{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:E67YVE3YEXMHS4LCNZNE4SB6PK","short_pith_number":"pith:E67YVE3Y","canonical_record":{"source":{"id":"1606.02580","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-08T14:37:39Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c294747290cdc1f9c89579259fa105fc1d5d64f45678426ce7731e9206799e8b","abstract_canon_sha256":"0da6a57c645228b4f931a1e833a44040d1dc3aa9bc879ac08bfc702ca57ca32c"},"schema_version":"1.0"},"canonical_sha256":"27bf8a937825d87971626e5a4e483e7aba5bc2223c05a930c391981d7f5cc2bd","source":{"kind":"arxiv","id":"1606.02580","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.02580","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"1606.02580v1","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02580","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"E67YVE3YEXMH","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"E67YVE3YEXMHS4LC","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"E67YVE3Y","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:E67YVE3YEXMHS4LCNZNE4SB6PK","target":"record","payload":{"canonical_record":{"source":{"id":"1606.02580","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-08T14:37:39Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c294747290cdc1f9c89579259fa105fc1d5d64f45678426ce7731e9206799e8b","abstract_canon_sha256":"0da6a57c645228b4f931a1e833a44040d1dc3aa9bc879ac08bfc702ca57ca32c"},"schema_version":"1.0"},"canonical_sha256":"27bf8a937825d87971626e5a4e483e7aba5bc2223c05a930c391981d7f5cc2bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:41.024150Z","signature_b64":"8/q35FjIs8Ndjypms/1APmxzm0HRoUP9UJU6JIdNqSWub66nIXCT9IiWWbjPL9cVWQ50R4ZSFvU8kmdP/PZ7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27bf8a937825d87971626e5a4e483e7aba5bc2223c05a930c391981d7f5cc2bd","last_reissued_at":"2026-05-18T01:12:41.023790Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:41.023790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.02580","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":"2026-05-18T01:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"keRsCMtGyjmLiYpWurlNCWcEqGE/Mh613BqfcwX+E4AQG3WwD6xZcHI5xdmTmyxZx7IO28B1FsDsZhtpqO43Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T03:32:10.050836Z"},"content_sha256":"538f07fc661e1b2a481d6b3903fceaf7ce1a3cff2c619998115910402733216b","schema_version":"1.0","event_id":"sha256:538f07fc661e1b2a481d6b3903fceaf7ce1a3cff2c619998115910402733216b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:E67YVE3YEXMHS4LCNZNE4SB6PK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convolution by Evolution: Differentiable Pattern Producing Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"Chrisantha Fernando, Daan Wierstra, David Pfau, Dylan Banarse, Frederic Besse, Malcolm Reynolds, Marc Lanctot, Max Jaderberg","submitted_at":"2016-06-08T14:37:39Z","abstract_excerpt":"In this work we introduce a differentiable version of the Compositional Pattern Producing Network, called the DPPN. Unlike a standard CPPN, the topology of a DPPN is evolved but the weights are learned. A Lamarckian algorithm, that combines evolution and learning, produces DPPNs to reconstruct an image. Our main result is that DPPNs can be evolved/trained to compress the weights of a denoising autoencoder from 157684 to roughly 200 parameters, while achieving a reconstruction accuracy comparable to a fully connected network with more than two orders of magnitude more parameters. The regulariza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02580","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":"2026-05-18T01:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LawFw5owoRkQ0ez9OL3axey5pub42Pnl5WMg8NCjN3S7JcftCZhotOqo1RQ0qTQcQZ+F5JOIrQ/RxxbDilQXAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T03:32:10.051197Z"},"content_sha256":"08a7de62d2846a357fc244e32b1f16babb0ba8d79f3fcb793e929bb44963dfca","schema_version":"1.0","event_id":"sha256:08a7de62d2846a357fc244e32b1f16babb0ba8d79f3fcb793e929bb44963dfca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E67YVE3YEXMHS4LCNZNE4SB6PK/bundle.json","state_url":"https://pith.science/pith/E67YVE3YEXMHS4LCNZNE4SB6PK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E67YVE3YEXMHS4LCNZNE4SB6PK/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":"2026-05-25T03:32:10Z","links":{"resolver":"https://pith.science/pith/E67YVE3YEXMHS4LCNZNE4SB6PK","bundle":"https://pith.science/pith/E67YVE3YEXMHS4LCNZNE4SB6PK/bundle.json","state":"https://pith.science/pith/E67YVE3YEXMHS4LCNZNE4SB6PK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E67YVE3YEXMHS4LCNZNE4SB6PK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:E67YVE3YEXMHS4LCNZNE4SB6PK","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":"0da6a57c645228b4f931a1e833a44040d1dc3aa9bc879ac08bfc702ca57ca32c","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-08T14:37:39Z","title_canon_sha256":"c294747290cdc1f9c89579259fa105fc1d5d64f45678426ce7731e9206799e8b"},"schema_version":"1.0","source":{"id":"1606.02580","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.02580","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"1606.02580v1","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02580","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"E67YVE3YEXMH","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"E67YVE3YEXMHS4LC","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"E67YVE3Y","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:08a7de62d2846a357fc244e32b1f16babb0ba8d79f3fcb793e929bb44963dfca","target":"graph","created_at":"2026-05-18T01:12:41Z","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":"In this work we introduce a differentiable version of the Compositional Pattern Producing Network, called the DPPN. Unlike a standard CPPN, the topology of a DPPN is evolved but the weights are learned. A Lamarckian algorithm, that combines evolution and learning, produces DPPNs to reconstruct an image. Our main result is that DPPNs can be evolved/trained to compress the weights of a denoising autoencoder from 157684 to roughly 200 parameters, while achieving a reconstruction accuracy comparable to a fully connected network with more than two orders of magnitude more parameters. The regulariza","authors_text":"Chrisantha Fernando, Daan Wierstra, David Pfau, Dylan Banarse, Frederic Besse, Malcolm Reynolds, Marc Lanctot, Max Jaderberg","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-08T14:37:39Z","title":"Convolution by Evolution: Differentiable Pattern Producing Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02580","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":"sha256:538f07fc661e1b2a481d6b3903fceaf7ce1a3cff2c619998115910402733216b","target":"record","created_at":"2026-05-18T01:12:41Z","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":"0da6a57c645228b4f931a1e833a44040d1dc3aa9bc879ac08bfc702ca57ca32c","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-08T14:37:39Z","title_canon_sha256":"c294747290cdc1f9c89579259fa105fc1d5d64f45678426ce7731e9206799e8b"},"schema_version":"1.0","source":{"id":"1606.02580","kind":"arxiv","version":1}},"canonical_sha256":"27bf8a937825d87971626e5a4e483e7aba5bc2223c05a930c391981d7f5cc2bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27bf8a937825d87971626e5a4e483e7aba5bc2223c05a930c391981d7f5cc2bd","first_computed_at":"2026-05-18T01:12:41.023790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:41.023790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8/q35FjIs8Ndjypms/1APmxzm0HRoUP9UJU6JIdNqSWub66nIXCT9IiWWbjPL9cVWQ50R4ZSFvU8kmdP/PZ7DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:41.024150Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.02580","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:538f07fc661e1b2a481d6b3903fceaf7ce1a3cff2c619998115910402733216b","sha256:08a7de62d2846a357fc244e32b1f16babb0ba8d79f3fcb793e929bb44963dfca"],"state_sha256":"92bc3bded59bd6b1de9f1f93d8710d3ba178beb3aece123d79440336d13166af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hXkbf78TTsZCaOQR7D0kHHbiy3QmHTUxGfy6ngqmXC4XRQZq37A6aHT00S4fZyQzNzHx5D2WKHV7PRYfHZLtCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T03:32:10.053641Z","bundle_sha256":"b46fe68517d7f43d91f2c91b513f5966ed624e26e205cb928dc50b74e978f743"}}