{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GOOJYMJJDNAL6UWBF5BLIR3NF2","short_pith_number":"pith:GOOJYMJJ","canonical_record":{"source":{"id":"1901.02878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T18:59:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2e4749288a0a484f7ce9b01e457a5b4035424c378dbea80e631b086cc6298f2","abstract_canon_sha256":"e0ef6ea0afa878218c31cc7cba4f062009209fd497559cfc6750376f966b6597"},"schema_version":"1.0"},"canonical_sha256":"339c9c31291b40bf52c12f42b4476d2ebc8725d038a65ca5c76738ba48bf78e1","source":{"kind":"arxiv","id":"1901.02878","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02878","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02878v1","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02878","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"pith_short_12","alias_value":"GOOJYMJJDNAL","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GOOJYMJJDNAL6UWB","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GOOJYMJJ","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GOOJYMJJDNAL6UWBF5BLIR3NF2","target":"record","payload":{"canonical_record":{"source":{"id":"1901.02878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T18:59:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2e4749288a0a484f7ce9b01e457a5b4035424c378dbea80e631b086cc6298f2","abstract_canon_sha256":"e0ef6ea0afa878218c31cc7cba4f062009209fd497559cfc6750376f966b6597"},"schema_version":"1.0"},"canonical_sha256":"339c9c31291b40bf52c12f42b4476d2ebc8725d038a65ca5c76738ba48bf78e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:39.293868Z","signature_b64":"uwGsiExKHf4s6qjgctS4GAnI3RvPUEhCd5kVNez8qCX5XBkg8Z9gAjiTUv9/KtgHG4OmtmTp6LnzWbCqkUcXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"339c9c31291b40bf52c12f42b4476d2ebc8725d038a65ca5c76738ba48bf78e1","last_reissued_at":"2026-05-17T23:56:39.293206Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:39.293206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.02878","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":"2026-05-17T23:56:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"34uuvLwx3YE1MRqiv2aCQJrYhIf2s19eFN3do0q3LkzB99chGwB0k75/olk9J2bkf4NGWMJSc4nUcoyf9sQXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T09:19:13.430019Z"},"content_sha256":"195193d17ad50db4d994145b8a615814b369ff5a947a35b6cd6c5875bf54c959","schema_version":"1.0","event_id":"sha256:195193d17ad50db4d994145b8a615814b369ff5a947a35b6cd6c5875bf54c959"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GOOJYMJJDNAL6UWBF5BLIR3NF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Constructive Approach for One-Shot Training of Neural Networks Using Hypercube-Based Topological Coverings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Enoch Yeung, W. Brent Daniel","submitted_at":"2019-01-09T18:59:10Z","abstract_excerpt":"In this paper we presented a novel constructive approach for training deep neural networks using geometric approaches. We show that a topological covering can be used to define a class of distributed linear matrix inequalities, which in turn directly specify the shape and depth of a neural network architecture. The key insight is a fundamental relationship between linear matrix inequalities and their ability to bound the shape of data, and the rectified linear unit (ReLU) activation function employed in modern neural networks. We show that unit cover geometry and cover porosity are two design "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02878","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":"2026-05-17T23:56:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OHvZx4C0vDCT1mFiY5T2xK5z/hPq69HW9nfJS9IU2wb1slOtRSP50X8ZM7XqbJf5SHN5iqUUN9VscvY7mipgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T09:19:13.430379Z"},"content_sha256":"e0eab5dea6d1a6cbdb85ec10da6d48f709e8e8dbb7e9bf99133d85ff26dded8d","schema_version":"1.0","event_id":"sha256:e0eab5dea6d1a6cbdb85ec10da6d48f709e8e8dbb7e9bf99133d85ff26dded8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GOOJYMJJDNAL6UWBF5BLIR3NF2/bundle.json","state_url":"https://pith.science/pith/GOOJYMJJDNAL6UWBF5BLIR3NF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GOOJYMJJDNAL6UWBF5BLIR3NF2/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":"2026-06-29T09:19:13Z","links":{"resolver":"https://pith.science/pith/GOOJYMJJDNAL6UWBF5BLIR3NF2","bundle":"https://pith.science/pith/GOOJYMJJDNAL6UWBF5BLIR3NF2/bundle.json","state":"https://pith.science/pith/GOOJYMJJDNAL6UWBF5BLIR3NF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GOOJYMJJDNAL6UWBF5BLIR3NF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GOOJYMJJDNAL6UWBF5BLIR3NF2","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":"e0ef6ea0afa878218c31cc7cba4f062009209fd497559cfc6750376f966b6597","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T18:59:10Z","title_canon_sha256":"e2e4749288a0a484f7ce9b01e457a5b4035424c378dbea80e631b086cc6298f2"},"schema_version":"1.0","source":{"id":"1901.02878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02878","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02878v1","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02878","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"pith_short_12","alias_value":"GOOJYMJJDNAL","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GOOJYMJJDNAL6UWB","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GOOJYMJJ","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:e0eab5dea6d1a6cbdb85ec10da6d48f709e8e8dbb7e9bf99133d85ff26dded8d","target":"graph","created_at":"2026-05-17T23:56:39Z","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":"In this paper we presented a novel constructive approach for training deep neural networks using geometric approaches. We show that a topological covering can be used to define a class of distributed linear matrix inequalities, which in turn directly specify the shape and depth of a neural network architecture. The key insight is a fundamental relationship between linear matrix inequalities and their ability to bound the shape of data, and the rectified linear unit (ReLU) activation function employed in modern neural networks. We show that unit cover geometry and cover porosity are two design ","authors_text":"Enoch Yeung, W. Brent Daniel","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T18:59:10Z","title":"A Constructive Approach for One-Shot Training of Neural Networks Using Hypercube-Based Topological Coverings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02878","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":"sha256:195193d17ad50db4d994145b8a615814b369ff5a947a35b6cd6c5875bf54c959","target":"record","created_at":"2026-05-17T23:56:39Z","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":"e0ef6ea0afa878218c31cc7cba4f062009209fd497559cfc6750376f966b6597","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T18:59:10Z","title_canon_sha256":"e2e4749288a0a484f7ce9b01e457a5b4035424c378dbea80e631b086cc6298f2"},"schema_version":"1.0","source":{"id":"1901.02878","kind":"arxiv","version":1}},"canonical_sha256":"339c9c31291b40bf52c12f42b4476d2ebc8725d038a65ca5c76738ba48bf78e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"339c9c31291b40bf52c12f42b4476d2ebc8725d038a65ca5c76738ba48bf78e1","first_computed_at":"2026-05-17T23:56:39.293206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:39.293206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uwGsiExKHf4s6qjgctS4GAnI3RvPUEhCd5kVNez8qCX5XBkg8Z9gAjiTUv9/KtgHG4OmtmTp6LnzWbCqkUcXBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:39.293868Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.02878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:195193d17ad50db4d994145b8a615814b369ff5a947a35b6cd6c5875bf54c959","sha256:e0eab5dea6d1a6cbdb85ec10da6d48f709e8e8dbb7e9bf99133d85ff26dded8d"],"state_sha256":"95e174325868fe98900852ffb791bb9aaef9e5f7e9273a18812b033b91625aa2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9VpOAXRqGd9jM22ned2fn6eBymEEEGiWbwjaFgLyz1EenAYR2GHoMGIimeooV+SS75KxEncOx5aTvd9xb6LFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T09:19:13.432237Z","bundle_sha256":"064ff574c394488cbd3a495661b5300842540259da3bbe70b8a4919000b9ff57"}}