{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UTDZE6F4S6YN6IMAK2H4KY4ESR","short_pith_number":"pith:UTDZE6F4","schema_version":"1.0","canonical_sha256":"a4c79278bc97b0df2180568fc56384945f870e4f7013ea94054ddb849a0510f1","source":{"kind":"arxiv","id":"1807.08716","version":2},"attestation_state":"computed","paper":{"title":"NullaNet: Training Deep Neural Networks for Reduced-Memory-Access Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ghasem Pasandi, Mahdi Nazemi, Massoud Pedram","submitted_at":"2018-07-23T16:50:31Z","abstract_excerpt":"Deep neural networks have been successfully deployed in a wide variety of applications including computer vision and speech recognition. However, computational and storage complexity of these models has forced the majority of computations to be performed on high-end computing platforms or on the cloud. To cope with computational and storage complexity of these models, this paper presents a training method that enables a radically different approach for realization of deep neural networks through Boolean logic minimization. The aforementioned realization completely removes the energy-hungry ste"},"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":"1807.08716","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-23T16:50:31Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"8aea3bf7336f45b51e429a405dab3a895a787eeb6e23126b6c3cb12b601eec8d","abstract_canon_sha256":"4532fca412a8bd85470b5977034cb4d32f72531dddf1bac479ebcb10b70290df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:17.152972Z","signature_b64":"3fYusURHys67RXnDXXFQxPgo2EtX5TYIfyvAX6jB7ypvDI2U3/Aqp9dFpf2ljsmSb6NewJAvNNdVNTHa7XRKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4c79278bc97b0df2180568fc56384945f870e4f7013ea94054ddb849a0510f1","last_reissued_at":"2026-05-18T00:07:17.152407Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:17.152407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NullaNet: Training Deep Neural Networks for Reduced-Memory-Access Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ghasem Pasandi, Mahdi Nazemi, Massoud Pedram","submitted_at":"2018-07-23T16:50:31Z","abstract_excerpt":"Deep neural networks have been successfully deployed in a wide variety of applications including computer vision and speech recognition. However, computational and storage complexity of these models has forced the majority of computations to be performed on high-end computing platforms or on the cloud. To cope with computational and storage complexity of these models, this paper presents a training method that enables a radically different approach for realization of deep neural networks through Boolean logic minimization. The aforementioned realization completely removes the energy-hungry ste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.08716","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":"1807.08716","created_at":"2026-05-18T00:07:17.152487+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.08716v2","created_at":"2026-05-18T00:07:17.152487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.08716","created_at":"2026-05-18T00:07:17.152487+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTDZE6F4S6YN","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTDZE6F4S6YN6IMA","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTDZE6F4","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1910.09876","citing_title":"Neural Network Training with Approximate Logarithmic Computations","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UTDZE6F4S6YN6IMAK2H4KY4ESR","json":"https://pith.science/pith/UTDZE6F4S6YN6IMAK2H4KY4ESR.json","graph_json":"https://pith.science/api/pith-number/UTDZE6F4S6YN6IMAK2H4KY4ESR/graph.json","events_json":"https://pith.science/api/pith-number/UTDZE6F4S6YN6IMAK2H4KY4ESR/events.json","paper":"https://pith.science/paper/UTDZE6F4"},"agent_actions":{"view_html":"https://pith.science/pith/UTDZE6F4S6YN6IMAK2H4KY4ESR","download_json":"https://pith.science/pith/UTDZE6F4S6YN6IMAK2H4KY4ESR.json","view_paper":"https://pith.science/paper/UTDZE6F4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.08716&json=true","fetch_graph":"https://pith.science/api/pith-number/UTDZE6F4S6YN6IMAK2H4KY4ESR/graph.json","fetch_events":"https://pith.science/api/pith-number/UTDZE6F4S6YN6IMAK2H4KY4ESR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTDZE6F4S6YN6IMAK2H4KY4ESR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTDZE6F4S6YN6IMAK2H4KY4ESR/action/storage_attestation","attest_author":"https://pith.science/pith/UTDZE6F4S6YN6IMAK2H4KY4ESR/action/author_attestation","sign_citation":"https://pith.science/pith/UTDZE6F4S6YN6IMAK2H4KY4ESR/action/citation_signature","submit_replication":"https://pith.science/pith/UTDZE6F4S6YN6IMAK2H4KY4ESR/action/replication_record"}},"created_at":"2026-05-18T00:07:17.152487+00:00","updated_at":"2026-05-18T00:07:17.152487+00:00"}