{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OVH2LWT2E4K226VHCHT5VYWGCK","short_pith_number":"pith:OVH2LWT2","schema_version":"1.0","canonical_sha256":"754fa5da7a2715ad7aa711e7dae2c6128cdf40189030a2a4e2f2a543df7b8bb5","source":{"kind":"arxiv","id":"1809.03368","version":1},"attestation_state":"computed","paper":{"title":"Probabilistic Binary Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jorn W.T. Peters, Max Welling","submitted_at":"2018-09-10T14:51:08Z","abstract_excerpt":"Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a probabilistic training method for Neural Network with both binary weights and activations, called BLRNet. By embracing stochasticity during training, we circumvent the need to approximate the gradient of non-differentiable functions such as sign(), while still obtaining a fully Binary Neural Network at test time. Moreover, it allows for anytime ensemble predictions for improved performance and uncertainty estimates by "},"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":"1809.03368","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-10T14:51:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3db3c945d3b0b26b52d9dc5180610fda0113d75ac4c70481f896628645e68e00","abstract_canon_sha256":"bfa927d48d1bcc1ab58c85cbeca901adbecd25af115322bb7527268bd81a86c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:07.059003Z","signature_b64":"Br9b8Gq4bYXKrUVQ1BNFbXuRVr1hd5qzZtBRu2NvNYDPz9yRg7Frqu/acOo8U4oJDIZT1NbRTpzvtRdEaPONAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"754fa5da7a2715ad7aa711e7dae2c6128cdf40189030a2a4e2f2a543df7b8bb5","last_reissued_at":"2026-05-18T00:06:07.058406Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:07.058406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Binary Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jorn W.T. Peters, Max Welling","submitted_at":"2018-09-10T14:51:08Z","abstract_excerpt":"Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a probabilistic training method for Neural Network with both binary weights and activations, called BLRNet. By embracing stochasticity during training, we circumvent the need to approximate the gradient of non-differentiable functions such as sign(), while still obtaining a fully Binary Neural Network at test time. Moreover, it allows for anytime ensemble predictions for improved performance and uncertainty estimates by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03368","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":"1809.03368","created_at":"2026-05-18T00:06:07.058493+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.03368v1","created_at":"2026-05-18T00:06:07.058493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03368","created_at":"2026-05-18T00:06:07.058493+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVH2LWT2E4K2","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVH2LWT2E4K226VH","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVH2LWT2","created_at":"2026-05-18T12:32:43.782077+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/OVH2LWT2E4K226VHCHT5VYWGCK","json":"https://pith.science/pith/OVH2LWT2E4K226VHCHT5VYWGCK.json","graph_json":"https://pith.science/api/pith-number/OVH2LWT2E4K226VHCHT5VYWGCK/graph.json","events_json":"https://pith.science/api/pith-number/OVH2LWT2E4K226VHCHT5VYWGCK/events.json","paper":"https://pith.science/paper/OVH2LWT2"},"agent_actions":{"view_html":"https://pith.science/pith/OVH2LWT2E4K226VHCHT5VYWGCK","download_json":"https://pith.science/pith/OVH2LWT2E4K226VHCHT5VYWGCK.json","view_paper":"https://pith.science/paper/OVH2LWT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.03368&json=true","fetch_graph":"https://pith.science/api/pith-number/OVH2LWT2E4K226VHCHT5VYWGCK/graph.json","fetch_events":"https://pith.science/api/pith-number/OVH2LWT2E4K226VHCHT5VYWGCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVH2LWT2E4K226VHCHT5VYWGCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVH2LWT2E4K226VHCHT5VYWGCK/action/storage_attestation","attest_author":"https://pith.science/pith/OVH2LWT2E4K226VHCHT5VYWGCK/action/author_attestation","sign_citation":"https://pith.science/pith/OVH2LWT2E4K226VHCHT5VYWGCK/action/citation_signature","submit_replication":"https://pith.science/pith/OVH2LWT2E4K226VHCHT5VYWGCK/action/replication_record"}},"created_at":"2026-05-18T00:06:07.058493+00:00","updated_at":"2026-05-18T00:06:07.058493+00:00"}