{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XITGITFLGGZOBZ3JH4ZXHIOMSO","short_pith_number":"pith:XITGITFL","canonical_record":{"source":{"id":"1801.01952","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-06T01:27:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"91eef1a0cc6f268a4253ad0fad6328b1c29eec93be024034eda284461ce609ad","abstract_canon_sha256":"7a7ae639496ae5d46e2ecfa9c402356a1c41d51acdb950a2a05c194bbd22fd75"},"schema_version":"1.0"},"canonical_sha256":"ba26644cab31b2e0e7693f3373a1cc93ad93e921a97bea1b24de6ecd90beb63b","source":{"kind":"arxiv","id":"1801.01952","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.01952","created_at":"2026-05-18T00:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"1801.01952v4","created_at":"2026-05-18T00:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.01952","created_at":"2026-05-18T00:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"XITGITFLGGZO","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XITGITFLGGZOBZ3J","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XITGITFL","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XITGITFLGGZOBZ3JH4ZXHIOMSO","target":"record","payload":{"canonical_record":{"source":{"id":"1801.01952","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-06T01:27:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"91eef1a0cc6f268a4253ad0fad6328b1c29eec93be024034eda284461ce609ad","abstract_canon_sha256":"7a7ae639496ae5d46e2ecfa9c402356a1c41d51acdb950a2a05c194bbd22fd75"},"schema_version":"1.0"},"canonical_sha256":"ba26644cab31b2e0e7693f3373a1cc93ad93e921a97bea1b24de6ecd90beb63b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:02.712397Z","signature_b64":"jQaBhYyljepboRoJdwD98/9Y/mohEeu3jtQV6bYv4h4clYR9vhRoOupIRC2syvdpuwfwqdOklF8WKvuZJMrNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba26644cab31b2e0e7693f3373a1cc93ad93e921a97bea1b24de6ecd90beb63b","last_reissued_at":"2026-05-18T00:19:02.711672Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:02.711672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.01952","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GjKSl8Ngm6+n7Qaw+ItshVEauR/4JQPOMaManVR8ZkQz80z1NNXNZmPCvwSZ99NvSHmsBAINis5/JGz6A9VMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:53:14.711574Z"},"content_sha256":"0ff10d1ded7c95311981332c9a08f3b628fac59e8f864a14b4d8e0efddf9cdcd","schema_version":"1.0","event_id":"sha256:0ff10d1ded7c95311981332c9a08f3b628fac59e8f864a14b4d8e0efddf9cdcd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XITGITFLGGZOBZ3JH4ZXHIOMSO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generating Neural Networks with Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Lior Deutsch","submitted_at":"2018-01-06T01:27:16Z","abstract_excerpt":"Hypernetworks are neural networks that generate weights for another neural network. We formulate the hypernetwork training objective as a compromise between accuracy and diversity, where the diversity takes into account trivial symmetry transformations of the target network. We explain how this simple formulation generalizes variational inference. We use multi-layered perceptrons to form the mapping from the low dimensional input random vector to the high dimensional weight space, and demonstrate how to reduce the number of parameters in this mapping by parameter sharing. We perform experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.01952","kind":"arxiv","version":4},"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":"2026-05-18T00:19:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sv8inXMFGLt58PmgKbiU9VN7WZGXcMiJtG7e8XCI9WFWekMqzsgfetpwRbb87/NIXnpKKzdMrjOKXpFWwtgHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:53:14.712348Z"},"content_sha256":"39b2c29ef01d19f9c407d3742ebec1d4d9fd56b0c8245db6c174da46f4282b89","schema_version":"1.0","event_id":"sha256:39b2c29ef01d19f9c407d3742ebec1d4d9fd56b0c8245db6c174da46f4282b89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XITGITFLGGZOBZ3JH4ZXHIOMSO/bundle.json","state_url":"https://pith.science/pith/XITGITFLGGZOBZ3JH4ZXHIOMSO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XITGITFLGGZOBZ3JH4ZXHIOMSO/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":"2026-08-08T11:53:14Z","links":{"resolver":"https://pith.science/pith/XITGITFLGGZOBZ3JH4ZXHIOMSO","bundle":"https://pith.science/pith/XITGITFLGGZOBZ3JH4ZXHIOMSO/bundle.json","state":"https://pith.science/pith/XITGITFLGGZOBZ3JH4ZXHIOMSO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XITGITFLGGZOBZ3JH4ZXHIOMSO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XITGITFLGGZOBZ3JH4ZXHIOMSO","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":"7a7ae639496ae5d46e2ecfa9c402356a1c41d51acdb950a2a05c194bbd22fd75","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-06T01:27:16Z","title_canon_sha256":"91eef1a0cc6f268a4253ad0fad6328b1c29eec93be024034eda284461ce609ad"},"schema_version":"1.0","source":{"id":"1801.01952","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.01952","created_at":"2026-05-18T00:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"1801.01952v4","created_at":"2026-05-18T00:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.01952","created_at":"2026-05-18T00:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"XITGITFLGGZO","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XITGITFLGGZOBZ3J","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XITGITFL","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:39b2c29ef01d19f9c407d3742ebec1d4d9fd56b0c8245db6c174da46f4282b89","target":"graph","created_at":"2026-05-18T00:19:02Z","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":"Hypernetworks are neural networks that generate weights for another neural network. We formulate the hypernetwork training objective as a compromise between accuracy and diversity, where the diversity takes into account trivial symmetry transformations of the target network. We explain how this simple formulation generalizes variational inference. We use multi-layered perceptrons to form the mapping from the low dimensional input random vector to the high dimensional weight space, and demonstrate how to reduce the number of parameters in this mapping by parameter sharing. We perform experiment","authors_text":"Lior Deutsch","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-06T01:27:16Z","title":"Generating Neural Networks with Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.01952","kind":"arxiv","version":4},"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":"sha256:0ff10d1ded7c95311981332c9a08f3b628fac59e8f864a14b4d8e0efddf9cdcd","target":"record","created_at":"2026-05-18T00:19:02Z","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":"7a7ae639496ae5d46e2ecfa9c402356a1c41d51acdb950a2a05c194bbd22fd75","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-06T01:27:16Z","title_canon_sha256":"91eef1a0cc6f268a4253ad0fad6328b1c29eec93be024034eda284461ce609ad"},"schema_version":"1.0","source":{"id":"1801.01952","kind":"arxiv","version":4}},"canonical_sha256":"ba26644cab31b2e0e7693f3373a1cc93ad93e921a97bea1b24de6ecd90beb63b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba26644cab31b2e0e7693f3373a1cc93ad93e921a97bea1b24de6ecd90beb63b","first_computed_at":"2026-05-18T00:19:02.711672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:02.711672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jQaBhYyljepboRoJdwD98/9Y/mohEeu3jtQV6bYv4h4clYR9vhRoOupIRC2syvdpuwfwqdOklF8WKvuZJMrNCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:02.712397Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.01952","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ff10d1ded7c95311981332c9a08f3b628fac59e8f864a14b4d8e0efddf9cdcd","sha256:39b2c29ef01d19f9c407d3742ebec1d4d9fd56b0c8245db6c174da46f4282b89"],"state_sha256":"ec5f4bc703c756f5bb79e1eed37297b3d0aafc39b73a65ffe33faa9ff691ec05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LgWZwwN/unU5H8PCEXbkf0Fp1759ddwEQjyFjWi4Unobl8yOqCvS3q8p89qWj06TxdpHmsoIbNMQL4xWQQTcDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:53:14.716668Z","bundle_sha256":"dc530ff230d5896cd9f0f6c39291fa088378bbb2a270a08e3b3afc03f4eb80af"}}