{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EM7OM7HSWVO5LKRJTAAFF6SJQE","short_pith_number":"pith:EM7OM7HS","canonical_record":{"source":{"id":"1806.09819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-06-26T07:17:51Z","cross_cats_sorted":[],"title_canon_sha256":"543ba8b8e113259791dbc7101c0655145888af19e708988520fd708576c9442a","abstract_canon_sha256":"b497da763312160e70b268877d4c4fadfe0129a3a3cdd2537661cb3e369d86c6"},"schema_version":"1.0"},"canonical_sha256":"233ee67cf2b55dd5aa29980052fa49813e06f684a4d0da45df4eb6e30f1eb05e","source":{"kind":"arxiv","id":"1806.09819","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.09819","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"1806.09819v1","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09819","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"EM7OM7HSWVO5","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EM7OM7HSWVO5LKRJ","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EM7OM7HS","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EM7OM7HSWVO5LKRJTAAFF6SJQE","target":"record","payload":{"canonical_record":{"source":{"id":"1806.09819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-06-26T07:17:51Z","cross_cats_sorted":[],"title_canon_sha256":"543ba8b8e113259791dbc7101c0655145888af19e708988520fd708576c9442a","abstract_canon_sha256":"b497da763312160e70b268877d4c4fadfe0129a3a3cdd2537661cb3e369d86c6"},"schema_version":"1.0"},"canonical_sha256":"233ee67cf2b55dd5aa29980052fa49813e06f684a4d0da45df4eb6e30f1eb05e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:23.253175Z","signature_b64":"ksB9BcVrr2xG5AE9HyEzDOqr4ZbK8BJtQW1+GeRl4fzuy2JSgoDIIaSV9mi41Sb+TuWDkwPF8POSiW88pjYrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"233ee67cf2b55dd5aa29980052fa49813e06f684a4d0da45df4eb6e30f1eb05e","last_reissued_at":"2026-05-18T00:12:23.252531Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:23.252531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.09819","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":"2026-05-18T00:12:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GcywyWNN3YMDBsFnw3ZZzj+op8gBNZOa0DPDOSyjOTOhRTPVHnoZgdo7uUbabfSBdyw6Sy6mDUEL1u3SNV+jBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:37:22.867109Z"},"content_sha256":"e1726300c161d08c780baaa9b23c3e5d47bedd4f7a0810448bc0f19494255ee1","schema_version":"1.0","event_id":"sha256:e1726300c161d08c780baaa9b23c3e5d47bedd4f7a0810448bc0f19494255ee1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EM7OM7HSWVO5LKRJTAAFF6SJQE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Limited Evaluation Evolutionary Optimization of Large Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Jonas Prellberg, Oliver Kramer","submitted_at":"2018-06-26T07:17:51Z","abstract_excerpt":"Stochastic gradient descent is the most prevalent algorithm to train neural networks. However, other approaches such as evolutionary algorithms are also applicable to this task. Evolutionary algorithms bring unique trade-offs that are worth exploring, but computational demands have so far restricted exploration to small networks with few parameters. We implement an evolutionary algorithm that executes entirely on the GPU, which allows to efficiently batch-evaluate a whole population of networks. Within this framework, we explore the limited evaluation evolutionary algorithm for neural network "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09819","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":"2026-05-18T00:12:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5cqUT+HMxZNwzY6Rr9akqk6ul4fS3nUJ9KovwQVwrS3UZPyHDDyouejONGcKPdgdH4qXNnmk8vLVOzOlOElzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:37:22.867845Z"},"content_sha256":"734be3196afd7c06f2157847083ba46770b1068d6771fba8856c6e062a56b0fb","schema_version":"1.0","event_id":"sha256:734be3196afd7c06f2157847083ba46770b1068d6771fba8856c6e062a56b0fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EM7OM7HSWVO5LKRJTAAFF6SJQE/bundle.json","state_url":"https://pith.science/pith/EM7OM7HSWVO5LKRJTAAFF6SJQE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EM7OM7HSWVO5LKRJTAAFF6SJQE/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":"2026-05-28T22:37:22Z","links":{"resolver":"https://pith.science/pith/EM7OM7HSWVO5LKRJTAAFF6SJQE","bundle":"https://pith.science/pith/EM7OM7HSWVO5LKRJTAAFF6SJQE/bundle.json","state":"https://pith.science/pith/EM7OM7HSWVO5LKRJTAAFF6SJQE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EM7OM7HSWVO5LKRJTAAFF6SJQE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EM7OM7HSWVO5LKRJTAAFF6SJQE","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":"b497da763312160e70b268877d4c4fadfe0129a3a3cdd2537661cb3e369d86c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-06-26T07:17:51Z","title_canon_sha256":"543ba8b8e113259791dbc7101c0655145888af19e708988520fd708576c9442a"},"schema_version":"1.0","source":{"id":"1806.09819","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.09819","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"1806.09819v1","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09819","created_at":"2026-05-18T00:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"EM7OM7HSWVO5","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EM7OM7HSWVO5LKRJ","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EM7OM7HS","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:734be3196afd7c06f2157847083ba46770b1068d6771fba8856c6e062a56b0fb","target":"graph","created_at":"2026-05-18T00:12:23Z","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":"Stochastic gradient descent is the most prevalent algorithm to train neural networks. However, other approaches such as evolutionary algorithms are also applicable to this task. Evolutionary algorithms bring unique trade-offs that are worth exploring, but computational demands have so far restricted exploration to small networks with few parameters. We implement an evolutionary algorithm that executes entirely on the GPU, which allows to efficiently batch-evaluate a whole population of networks. Within this framework, we explore the limited evaluation evolutionary algorithm for neural network ","authors_text":"Jonas Prellberg, Oliver Kramer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-06-26T07:17:51Z","title":"Limited Evaluation Evolutionary Optimization of Large Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09819","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:e1726300c161d08c780baaa9b23c3e5d47bedd4f7a0810448bc0f19494255ee1","target":"record","created_at":"2026-05-18T00:12:23Z","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":"b497da763312160e70b268877d4c4fadfe0129a3a3cdd2537661cb3e369d86c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-06-26T07:17:51Z","title_canon_sha256":"543ba8b8e113259791dbc7101c0655145888af19e708988520fd708576c9442a"},"schema_version":"1.0","source":{"id":"1806.09819","kind":"arxiv","version":1}},"canonical_sha256":"233ee67cf2b55dd5aa29980052fa49813e06f684a4d0da45df4eb6e30f1eb05e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"233ee67cf2b55dd5aa29980052fa49813e06f684a4d0da45df4eb6e30f1eb05e","first_computed_at":"2026-05-18T00:12:23.252531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:23.252531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ksB9BcVrr2xG5AE9HyEzDOqr4ZbK8BJtQW1+GeRl4fzuy2JSgoDIIaSV9mi41Sb+TuWDkwPF8POSiW88pjYrAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:23.253175Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.09819","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1726300c161d08c780baaa9b23c3e5d47bedd4f7a0810448bc0f19494255ee1","sha256:734be3196afd7c06f2157847083ba46770b1068d6771fba8856c6e062a56b0fb"],"state_sha256":"d14374286f01ad3a7ce73adb512a20e4b4c2a4989fcfe7d81053e5e18c9784c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YO3Ea1a+ia9Uc41UYo0F7qBIk2caIE6nJb+4PtBtIRuVM5YHGyzn5zRJiPPxYRDHvfA+xac4YVFaWtm374GjBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T22:37:22.871251Z","bundle_sha256":"60c0d4556e973e0b1f45388f75a671e80ea38fe9922c7ec8995f56a89a0fd1a7"}}