{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MDAOA5QIOS5YI3M7R42QLGITVT","short_pith_number":"pith:MDAOA5QI","schema_version":"1.0","canonical_sha256":"60c0e0760874bb846d9f8f35059913acee901c69aaf1ac6587909ab064bc275f","source":{"kind":"arxiv","id":"2012.12206","version":1},"attestation_state":"computed","paper":{"title":"FracBNN: Accurate and FPGA-Efficient Binary Neural Networks with Fractional Activations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Deming Chen, Hongzheng Chen, Junhao Pan, Xinheng Liu, Yichi Zhang, Zhiru Zhang","submitted_at":"2020-12-22T17:49:30Z","abstract_excerpt":"Binary neural networks (BNNs) have 1-bit weights and activations. Such networks are well suited for FPGAs, as their dominant computations are bitwise arithmetic and the memory requirement is also significantly reduced. However, compared to start-of-the-art compact convolutional neural network (CNN) models, BNNs tend to produce a much lower accuracy on realistic datasets such as ImageNet. In addition, the input layer of BNNs has gradually become a major compute bottleneck, because it is conventionally excluded from binarization to avoid a large accuracy loss. This work proposes FracBNN, which e"},"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":"2012.12206","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-22T17:49:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e8ab44bd9310e9245bc804ae56cb610bd369d5672c544f5fd7af03cb2969ae6a","abstract_canon_sha256":"7107ab8abdbda87d159d47726c1497da6c1967b90640e25867c342cc9912d909"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:01:26.019536Z","signature_b64":"1e3iM3zSVZeVlnrrEkcDmbclTvQfUZWHOaoCpSdQNjcxWHvfshBFTwh1eO8eH8PPwNnqypNEX1r3wWpN+cC7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60c0e0760874bb846d9f8f35059913acee901c69aaf1ac6587909ab064bc275f","last_reissued_at":"2026-07-05T02:01:26.019092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:01:26.019092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FracBNN: Accurate and FPGA-Efficient Binary Neural Networks with Fractional Activations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Deming Chen, Hongzheng Chen, Junhao Pan, Xinheng Liu, Yichi Zhang, Zhiru Zhang","submitted_at":"2020-12-22T17:49:30Z","abstract_excerpt":"Binary neural networks (BNNs) have 1-bit weights and activations. Such networks are well suited for FPGAs, as their dominant computations are bitwise arithmetic and the memory requirement is also significantly reduced. However, compared to start-of-the-art compact convolutional neural network (CNN) models, BNNs tend to produce a much lower accuracy on realistic datasets such as ImageNet. In addition, the input layer of BNNs has gradually become a major compute bottleneck, because it is conventionally excluded from binarization to avoid a large accuracy loss. This work proposes FracBNN, which e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.12206","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.12206/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2012.12206","created_at":"2026-07-05T02:01:26.019157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.12206v1","created_at":"2026-07-05T02:01:26.019157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.12206","created_at":"2026-07-05T02:01:26.019157+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDAOA5QIOS5Y","created_at":"2026-07-05T02:01:26.019157+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDAOA5QIOS5YI3M7","created_at":"2026-07-05T02:01:26.019157+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDAOA5QI","created_at":"2026-07-05T02:01:26.019157+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/MDAOA5QIOS5YI3M7R42QLGITVT","json":"https://pith.science/pith/MDAOA5QIOS5YI3M7R42QLGITVT.json","graph_json":"https://pith.science/api/pith-number/MDAOA5QIOS5YI3M7R42QLGITVT/graph.json","events_json":"https://pith.science/api/pith-number/MDAOA5QIOS5YI3M7R42QLGITVT/events.json","paper":"https://pith.science/paper/MDAOA5QI"},"agent_actions":{"view_html":"https://pith.science/pith/MDAOA5QIOS5YI3M7R42QLGITVT","download_json":"https://pith.science/pith/MDAOA5QIOS5YI3M7R42QLGITVT.json","view_paper":"https://pith.science/paper/MDAOA5QI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.12206&json=true","fetch_graph":"https://pith.science/api/pith-number/MDAOA5QIOS5YI3M7R42QLGITVT/graph.json","fetch_events":"https://pith.science/api/pith-number/MDAOA5QIOS5YI3M7R42QLGITVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDAOA5QIOS5YI3M7R42QLGITVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDAOA5QIOS5YI3M7R42QLGITVT/action/storage_attestation","attest_author":"https://pith.science/pith/MDAOA5QIOS5YI3M7R42QLGITVT/action/author_attestation","sign_citation":"https://pith.science/pith/MDAOA5QIOS5YI3M7R42QLGITVT/action/citation_signature","submit_replication":"https://pith.science/pith/MDAOA5QIOS5YI3M7R42QLGITVT/action/replication_record"}},"created_at":"2026-07-05T02:01:26.019157+00:00","updated_at":"2026-07-05T02:01:26.019157+00:00"}