{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DAEXCDHKPPDAVJI637ZCWIJV4O","short_pith_number":"pith:DAEXCDHK","schema_version":"1.0","canonical_sha256":"1809710cea7bc60aa51edff22b2135e3b1f5e81ee0b7e2be8d382642ca2da857","source":{"kind":"arxiv","id":"2004.03333","version":1},"attestation_state":"computed","paper":{"title":"Binary Neural Networks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"Haotong Qin, Jingkuan Song, Nicu Sebe, Ruihao Gong, Xianglong Liu, Xiao Bai","submitted_at":"2020-03-31T16:47:20Z","abstract_excerpt":"The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the binarization inevitably causes severe information loss, and even worse, its discontinuity brings difficulty to the optimization of the deep network. To address these issues, a variety of algorithms have been proposed, and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the opti"},"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":"2004.03333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2020-03-31T16:47:20Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"80e5c89fd141380cfde11bf50a1df410c4c7cb731ffe55aac3dea3909760a2b2","abstract_canon_sha256":"f0804578d3e4a64220110118366ad7a4fab0aed1e3f2afd658cdcf2b98ccd848"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:25.057120Z","signature_b64":"Z8GRWvcGNdLt10+PhfdxVcj5CJb+SGGxGEWgnkv8w1LnbwG+WGxEfRdOuK4xexjcObJMWq8HQ6ytas5A/OVOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1809710cea7bc60aa51edff22b2135e3b1f5e81ee0b7e2be8d382642ca2da857","last_reissued_at":"2026-07-05T00:53:25.056704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:25.056704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Binary Neural Networks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"Haotong Qin, Jingkuan Song, Nicu Sebe, Ruihao Gong, Xianglong Liu, Xiao Bai","submitted_at":"2020-03-31T16:47:20Z","abstract_excerpt":"The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the binarization inevitably causes severe information loss, and even worse, its discontinuity brings difficulty to the optimization of the deep network. To address these issues, a variety of algorithms have been proposed, and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03333","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/2004.03333/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":"2004.03333","created_at":"2026-07-05T00:53:25.056764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.03333v1","created_at":"2026-07-05T00:53:25.056764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03333","created_at":"2026-07-05T00:53:25.056764+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAEXCDHKPPDA","created_at":"2026-07-05T00:53:25.056764+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAEXCDHKPPDAVJI6","created_at":"2026-07-05T00:53:25.056764+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAEXCDHK","created_at":"2026-07-05T00:53:25.056764+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2208.07339","citing_title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","ref_index":155,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DAEXCDHKPPDAVJI637ZCWIJV4O","json":"https://pith.science/pith/DAEXCDHKPPDAVJI637ZCWIJV4O.json","graph_json":"https://pith.science/api/pith-number/DAEXCDHKPPDAVJI637ZCWIJV4O/graph.json","events_json":"https://pith.science/api/pith-number/DAEXCDHKPPDAVJI637ZCWIJV4O/events.json","paper":"https://pith.science/paper/DAEXCDHK"},"agent_actions":{"view_html":"https://pith.science/pith/DAEXCDHKPPDAVJI637ZCWIJV4O","download_json":"https://pith.science/pith/DAEXCDHKPPDAVJI637ZCWIJV4O.json","view_paper":"https://pith.science/paper/DAEXCDHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.03333&json=true","fetch_graph":"https://pith.science/api/pith-number/DAEXCDHKPPDAVJI637ZCWIJV4O/graph.json","fetch_events":"https://pith.science/api/pith-number/DAEXCDHKPPDAVJI637ZCWIJV4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAEXCDHKPPDAVJI637ZCWIJV4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAEXCDHKPPDAVJI637ZCWIJV4O/action/storage_attestation","attest_author":"https://pith.science/pith/DAEXCDHKPPDAVJI637ZCWIJV4O/action/author_attestation","sign_citation":"https://pith.science/pith/DAEXCDHKPPDAVJI637ZCWIJV4O/action/citation_signature","submit_replication":"https://pith.science/pith/DAEXCDHKPPDAVJI637ZCWIJV4O/action/replication_record"}},"created_at":"2026-07-05T00:53:25.056764+00:00","updated_at":"2026-07-05T00:53:25.056764+00:00"}