{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SIPWV7ZDSMFYVJHQ6GO4RI4MN4","short_pith_number":"pith:SIPWV7ZD","schema_version":"1.0","canonical_sha256":"921f6aff23930b8aa4f0f19dc8a38c6f1dd8249ae9d5635716297465086d29a0","source":{"kind":"arxiv","id":"2006.03108","version":1},"attestation_state":"computed","paper":{"title":"A Linear Algebraic Approach to Model Parallelism in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Russell J. Hewett, Thomas J. Grady II","submitted_at":"2020-06-04T19:38:05Z","abstract_excerpt":"Training deep neural networks (DNNs) in large-cluster computing environments is increasingly necessary, as networks grow in size and complexity. Local memory and processing limitations require robust data and model parallelism for crossing compute node boundaries. We propose a linear-algebraic approach to model parallelism in deep learning, which allows parallel distribution of any tensor in the DNN. Rather than rely on automatic differentiation tools, which do not universally support distributed memory parallelism models, we show that parallel data movement operations, e.g., broadcast, sum-re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.03108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-04T19:38:05Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"164d74f2e8e6a96dba82a3e85a9ff7c5014d9976973fc1d71c32c5690ecec36a","abstract_canon_sha256":"9db170f0728b4072803bdb7b7af1f415fb35228b91a1437e590ab8c91d1bae77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:14.670438Z","signature_b64":"VXzN8+N0qf3+KGjwF03U2lB0AxTLDFmNYiKyFLl4MToir8DVy2KJ3dGp0zZYySrNb08puk7E4zQCDGNHTBcuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"921f6aff23930b8aa4f0f19dc8a38c6f1dd8249ae9d5635716297465086d29a0","last_reissued_at":"2026-07-05T01:08:14.670009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:14.670009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Linear Algebraic Approach to Model Parallelism in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Russell J. Hewett, Thomas J. Grady II","submitted_at":"2020-06-04T19:38:05Z","abstract_excerpt":"Training deep neural networks (DNNs) in large-cluster computing environments is increasingly necessary, as networks grow in size and complexity. Local memory and processing limitations require robust data and model parallelism for crossing compute node boundaries. We propose a linear-algebraic approach to model parallelism in deep learning, which allows parallel distribution of any tensor in the DNN. Rather than rely on automatic differentiation tools, which do not universally support distributed memory parallelism models, we show that parallel data movement operations, e.g., broadcast, sum-re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03108","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.03108/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.03108","created_at":"2026-07-05T01:08:14.670065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.03108v1","created_at":"2026-07-05T01:08:14.670065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03108","created_at":"2026-07-05T01:08:14.670065+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIPWV7ZDSMFY","created_at":"2026-07-05T01:08:14.670065+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIPWV7ZDSMFYVJHQ","created_at":"2026-07-05T01:08:14.670065+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIPWV7ZD","created_at":"2026-07-05T01:08:14.670065+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.14394","citing_title":"DRIFT: Direct Reduced Fourier Transforms for Distributed Spectral Neural Operators","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIPWV7ZDSMFYVJHQ6GO4RI4MN4","json":"https://pith.science/pith/SIPWV7ZDSMFYVJHQ6GO4RI4MN4.json","graph_json":"https://pith.science/api/pith-number/SIPWV7ZDSMFYVJHQ6GO4RI4MN4/graph.json","events_json":"https://pith.science/api/pith-number/SIPWV7ZDSMFYVJHQ6GO4RI4MN4/events.json","paper":"https://pith.science/paper/SIPWV7ZD"},"agent_actions":{"view_html":"https://pith.science/pith/SIPWV7ZDSMFYVJHQ6GO4RI4MN4","download_json":"https://pith.science/pith/SIPWV7ZDSMFYVJHQ6GO4RI4MN4.json","view_paper":"https://pith.science/paper/SIPWV7ZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.03108&json=true","fetch_graph":"https://pith.science/api/pith-number/SIPWV7ZDSMFYVJHQ6GO4RI4MN4/graph.json","fetch_events":"https://pith.science/api/pith-number/SIPWV7ZDSMFYVJHQ6GO4RI4MN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIPWV7ZDSMFYVJHQ6GO4RI4MN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIPWV7ZDSMFYVJHQ6GO4RI4MN4/action/storage_attestation","attest_author":"https://pith.science/pith/SIPWV7ZDSMFYVJHQ6GO4RI4MN4/action/author_attestation","sign_citation":"https://pith.science/pith/SIPWV7ZDSMFYVJHQ6GO4RI4MN4/action/citation_signature","submit_replication":"https://pith.science/pith/SIPWV7ZDSMFYVJHQ6GO4RI4MN4/action/replication_record"}},"created_at":"2026-07-05T01:08:14.670065+00:00","updated_at":"2026-07-05T01:08:14.670065+00:00"}