{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:F5IQ6VL5GKBWPCPI57RJYAONRA","short_pith_number":"pith:F5IQ6VL5","schema_version":"1.0","canonical_sha256":"2f510f557d32836789e8efe29c01cd880a0e70dc1eecf9d8d27517e6c275af1d","source":{"kind":"arxiv","id":"1812.01965","version":1},"attestation_state":"computed","paper":{"title":"Training Competitive Binary Neural Networks from Scratch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrian Loy, Christoph Meinel, Haojin Yang, Joseph Bethge, Marvin Bornstein","submitted_at":"2018-12-05T12:48:50Z","abstract_excerpt":"Convolutional neural networks have achieved astonishing results in different application areas. Various methods that allow us to use these models on mobile and embedded devices have been proposed. Especially binary neural networks are a promising approach for devices with low computational power. However, training accurate binary models from scratch remains a challenge. Previous work often uses prior knowledge from full-precision models and complex training strategies. In our work, we focus on increasing the performance of binary neural networks without such prior knowledge and a much simpler "},"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":"1812.01965","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-05T12:48:50Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"ed75e56a609527a7c33a2cce9a8480884b2153f0e9599b7ad8b1f06e0337aa21","abstract_canon_sha256":"c39dae32b028061e32dbfc2d916b646198e39c0d3da88b08bed949803e0b7b7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:00.049832Z","signature_b64":"m64eWvtLf8fv2fTutcTlJKDReBS8L0nqavNwLE7Mvo0J5CR+ho3vv/lX3MbKOCR+bfFniQfYn19ChzG2yCJjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f510f557d32836789e8efe29c01cd880a0e70dc1eecf9d8d27517e6c275af1d","last_reissued_at":"2026-05-17T23:59:00.049246Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:00.049246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Competitive Binary Neural Networks from Scratch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrian Loy, Christoph Meinel, Haojin Yang, Joseph Bethge, Marvin Bornstein","submitted_at":"2018-12-05T12:48:50Z","abstract_excerpt":"Convolutional neural networks have achieved astonishing results in different application areas. Various methods that allow us to use these models on mobile and embedded devices have been proposed. Especially binary neural networks are a promising approach for devices with low computational power. However, training accurate binary models from scratch remains a challenge. Previous work often uses prior knowledge from full-precision models and complex training strategies. In our work, we focus on increasing the performance of binary neural networks without such prior knowledge and a much simpler "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01965","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":"1812.01965","created_at":"2026-05-17T23:59:00.049336+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01965v1","created_at":"2026-05-17T23:59:00.049336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01965","created_at":"2026-05-17T23:59:00.049336+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5IQ6VL5GKBW","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5IQ6VL5GKBWPCPI","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5IQ6VL5","created_at":"2026-05-18T12:32:22.470017+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/F5IQ6VL5GKBWPCPI57RJYAONRA","json":"https://pith.science/pith/F5IQ6VL5GKBWPCPI57RJYAONRA.json","graph_json":"https://pith.science/api/pith-number/F5IQ6VL5GKBWPCPI57RJYAONRA/graph.json","events_json":"https://pith.science/api/pith-number/F5IQ6VL5GKBWPCPI57RJYAONRA/events.json","paper":"https://pith.science/paper/F5IQ6VL5"},"agent_actions":{"view_html":"https://pith.science/pith/F5IQ6VL5GKBWPCPI57RJYAONRA","download_json":"https://pith.science/pith/F5IQ6VL5GKBWPCPI57RJYAONRA.json","view_paper":"https://pith.science/paper/F5IQ6VL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01965&json=true","fetch_graph":"https://pith.science/api/pith-number/F5IQ6VL5GKBWPCPI57RJYAONRA/graph.json","fetch_events":"https://pith.science/api/pith-number/F5IQ6VL5GKBWPCPI57RJYAONRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5IQ6VL5GKBWPCPI57RJYAONRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5IQ6VL5GKBWPCPI57RJYAONRA/action/storage_attestation","attest_author":"https://pith.science/pith/F5IQ6VL5GKBWPCPI57RJYAONRA/action/author_attestation","sign_citation":"https://pith.science/pith/F5IQ6VL5GKBWPCPI57RJYAONRA/action/citation_signature","submit_replication":"https://pith.science/pith/F5IQ6VL5GKBWPCPI57RJYAONRA/action/replication_record"}},"created_at":"2026-05-17T23:59:00.049336+00:00","updated_at":"2026-05-17T23:59:00.049336+00:00"}