{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:U2IYXFSULBQDBILQUFOXUKRL2B","short_pith_number":"pith:U2IYXFSU","schema_version":"1.0","canonical_sha256":"a6918b9654586030a170a15d7a2a2bd0656dcbddad73c2d77a4792f31bc46e54","source":{"kind":"arxiv","id":"1807.00942","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Layer-Wise Precision in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Graham W. Taylor, Griffin Lacey, Shawki Areibi","submitted_at":"2018-07-03T01:11:14Z","abstract_excerpt":"Low precision weights, activations, and gradients have been proposed as a way to improve the computational efficiency and memory footprint of deep neural networks. Recently, low precision networks have even shown to be more robust to adversarial attacks. However, typical implementations of low precision DNNs use uniform precision across all layers of the network. In this work, we explore whether a heterogeneous allocation of precision across a network leads to improved performance, and introduce a learning scheme where a DNN stochastically explores multiple precision configurations through lea"},"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":"1807.00942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-03T01:11:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e171a15aae021b02d5e2c691e1fcef47f490d9566160ea4e1cf47f613831b62b","abstract_canon_sha256":"eb0ffc09619827d0affe8d9583a95908f620170485e2bbed7e3c66a7d1c0d573"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:45.986144Z","signature_b64":"IhssDs1OZWD0fh2KWLamPECHcPYsicHr9Xu/Z66NqIqoHh5gMLzkrR7UlzrINIUP83Si5xsRk5U5CtUE+DK/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6918b9654586030a170a15d7a2a2bd0656dcbddad73c2d77a4792f31bc46e54","last_reissued_at":"2026-05-18T00:11:45.985587Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:45.985587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Layer-Wise Precision in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Graham W. Taylor, Griffin Lacey, Shawki Areibi","submitted_at":"2018-07-03T01:11:14Z","abstract_excerpt":"Low precision weights, activations, and gradients have been proposed as a way to improve the computational efficiency and memory footprint of deep neural networks. Recently, low precision networks have even shown to be more robust to adversarial attacks. However, typical implementations of low precision DNNs use uniform precision across all layers of the network. In this work, we explore whether a heterogeneous allocation of precision across a network leads to improved performance, and introduce a learning scheme where a DNN stochastically explores multiple precision configurations through lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00942","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.00942","created_at":"2026-05-18T00:11:45.985661+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00942v1","created_at":"2026-05-18T00:11:45.985661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00942","created_at":"2026-05-18T00:11:45.985661+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2IYXFSULBQD","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2IYXFSULBQDBILQ","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2IYXFSU","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U2IYXFSULBQDBILQUFOXUKRL2B","json":"https://pith.science/pith/U2IYXFSULBQDBILQUFOXUKRL2B.json","graph_json":"https://pith.science/api/pith-number/U2IYXFSULBQDBILQUFOXUKRL2B/graph.json","events_json":"https://pith.science/api/pith-number/U2IYXFSULBQDBILQUFOXUKRL2B/events.json","paper":"https://pith.science/paper/U2IYXFSU"},"agent_actions":{"view_html":"https://pith.science/pith/U2IYXFSULBQDBILQUFOXUKRL2B","download_json":"https://pith.science/pith/U2IYXFSULBQDBILQUFOXUKRL2B.json","view_paper":"https://pith.science/paper/U2IYXFSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00942&json=true","fetch_graph":"https://pith.science/api/pith-number/U2IYXFSULBQDBILQUFOXUKRL2B/graph.json","fetch_events":"https://pith.science/api/pith-number/U2IYXFSULBQDBILQUFOXUKRL2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2IYXFSULBQDBILQUFOXUKRL2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2IYXFSULBQDBILQUFOXUKRL2B/action/storage_attestation","attest_author":"https://pith.science/pith/U2IYXFSULBQDBILQUFOXUKRL2B/action/author_attestation","sign_citation":"https://pith.science/pith/U2IYXFSULBQDBILQUFOXUKRL2B/action/citation_signature","submit_replication":"https://pith.science/pith/U2IYXFSULBQDBILQUFOXUKRL2B/action/replication_record"}},"created_at":"2026-05-18T00:11:45.985661+00:00","updated_at":"2026-05-18T00:11:45.985661+00:00"}