{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:XTMPV52MWM2PJDBQXKLMDG7SUW","short_pith_number":"pith:XTMPV52M","canonical_record":{"source":{"id":"1609.09106","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-27T05:57:00Z","cross_cats_sorted":[],"title_canon_sha256":"8bf1cfa479388c867ba136c02430ed6c91ee9657893763355e6cdb314b78f562","abstract_canon_sha256":"85d2334c445f73488e44c555f4a9dff5581eefd31f01895a8957c256ad2c12be"},"schema_version":"1.0"},"canonical_sha256":"bcd8faf74cb334f48c30ba96c19bf2a5a450e16762219b99ee36f70678c1053f","source":{"kind":"arxiv","id":"1609.09106","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.09106","created_at":"2026-05-18T03:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"1609.09106v4","created_at":"2026-05-18T03:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.09106","created_at":"2026-05-18T03:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"XTMPV52MWM2P","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XTMPV52MWM2PJDBQ","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XTMPV52M","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:XTMPV52MWM2PJDBQXKLMDG7SUW","target":"record","payload":{"canonical_record":{"source":{"id":"1609.09106","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-27T05:57:00Z","cross_cats_sorted":[],"title_canon_sha256":"8bf1cfa479388c867ba136c02430ed6c91ee9657893763355e6cdb314b78f562","abstract_canon_sha256":"85d2334c445f73488e44c555f4a9dff5581eefd31f01895a8957c256ad2c12be"},"schema_version":"1.0"},"canonical_sha256":"bcd8faf74cb334f48c30ba96c19bf2a5a450e16762219b99ee36f70678c1053f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:23:37.616984Z","signature_b64":"97JBk0O+6zvYNFkUI0bB0O/E50tTS4JzLaE9+sfjQK9rMFzlpBajHHhSr9tmjHuANJL5yWs6jb4mrrDymVYODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcd8faf74cb334f48c30ba96c19bf2a5a450e16762219b99ee36f70678c1053f","last_reissued_at":"2026-05-18T03:23:37.616277Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:23:37.616277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.09106","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":"2026-05-18T03:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AKzRi8rGOv8Ttk8rBL/YVJ/5bWlkjqLrUaMEuqQVVer29U4ofGc1yguAnPz0HCTjng4oeQXJnDsHw4a2e2GwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T08:55:05.048395Z"},"content_sha256":"09f8e8430949660cba8c4a89909fea0fb742795306d2277fb389ce8d0ea2365f","schema_version":"1.0","event_id":"sha256:09f8e8430949660cba8c4a89909fea0fb742795306d2277fb389ce8d0ea2365f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:XTMPV52MWM2PJDBQXKLMDG7SUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HyperNetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A hypernetwork generates the weights for another network to enable non-shared weights in LSTMs.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Dai, David Ha, Quoc V. Le","submitted_at":"2016-09-27T05:57:00Z","abstract_excerpt":"This work explores hypernetworks: an approach of using a one network, also known as a hypernetwork, to generate the weights for another network. Hypernetworks provide an abstraction that is similar to what is found in nature: the relationship between a genotype - the hypernetwork - and a phenotype - the main network. Though they are also reminiscent of HyperNEAT in evolution, our hypernetworks are trained end-to-end with backpropagation and thus are usually faster. The focus of this work is to make hypernetworks useful for deep convolutional networks and long recurrent networks, where hypernet"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our main result is that hypernetworks can generate non-shared weights for LSTM and achieve near state-of-the-art results on a variety of sequence modelling tasks including character-level language modelling, handwriting generation and neural machine translation, challenging the weight-sharing paradigm for recurrent networks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the hypernetwork can be effectively trained end-to-end with backpropagation to produce high-quality weights for the main network without introducing instability, overfitting, or requiring excessive additional computation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Hypernetworks generate weights for a main network, allowing LSTMs to use non-shared weights and achieve near state-of-the-art results on sequence modeling tasks while using fewer parameters overall.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A hypernetwork generates the weights for another network to enable non-shared weights in LSTMs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a6c81e69fc6a6113cc3a1c8af25ce7bffeea20dddaaab4e40d518b093ab378b7"},"source":{"id":"1609.09106","kind":"arxiv","version":4},"verdict":{"id":"ffe8543a-bf39-408a-baa3-3f8263dc554f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T00:14:34.273271Z","strongest_claim":"Our main result is that hypernetworks can generate non-shared weights for LSTM and achieve near state-of-the-art results on a variety of sequence modelling tasks including character-level language modelling, handwriting generation and neural machine translation, challenging the weight-sharing paradigm for recurrent networks.","one_line_summary":"Hypernetworks generate weights for a main network, allowing LSTMs to use non-shared weights and achieve near state-of-the-art results on sequence modeling tasks while using fewer parameters overall.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the hypernetwork can be effectively trained end-to-end with backpropagation to produce high-quality weights for the main network without introducing instability, overfitting, or requiring excessive additional computation.","pith_extraction_headline":"A hypernetwork generates the weights for another network to enable non-shared weights in LSTMs."},"references":{"count":2,"sample":[{"doi":"","year":2016,"title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","work_id":"91f3c09e-dae6-48ca-80c0-463dd1b1f6e1","ref_index":1,"cited_arxiv_id":"1603.04467","is_internal_anchor":false},{"doi":"","year":2015,"title":"Large Embedding","work_id":"f71b6e48-8bbe-460c-ba5d-4ad1d91006fd","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":2,"snapshot_sha256":"03304a60339b17fe679342dc4ba51791cc91c58006c5498e1c8726e97ce099f4","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"da15d5c9170af51bc94b5e34cd417ef8aebdb0b15b9d7e7f0373e8ce9a100ec2"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"ffe8543a-bf39-408a-baa3-3f8263dc554f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"slF044X7UYdTkf09KSh7pBQ7TccqmvSHVGTKs/DMmp318ZtHKsdq7+Zt/3G35Q6bcA8oh88fP8JRgQ2KmbrqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T08:55:05.049181Z"},"content_sha256":"694d7b5eb3f196d6b28ff77556d2740508dcbdb6ca303b0da2c549e71d290011","schema_version":"1.0","event_id":"sha256:694d7b5eb3f196d6b28ff77556d2740508dcbdb6ca303b0da2c549e71d290011"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTMPV52MWM2PJDBQXKLMDG7SUW/bundle.json","state_url":"https://pith.science/pith/XTMPV52MWM2PJDBQXKLMDG7SUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTMPV52MWM2PJDBQXKLMDG7SUW/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":"2026-05-31T08:55:05Z","links":{"resolver":"https://pith.science/pith/XTMPV52MWM2PJDBQXKLMDG7SUW","bundle":"https://pith.science/pith/XTMPV52MWM2PJDBQXKLMDG7SUW/bundle.json","state":"https://pith.science/pith/XTMPV52MWM2PJDBQXKLMDG7SUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTMPV52MWM2PJDBQXKLMDG7SUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:XTMPV52MWM2PJDBQXKLMDG7SUW","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":"85d2334c445f73488e44c555f4a9dff5581eefd31f01895a8957c256ad2c12be","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-27T05:57:00Z","title_canon_sha256":"8bf1cfa479388c867ba136c02430ed6c91ee9657893763355e6cdb314b78f562"},"schema_version":"1.0","source":{"id":"1609.09106","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.09106","created_at":"2026-05-18T03:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"1609.09106v4","created_at":"2026-05-18T03:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.09106","created_at":"2026-05-18T03:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"XTMPV52MWM2P","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XTMPV52MWM2PJDBQ","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XTMPV52M","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:694d7b5eb3f196d6b28ff77556d2740508dcbdb6ca303b0da2c549e71d290011","target":"graph","created_at":"2026-05-18T03:23:37Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our main result is that hypernetworks can generate non-shared weights for LSTM and achieve near state-of-the-art results on a variety of sequence modelling tasks including character-level language modelling, handwriting generation and neural machine translation, challenging the weight-sharing paradigm for recurrent networks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the hypernetwork can be effectively trained end-to-end with backpropagation to produce high-quality weights for the main network without introducing instability, overfitting, or requiring excessive additional computation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Hypernetworks generate weights for a main network, allowing LSTMs to use non-shared weights and achieve near state-of-the-art results on sequence modeling tasks while using fewer parameters overall."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A hypernetwork generates the weights for another network to enable non-shared weights in LSTMs."}],"snapshot_sha256":"a6c81e69fc6a6113cc3a1c8af25ce7bffeea20dddaaab4e40d518b093ab378b7"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"da15d5c9170af51bc94b5e34cd417ef8aebdb0b15b9d7e7f0373e8ce9a100ec2"},"paper":{"abstract_excerpt":"This work explores hypernetworks: an approach of using a one network, also known as a hypernetwork, to generate the weights for another network. Hypernetworks provide an abstraction that is similar to what is found in nature: the relationship between a genotype - the hypernetwork - and a phenotype - the main network. Though they are also reminiscent of HyperNEAT in evolution, our hypernetworks are trained end-to-end with backpropagation and thus are usually faster. The focus of this work is to make hypernetworks useful for deep convolutional networks and long recurrent networks, where hypernet","authors_text":"Andrew Dai, David Ha, Quoc V. Le","cross_cats":[],"headline":"A hypernetwork generates the weights for another network to enable non-shared weights in LSTMs.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-27T05:57:00Z","title":"HyperNetworks"},"references":{"count":2,"internal_anchors":0,"resolved_work":2,"sample":[{"cited_arxiv_id":"1603.04467","doi":"","is_internal_anchor":false,"ref_index":1,"title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","work_id":"91f3c09e-dae6-48ca-80c0-463dd1b1f6e1","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Large Embedding","work_id":"f71b6e48-8bbe-460c-ba5d-4ad1d91006fd","year":2015}],"snapshot_sha256":"03304a60339b17fe679342dc4ba51791cc91c58006c5498e1c8726e97ce099f4"},"source":{"id":"1609.09106","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-14T00:14:34.273271Z","id":"ffe8543a-bf39-408a-baa3-3f8263dc554f","model_set":{"reader":"grok-4.3"},"one_line_summary":"Hypernetworks generate weights for a main network, allowing LSTMs to use non-shared weights and achieve near state-of-the-art results on sequence modeling tasks while using fewer parameters overall.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A hypernetwork generates the weights for another network to enable non-shared weights in LSTMs.","strongest_claim":"Our main result is that hypernetworks can generate non-shared weights for LSTM and achieve near state-of-the-art results on a variety of sequence modelling tasks including character-level language modelling, handwriting generation and neural machine translation, challenging the weight-sharing paradigm for recurrent networks.","weakest_assumption":"The assumption that the hypernetwork can be effectively trained end-to-end with backpropagation to produce high-quality weights for the main network without introducing instability, overfitting, or requiring excessive additional computation."}},"verdict_id":"ffe8543a-bf39-408a-baa3-3f8263dc554f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:09f8e8430949660cba8c4a89909fea0fb742795306d2277fb389ce8d0ea2365f","target":"record","created_at":"2026-05-18T03:23:37Z","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":"85d2334c445f73488e44c555f4a9dff5581eefd31f01895a8957c256ad2c12be","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-27T05:57:00Z","title_canon_sha256":"8bf1cfa479388c867ba136c02430ed6c91ee9657893763355e6cdb314b78f562"},"schema_version":"1.0","source":{"id":"1609.09106","kind":"arxiv","version":4}},"canonical_sha256":"bcd8faf74cb334f48c30ba96c19bf2a5a450e16762219b99ee36f70678c1053f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcd8faf74cb334f48c30ba96c19bf2a5a450e16762219b99ee36f70678c1053f","first_computed_at":"2026-05-18T03:23:37.616277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:23:37.616277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"97JBk0O+6zvYNFkUI0bB0O/E50tTS4JzLaE9+sfjQK9rMFzlpBajHHhSr9tmjHuANJL5yWs6jb4mrrDymVYODA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:23:37.616984Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.09106","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09f8e8430949660cba8c4a89909fea0fb742795306d2277fb389ce8d0ea2365f","sha256:694d7b5eb3f196d6b28ff77556d2740508dcbdb6ca303b0da2c549e71d290011"],"state_sha256":"153364483e2d5dd377d926003bf56fa2096f0925ba0f5dfabaf3c1cf56900b6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kL1EQkvPfmlyEQsnosWnJTsYhAtNDf3/b6KsOX2gR1Fh3/YjmCed8UmxTKvB6jRlH18Rh5k8xCCV2E73e9g/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T08:55:05.053060Z","bundle_sha256":"677cc4406dacb916f68dd83e8583eacacdf572a9845f022fb39c03e2b24e1de0"}}