{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YELCIOG2M3L5NKP5YLUWGBERNX","short_pith_number":"pith:YELCIOG2","schema_version":"1.0","canonical_sha256":"c1162438da66d7d6a9fdc2e96304916dc6b884438a3fdae955b583a11a01d6cf","source":{"kind":"arxiv","id":"1809.09244","version":2},"attestation_state":"computed","paper":{"title":"No Multiplication? No Floating Point? No Problem! Training Networks for Efficient Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Marwood, Michele Covell, Nick Johnston, Shumeet Baluja","submitted_at":"2018-09-24T22:29:24Z","abstract_excerpt":"For successful deployment of deep neural networks on highly--resource-constrained devices (hearing aids, earbuds, wearables), we must simplify the types of operations and the memory/power resources used during inference. Completely avoiding inference-time floating-point operations is one of the simplest ways to design networks for these highly-constrained environments. By discretizing both our in-network non-linearities and our network weights, we can move to simple, compact networks without floating point operations, without multiplications, and avoid all non-linear function computations. Our"},"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":"1809.09244","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-24T22:29:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"082cda222641564b822d5c2c1886303ea6eb51bd138af79aa078c66da3c55718","abstract_canon_sha256":"c460beb66be0f91596353045b3b8bf8b8db1364e42fd1a226c9bbbb1a55820d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:33.868610Z","signature_b64":"rTUJJiDnYVXzPnpPZOm4CmaU1RvDwWnKBDLL61w6uapwXLsuSQ58IJ+K0fk4oYrt0rgUorjIseJY3FmYOnrJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1162438da66d7d6a9fdc2e96304916dc6b884438a3fdae955b583a11a01d6cf","last_reissued_at":"2026-05-18T00:04:33.867943Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:33.867943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No Multiplication? No Floating Point? No Problem! Training Networks for Efficient Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Marwood, Michele Covell, Nick Johnston, Shumeet Baluja","submitted_at":"2018-09-24T22:29:24Z","abstract_excerpt":"For successful deployment of deep neural networks on highly--resource-constrained devices (hearing aids, earbuds, wearables), we must simplify the types of operations and the memory/power resources used during inference. Completely avoiding inference-time floating-point operations is one of the simplest ways to design networks for these highly-constrained environments. By discretizing both our in-network non-linearities and our network weights, we can move to simple, compact networks without floating point operations, without multiplications, and avoid all non-linear function computations. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09244","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":""},"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":"1809.09244","created_at":"2026-05-18T00:04:33.868044+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.09244v2","created_at":"2026-05-18T00:04:33.868044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09244","created_at":"2026-05-18T00:04:33.868044+00:00"},{"alias_kind":"pith_short_12","alias_value":"YELCIOG2M3L5","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YELCIOG2M3L5NKP5","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YELCIOG2","created_at":"2026-05-18T12:33:04.347982+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/YELCIOG2M3L5NKP5YLUWGBERNX","json":"https://pith.science/pith/YELCIOG2M3L5NKP5YLUWGBERNX.json","graph_json":"https://pith.science/api/pith-number/YELCIOG2M3L5NKP5YLUWGBERNX/graph.json","events_json":"https://pith.science/api/pith-number/YELCIOG2M3L5NKP5YLUWGBERNX/events.json","paper":"https://pith.science/paper/YELCIOG2"},"agent_actions":{"view_html":"https://pith.science/pith/YELCIOG2M3L5NKP5YLUWGBERNX","download_json":"https://pith.science/pith/YELCIOG2M3L5NKP5YLUWGBERNX.json","view_paper":"https://pith.science/paper/YELCIOG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.09244&json=true","fetch_graph":"https://pith.science/api/pith-number/YELCIOG2M3L5NKP5YLUWGBERNX/graph.json","fetch_events":"https://pith.science/api/pith-number/YELCIOG2M3L5NKP5YLUWGBERNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YELCIOG2M3L5NKP5YLUWGBERNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YELCIOG2M3L5NKP5YLUWGBERNX/action/storage_attestation","attest_author":"https://pith.science/pith/YELCIOG2M3L5NKP5YLUWGBERNX/action/author_attestation","sign_citation":"https://pith.science/pith/YELCIOG2M3L5NKP5YLUWGBERNX/action/citation_signature","submit_replication":"https://pith.science/pith/YELCIOG2M3L5NKP5YLUWGBERNX/action/replication_record"}},"created_at":"2026-05-18T00:04:33.868044+00:00","updated_at":"2026-05-18T00:04:33.868044+00:00"}