ5he3vV5V/ysGH10D//edGK//8yAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:25.319801Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.02464","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0db0295f0151dd83a7a5b8153012a78d8efedf1247fdeb7c9a17fe0ebcc097a1","sha256:f778d91c8b776528e3abfadd0e7f02dfe7318b6c95aaf6645afd00b067369153"],"state_sha256":"5d8640a7c30800fbca377756821dc3df97776b03af1ec9612692f4b9c68f1231"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5s7tlh+VyxyXuubWi/OEKhxaJj2J4CuyuWwNUBFackJ42kG/r74ZewiIF6oBay5bj46CT+ytWVeBEdfdQ/BRBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T19:12:23.349444Z","bundle_sha256":"7bf0b6a2c824ea47cc3ed7d80e76ed69b9b3e355c218584e5466ad440b8cbcc7"}}