{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WGVAS5P6TRAB2TG2QKZYRS6HDN","short_pith_number":"pith:WGVAS5P6","canonical_record":{"source":{"id":"1906.05032","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T09:43:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ddd291d0a02351ac2b5f74fa8a9b9e302b9ed4490a2c38137910628542b50c20","abstract_canon_sha256":"38205a1bc9042fc0ec2ab5d399e754c43b6bb319e8e3298a660900eac85c4d9c"},"schema_version":"1.0"},"canonical_sha256":"b1aa0975fe9c401d4cda82b388cbc71b508f996358af09369cceac543eb4940d","source":{"kind":"arxiv","id":"1906.05032","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05032","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05032v1","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05032","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"WGVAS5P6TRAB","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WGVAS5P6TRAB2TG2","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WGVAS5P6","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WGVAS5P6TRAB2TG2QKZYRS6HDN","target":"record","payload":{"canonical_record":{"source":{"id":"1906.05032","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T09:43:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ddd291d0a02351ac2b5f74fa8a9b9e302b9ed4490a2c38137910628542b50c20","abstract_canon_sha256":"38205a1bc9042fc0ec2ab5d399e754c43b6bb319e8e3298a660900eac85c4d9c"},"schema_version":"1.0"},"canonical_sha256":"b1aa0975fe9c401d4cda82b388cbc71b508f996358af09369cceac543eb4940d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:29.692896Z","signature_b64":"/xDAQgK9mPmpUpkjzxw49P61gJiuklcI+kM5oRGu4XWesWSirPo+2gFK5E9uOltiUDGaickYWm28mUPDGaM1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1aa0975fe9c401d4cda82b388cbc71b508f996358af09369cceac543eb4940d","last_reissued_at":"2026-05-17T23:43:29.692240Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:29.692240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.05032","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":"2026-05-17T23:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9w/Mlj2Mu6xIdw1mcA/0GDB2l9RvDE2jk9zCRrIa2pbWazSgkGe8DwkvIhxWdZjHb1GIHdvNrsDcet06y6c7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:00:14.442900Z"},"content_sha256":"dccdf9eb872584b89421e15b0852be3623647567b88f4d206e5ac6d1cfb687f7","schema_version":"1.0","event_id":"sha256:dccdf9eb872584b89421e15b0852be3623647567b88f4d206e5ac6d1cfb687f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WGVAS5P6TRAB2TG2QKZYRS6HDN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoupling Gating from Linearity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eran Malach, Jonathan Fiat, Shai Shalev-Shwartz","submitted_at":"2019-06-12T09:43:05Z","abstract_excerpt":"ReLU neural-networks have been in the focus of many recent theoretical works, trying to explain their empirical success. Nonetheless, there is still a gap between current theoretical results and empirical observations, even in the case of shallow (one hidden-layer) networks. For example, in the task of memorizing a random sample of size $m$ and dimension $d$, the best theoretical result requires the size of the network to be $\\tilde{\\Omega}(\\frac{m^2}{d})$, while empirically a network of size slightly larger than $\\frac{m}{d}$ is sufficient. To bridge this gap, we turn to study a simplified mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05032","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":"2026-05-17T23:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tvH2ZnjG6lECJPJHIEBKMY4ojcI17tKwo5KRiD2g7Z2jDoa0CcJjmb6cXXipHXjc6Sg1zhqnpGMYBtf8xvcJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:00:14.443308Z"},"content_sha256":"186e590c567e90f7e8f0d45f10be48f6175923cec2c0bb4e00b025e57ec410d8","schema_version":"1.0","event_id":"sha256:186e590c567e90f7e8f0d45f10be48f6175923cec2c0bb4e00b025e57ec410d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WGVAS5P6TRAB2TG2QKZYRS6HDN/bundle.json","state_url":"https://pith.science/pith/WGVAS5P6TRAB2TG2QKZYRS6HDN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WGVAS5P6TRAB2TG2QKZYRS6HDN/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":"2026-05-26T04:00:14Z","links":{"resolver":"https://pith.science/pith/WGVAS5P6TRAB2TG2QKZYRS6HDN","bundle":"https://pith.science/pith/WGVAS5P6TRAB2TG2QKZYRS6HDN/bundle.json","state":"https://pith.science/pith/WGVAS5P6TRAB2TG2QKZYRS6HDN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WGVAS5P6TRAB2TG2QKZYRS6HDN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WGVAS5P6TRAB2TG2QKZYRS6HDN","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":"38205a1bc9042fc0ec2ab5d399e754c43b6bb319e8e3298a660900eac85c4d9c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T09:43:05Z","title_canon_sha256":"ddd291d0a02351ac2b5f74fa8a9b9e302b9ed4490a2c38137910628542b50c20"},"schema_version":"1.0","source":{"id":"1906.05032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05032","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05032v1","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05032","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"WGVAS5P6TRAB","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WGVAS5P6TRAB2TG2","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WGVAS5P6","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:186e590c567e90f7e8f0d45f10be48f6175923cec2c0bb4e00b025e57ec410d8","target":"graph","created_at":"2026-05-17T23:43:29Z","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":"ReLU neural-networks have been in the focus of many recent theoretical works, trying to explain their empirical success. Nonetheless, there is still a gap between current theoretical results and empirical observations, even in the case of shallow (one hidden-layer) networks. For example, in the task of memorizing a random sample of size $m$ and dimension $d$, the best theoretical result requires the size of the network to be $\\tilde{\\Omega}(\\frac{m^2}{d})$, while empirically a network of size slightly larger than $\\frac{m}{d}$ is sufficient. To bridge this gap, we turn to study a simplified mo","authors_text":"Eran Malach, Jonathan Fiat, Shai Shalev-Shwartz","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T09:43:05Z","title":"Decoupling Gating from Linearity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05032","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:dccdf9eb872584b89421e15b0852be3623647567b88f4d206e5ac6d1cfb687f7","target":"record","created_at":"2026-05-17T23:43:29Z","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":"38205a1bc9042fc0ec2ab5d399e754c43b6bb319e8e3298a660900eac85c4d9c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T09:43:05Z","title_canon_sha256":"ddd291d0a02351ac2b5f74fa8a9b9e302b9ed4490a2c38137910628542b50c20"},"schema_version":"1.0","source":{"id":"1906.05032","kind":"arxiv","version":1}},"canonical_sha256":"b1aa0975fe9c401d4cda82b388cbc71b508f996358af09369cceac543eb4940d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1aa0975fe9c401d4cda82b388cbc71b508f996358af09369cceac543eb4940d","first_computed_at":"2026-05-17T23:43:29.692240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:29.692240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/xDAQgK9mPmpUpkjzxw49P61gJiuklcI+kM5oRGu4XWesWSirPo+2gFK5E9uOltiUDGaickYWm28mUPDGaM1DA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:29.692896Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dccdf9eb872584b89421e15b0852be3623647567b88f4d206e5ac6d1cfb687f7","sha256:186e590c567e90f7e8f0d45f10be48f6175923cec2c0bb4e00b025e57ec410d8"],"state_sha256":"100cfaecbca8f6a9224d11276c5e14500bbe86bde8153d91f652265f55b58349"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U19RepuzwAut4BQM9z2C2+9EMQ/6o2ukWyTSl46wLnwmdlq0QB7dGJOJwAPhk2TEMTjmGQI5FeyQw8k394MuDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T04:00:14.446806Z","bundle_sha256":"6e8e7cabdcb075a169f52d9f93733389817c7554d9bd4a584a7a6c36806fbee0"}}