{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XNND3TIFI6QC4NXXEJJRUKVIUN","short_pith_number":"pith:XNND3TIF","canonical_record":{"source":{"id":"2304.07645","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-15T22:18:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c98e5d097f48f084cca047db42e3825a06df1eaa6c33eedfc92205207fe614fe","abstract_canon_sha256":"91609272c600059c644d353141cb49063080f0b775ce3c2a8c399e0b2b4ea31a"},"schema_version":"1.0"},"canonical_sha256":"bb5a3dcd0547a02e36f722531a2aa8a35b5ea51da6176e36c2768f920acaed66","source":{"kind":"arxiv","id":"2304.07645","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.07645","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"arxiv_version","alias_value":"2304.07645v2","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07645","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_12","alias_value":"XNND3TIFI6QC","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_16","alias_value":"XNND3TIFI6QC4NXX","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_8","alias_value":"XNND3TIF","created_at":"2026-07-05T06:26:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XNND3TIFI6QC4NXXEJJRUKVIUN","target":"record","payload":{"canonical_record":{"source":{"id":"2304.07645","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-15T22:18:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c98e5d097f48f084cca047db42e3825a06df1eaa6c33eedfc92205207fe614fe","abstract_canon_sha256":"91609272c600059c644d353141cb49063080f0b775ce3c2a8c399e0b2b4ea31a"},"schema_version":"1.0"},"canonical_sha256":"bb5a3dcd0547a02e36f722531a2aa8a35b5ea51da6176e36c2768f920acaed66","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:01.766173Z","signature_b64":"QWHXkiuqVK/28neZBZxU+3e7NVsoV+nXewO3BpRKOhtFzXawiLDlWV+BpG141OGAc5ow/tC3t7df8sw2eTnNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb5a3dcd0547a02e36f722531a2aa8a35b5ea51da6176e36c2768f920acaed66","last_reissued_at":"2026-07-05T06:26:01.765738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:01.765738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.07645","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:26:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/EOktvOx9QPLZJ0274BMjn6ozNxlxGunnWW4dBcphMGiYtDLBUjnYFntFn9c3I46/l6+N+bxBBJ8nseRPgDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:50:58.178845Z"},"content_sha256":"c124df20e123346cde32a9cc22d2590f422208838b82aff257347d7e691e34dd","schema_version":"1.0","event_id":"sha256:c124df20e123346cde32a9cc22d2590f422208838b82aff257347d7e691e34dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XNND3TIFI6QC4NXXEJJRUKVIUN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Magnitude Invariant Parametrizations Improve Hypernetwork Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adrian Dalca, John Guttag, Jose Javier Gonzalez Ortiz","submitted_at":"2023-04-15T22:18:29Z","abstract_excerpt":"Hypernetworks, neural networks that predict the parameters of another neural network, are powerful models that have been successfully used in diverse applications from image generation to multi-task learning. Unfortunately, existing hypernetworks are often challenging to train. Training typically converges far more slowly than for non-hypernetwork models, and the rate of convergence can be very sensitive to hyperparameter choices. In this work, we identify a fundamental and previously unidentified problem that contributes to the challenge of training hypernetworks: a magnitude proportionality "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07645","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.07645/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T06:26:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m+hUzHOobAS1ylzC7x6VYfokWboz9KghSqALKAHOmb1JTnICpj+0x2Qd7gikmRYth42HczqB0Ugt4CbXhAHZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:50:58.179635Z"},"content_sha256":"adab37b56fc5d8efa81989f1735ba6a33d00b532819640078a6d1068274cc77a","schema_version":"1.0","event_id":"sha256:adab37b56fc5d8efa81989f1735ba6a33d00b532819640078a6d1068274cc77a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XNND3TIFI6QC4NXXEJJRUKVIUN/bundle.json","state_url":"https://pith.science/pith/XNND3TIFI6QC4NXXEJJRUKVIUN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XNND3TIFI6QC4NXXEJJRUKVIUN/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":"2026-08-20T12:50:58Z","links":{"resolver":"https://pith.science/pith/XNND3TIFI6QC4NXXEJJRUKVIUN","bundle":"https://pith.science/pith/XNND3TIFI6QC4NXXEJJRUKVIUN/bundle.json","state":"https://pith.science/pith/XNND3TIFI6QC4NXXEJJRUKVIUN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XNND3TIFI6QC4NXXEJJRUKVIUN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XNND3TIFI6QC4NXXEJJRUKVIUN","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":"91609272c600059c644d353141cb49063080f0b775ce3c2a8c399e0b2b4ea31a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-15T22:18:29Z","title_canon_sha256":"c98e5d097f48f084cca047db42e3825a06df1eaa6c33eedfc92205207fe614fe"},"schema_version":"1.0","source":{"id":"2304.07645","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.07645","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"arxiv_version","alias_value":"2304.07645v2","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07645","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_12","alias_value":"XNND3TIFI6QC","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_16","alias_value":"XNND3TIFI6QC4NXX","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_8","alias_value":"XNND3TIF","created_at":"2026-07-05T06:26:01Z"}],"graph_snapshots":[{"event_id":"sha256:adab37b56fc5d8efa81989f1735ba6a33d00b532819640078a6d1068274cc77a","target":"graph","created_at":"2026-07-05T06:26:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.07645/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hypernetworks, neural networks that predict the parameters of another neural network, are powerful models that have been successfully used in diverse applications from image generation to multi-task learning. Unfortunately, existing hypernetworks are often challenging to train. Training typically converges far more slowly than for non-hypernetwork models, and the rate of convergence can be very sensitive to hyperparameter choices. In this work, we identify a fundamental and previously unidentified problem that contributes to the challenge of training hypernetworks: a magnitude proportionality ","authors_text":"Adrian Dalca, John Guttag, Jose Javier Gonzalez Ortiz","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-15T22:18:29Z","title":"Magnitude Invariant Parametrizations Improve Hypernetwork Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07645","kind":"arxiv","version":2},"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:c124df20e123346cde32a9cc22d2590f422208838b82aff257347d7e691e34dd","target":"record","created_at":"2026-07-05T06:26:01Z","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":"91609272c600059c644d353141cb49063080f0b775ce3c2a8c399e0b2b4ea31a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-15T22:18:29Z","title_canon_sha256":"c98e5d097f48f084cca047db42e3825a06df1eaa6c33eedfc92205207fe614fe"},"schema_version":"1.0","source":{"id":"2304.07645","kind":"arxiv","version":2}},"canonical_sha256":"bb5a3dcd0547a02e36f722531a2aa8a35b5ea51da6176e36c2768f920acaed66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb5a3dcd0547a02e36f722531a2aa8a35b5ea51da6176e36c2768f920acaed66","first_computed_at":"2026-07-05T06:26:01.765738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:01.765738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QWHXkiuqVK/28neZBZxU+3e7NVsoV+nXewO3BpRKOhtFzXawiLDlWV+BpG141OGAc5ow/tC3t7df8sw2eTnNBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:01.766173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.07645","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c124df20e123346cde32a9cc22d2590f422208838b82aff257347d7e691e34dd","sha256:adab37b56fc5d8efa81989f1735ba6a33d00b532819640078a6d1068274cc77a"],"state_sha256":"10e87b178b84c966d0ef6b8eeb7199b00d4a77aeb6926c180aa568df83f69c8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d5ws4CM53rwHahvGgodVo9RM7H8sfTUDQcxezVKr5sIClq4BIdXt9Evr0kycbhBLtsdppVSOYirMJkxYiclIBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T12:50:58.186873Z","bundle_sha256":"43525b3bb2903ab5ca2d907d429d5cc135b42647113db2a3d4f99fd144a0a1eb"}}