{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BZSLCOBWVGRXDAUVXNZTIGVXDL","short_pith_number":"pith:BZSLCOBW","schema_version":"1.0","canonical_sha256":"0e64b13836a9a3718295bb73341ab71acd72057ad83dc3c6ece41b25ae5dd2d3","source":{"kind":"arxiv","id":"1909.09934","version":4},"attestation_state":"computed","paper":{"title":"Structured Binary Neural Networks for Image Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Chunhua Shen, Ian Reid, Lingqiao Liu, Mingkui Tan, Peng Chen","submitted_at":"2019-09-22T03:45:49Z","abstract_excerpt":"We propose methods to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models that are specifically friendly to mobile devices with limited power capacity and computation resources. Previous works on quantizing CNNs often seek to approximate the floating-point information using a set of discrete values, which we call value approximation, typically assuming the same architecture as the full-precision networks. Here we take a novel \"structure approximation\" view of quantization -- it is very likely that different architectures designed "},"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":"1909.09934","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-09-22T03:45:49Z","cross_cats_sorted":[],"title_canon_sha256":"e01591c829551168c34160668d439f5c773c12a369a637c336bc27df6eeb263f","abstract_canon_sha256":"e5940d6fc989f6a4a81594770e3e247dec3dece79984c3a8ceb726b843a347b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:06.352999Z","signature_b64":"wm+v0DCtQlMggZmN6q3jMRzZ1mlbsfhFT+c1M1EtuzkkVjFY7XI5DEVM1tKSELmDy1LMI6Oxk+KqnXnl1Bd2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e64b13836a9a3718295bb73341ab71acd72057ad83dc3c6ece41b25ae5dd2d3","last_reissued_at":"2026-07-05T04:29:06.352568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:06.352568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Binary Neural Networks for Image Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Chunhua Shen, Ian Reid, Lingqiao Liu, Mingkui Tan, Peng Chen","submitted_at":"2019-09-22T03:45:49Z","abstract_excerpt":"We propose methods to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models that are specifically friendly to mobile devices with limited power capacity and computation resources. Previous works on quantizing CNNs often seek to approximate the floating-point information using a set of discrete values, which we call value approximation, typically assuming the same architecture as the full-precision networks. Here we take a novel \"structure approximation\" view of quantization -- it is very likely that different architectures designed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.09934","kind":"arxiv","version":4},"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/1909.09934/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":"1909.09934","created_at":"2026-07-05T04:29:06.352629+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.09934v4","created_at":"2026-07-05T04:29:06.352629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.09934","created_at":"2026-07-05T04:29:06.352629+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZSLCOBWVGRX","created_at":"2026-07-05T04:29:06.352629+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZSLCOBWVGRXDAUV","created_at":"2026-07-05T04:29:06.352629+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZSLCOBW","created_at":"2026-07-05T04:29:06.352629+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08339","citing_title":"SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning","ref_index":176,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZSLCOBWVGRXDAUVXNZTIGVXDL","json":"https://pith.science/pith/BZSLCOBWVGRXDAUVXNZTIGVXDL.json","graph_json":"https://pith.science/api/pith-number/BZSLCOBWVGRXDAUVXNZTIGVXDL/graph.json","events_json":"https://pith.science/api/pith-number/BZSLCOBWVGRXDAUVXNZTIGVXDL/events.json","paper":"https://pith.science/paper/BZSLCOBW"},"agent_actions":{"view_html":"https://pith.science/pith/BZSLCOBWVGRXDAUVXNZTIGVXDL","download_json":"https://pith.science/pith/BZSLCOBWVGRXDAUVXNZTIGVXDL.json","view_paper":"https://pith.science/paper/BZSLCOBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.09934&json=true","fetch_graph":"https://pith.science/api/pith-number/BZSLCOBWVGRXDAUVXNZTIGVXDL/graph.json","fetch_events":"https://pith.science/api/pith-number/BZSLCOBWVGRXDAUVXNZTIGVXDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZSLCOBWVGRXDAUVXNZTIGVXDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZSLCOBWVGRXDAUVXNZTIGVXDL/action/storage_attestation","attest_author":"https://pith.science/pith/BZSLCOBWVGRXDAUVXNZTIGVXDL/action/author_attestation","sign_citation":"https://pith.science/pith/BZSLCOBWVGRXDAUVXNZTIGVXDL/action/citation_signature","submit_replication":"https://pith.science/pith/BZSLCOBWVGRXDAUVXNZTIGVXDL/action/replication_record"}},"created_at":"2026-07-05T04:29:06.352629+00:00","updated_at":"2026-07-05T04:29:06.352629+00:00"}