{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:Q7MUJFIQD7L5HG56KSWOFEGZ3P","short_pith_number":"pith:Q7MUJFIQ","schema_version":"1.0","canonical_sha256":"87d94495101fd7d39bbe54ace290d9dbec3af4327db8c68aad80d01f68b4bc5b","source":{"kind":"arxiv","id":"1602.02505","version":3},"attestation_state":"computed","paper":{"title":"Binarized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Daniel Soudry, Itay Hubara, Ran El Yaniv","submitted_at":"2016-02-08T09:37:46Z","abstract_excerpt":"We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time and when computing the parameters' gradient at train-time. We conduct two sets of experiments, each based on a different framework, namely Torch7 and Theano, where we train BNNs on MNIST, CIFAR-10 and SVHN, and achieve nearly state-of-the-art results. During the forward pass, BNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations, which might lead to a great increase in power-efficiency. Last but not least, "},"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":"1602.02505","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-08T09:37:46Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"f33eac8e61b0becc4968333b902bd6e61f7f492d09aa7cef37c4d5e235eb2259","abstract_canon_sha256":"f88ebcde087c80f8010c7019901b24402459ab3ecc649812846491b73314c8d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:18.247234Z","signature_b64":"1OJt0dQAS4hMn/lmaI9RS74SLWSYE5G/xWD50BAkqzdmuNZBQa0nxU8gd1cBOGzWXxHyE+9OpFvtk2NpmJKYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87d94495101fd7d39bbe54ace290d9dbec3af4327db8c68aad80d01f68b4bc5b","last_reissued_at":"2026-05-18T01:19:18.246845Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:18.246845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Binarized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Daniel Soudry, Itay Hubara, Ran El Yaniv","submitted_at":"2016-02-08T09:37:46Z","abstract_excerpt":"We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time and when computing the parameters' gradient at train-time. We conduct two sets of experiments, each based on a different framework, namely Torch7 and Theano, where we train BNNs on MNIST, CIFAR-10 and SVHN, and achieve nearly state-of-the-art results. During the forward pass, BNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations, which might lead to a great increase in power-efficiency. Last but not least, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02505","kind":"arxiv","version":3},"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":"1602.02505","created_at":"2026-05-18T01:19:18.246902+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.02505v3","created_at":"2026-05-18T01:19:18.246902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02505","created_at":"2026-05-18T01:19:18.246902+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7MUJFIQD7L5","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7MUJFIQD7L5HG56","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7MUJFIQ","created_at":"2026-05-18T12:30:39.010887+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/Q7MUJFIQD7L5HG56KSWOFEGZ3P","json":"https://pith.science/pith/Q7MUJFIQD7L5HG56KSWOFEGZ3P.json","graph_json":"https://pith.science/api/pith-number/Q7MUJFIQD7L5HG56KSWOFEGZ3P/graph.json","events_json":"https://pith.science/api/pith-number/Q7MUJFIQD7L5HG56KSWOFEGZ3P/events.json","paper":"https://pith.science/paper/Q7MUJFIQ"},"agent_actions":{"view_html":"https://pith.science/pith/Q7MUJFIQD7L5HG56KSWOFEGZ3P","download_json":"https://pith.science/pith/Q7MUJFIQD7L5HG56KSWOFEGZ3P.json","view_paper":"https://pith.science/paper/Q7MUJFIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.02505&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7MUJFIQD7L5HG56KSWOFEGZ3P/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7MUJFIQD7L5HG56KSWOFEGZ3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7MUJFIQD7L5HG56KSWOFEGZ3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7MUJFIQD7L5HG56KSWOFEGZ3P/action/storage_attestation","attest_author":"https://pith.science/pith/Q7MUJFIQD7L5HG56KSWOFEGZ3P/action/author_attestation","sign_citation":"https://pith.science/pith/Q7MUJFIQD7L5HG56KSWOFEGZ3P/action/citation_signature","submit_replication":"https://pith.science/pith/Q7MUJFIQD7L5HG56KSWOFEGZ3P/action/replication_record"}},"created_at":"2026-05-18T01:19:18.246902+00:00","updated_at":"2026-05-18T01:19:18.246902+00:00"}