{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RPS7HV2LCR2QDAGATHXH6BPGI4","short_pith_number":"pith:RPS7HV2L","schema_version":"1.0","canonical_sha256":"8be5f3d74b14750180c099ee7f05e647373f99b8cb12d17c39facea824c8f89d","source":{"kind":"arxiv","id":"1906.08637","version":1},"attestation_state":"computed","paper":{"title":"Back to Simplicity: How to Train Accurate BNNs from Scratch?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph Meinel, Haojin Yang, Joseph Bethge, Marvin Bornstein","submitted_at":"2019-06-19T10:32:45Z","abstract_excerpt":"Binary Neural Networks (BNNs) show promising progress in reducing computational and memory costs but suffer from substantial accuracy degradation compared to their real-valued counterparts on large-scale datasets, e.g., ImageNet. Previous work mainly focused on reducing quantization errors of weights and activations, whereby a series of approximation methods and sophisticated training tricks have been proposed. In this work, we make several observations that challenge conventional wisdom. We revisit some commonly used techniques, such as scaling factors and custom gradients, and show that thes"},"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":"1906.08637","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T10:32:45Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"c988c47eae1dc01542feb871e78011723b675eb008bdb2d2e308e4b3396d0ae9","abstract_canon_sha256":"b6272387798a28649f8afcc13a591abbb7aa5b50c758257a57f0dbf9352daf03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:50.026855Z","signature_b64":"Larx5L+TVQNS58q2M/bcus715lPJrry84SNJtqDRS5SCqScCcjdQcC4NmAvLI70b7yEyuqgP7Expg2CB3WJ9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8be5f3d74b14750180c099ee7f05e647373f99b8cb12d17c39facea824c8f89d","last_reissued_at":"2026-05-17T23:42:50.026365Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:50.026365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Back to Simplicity: How to Train Accurate BNNs from Scratch?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph Meinel, Haojin Yang, Joseph Bethge, Marvin Bornstein","submitted_at":"2019-06-19T10:32:45Z","abstract_excerpt":"Binary Neural Networks (BNNs) show promising progress in reducing computational and memory costs but suffer from substantial accuracy degradation compared to their real-valued counterparts on large-scale datasets, e.g., ImageNet. Previous work mainly focused on reducing quantization errors of weights and activations, whereby a series of approximation methods and sophisticated training tricks have been proposed. In this work, we make several observations that challenge conventional wisdom. We revisit some commonly used techniques, such as scaling factors and custom gradients, and show that thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08637","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":"1906.08637","created_at":"2026-05-17T23:42:50.026437+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.08637v1","created_at":"2026-05-17T23:42:50.026437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08637","created_at":"2026-05-17T23:42:50.026437+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPS7HV2LCR2Q","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPS7HV2LCR2QDAGA","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPS7HV2L","created_at":"2026-05-18T12:33:27.125529+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/RPS7HV2LCR2QDAGATHXH6BPGI4","json":"https://pith.science/pith/RPS7HV2LCR2QDAGATHXH6BPGI4.json","graph_json":"https://pith.science/api/pith-number/RPS7HV2LCR2QDAGATHXH6BPGI4/graph.json","events_json":"https://pith.science/api/pith-number/RPS7HV2LCR2QDAGATHXH6BPGI4/events.json","paper":"https://pith.science/paper/RPS7HV2L"},"agent_actions":{"view_html":"https://pith.science/pith/RPS7HV2LCR2QDAGATHXH6BPGI4","download_json":"https://pith.science/pith/RPS7HV2LCR2QDAGATHXH6BPGI4.json","view_paper":"https://pith.science/paper/RPS7HV2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.08637&json=true","fetch_graph":"https://pith.science/api/pith-number/RPS7HV2LCR2QDAGATHXH6BPGI4/graph.json","fetch_events":"https://pith.science/api/pith-number/RPS7HV2LCR2QDAGATHXH6BPGI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPS7HV2LCR2QDAGATHXH6BPGI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPS7HV2LCR2QDAGATHXH6BPGI4/action/storage_attestation","attest_author":"https://pith.science/pith/RPS7HV2LCR2QDAGATHXH6BPGI4/action/author_attestation","sign_citation":"https://pith.science/pith/RPS7HV2LCR2QDAGATHXH6BPGI4/action/citation_signature","submit_replication":"https://pith.science/pith/RPS7HV2LCR2QDAGATHXH6BPGI4/action/replication_record"}},"created_at":"2026-05-17T23:42:50.026437+00:00","updated_at":"2026-05-17T23:42:50.026437+00:00"}