{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4GLFCPFGKXF5SRCLEED44RH3J5","short_pith_number":"pith:4GLFCPFG","schema_version":"1.0","canonical_sha256":"e196513ca655cbd9444b2107ce44fb4f650e46e1ad670179623ac4aaff743bac","source":{"kind":"arxiv","id":"2112.10149","version":2},"attestation_state":"computed","paper":{"title":"Elastic-Link for Binarized Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enhua Wu, Jie Hu, Mengze Zeng, Vince Tan, Zhilin Lu, Ziheng Wu","submitted_at":"2021-12-19T13:49:29Z","abstract_excerpt":"Recent work has shown that Binarized Neural Networks (BNNs) are able to greatly reduce computational costs and memory footprints, facilitating model deployment on resource-constrained devices. However, in comparison to their full-precision counterparts, BNNs suffer from severe accuracy degradation. Research aiming to reduce this accuracy gap has thus far largely focused on specific network architectures with few or no 1x1 convolutional layers, for which standard binarization methods do not work well. Because 1x1 convolutions are common in the design of modern architectures (e.g. GoogleNet, Res"},"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":"2112.10149","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-19T13:49:29Z","cross_cats_sorted":[],"title_canon_sha256":"292a7d29abf17868a59c873d89aee545f854139e05071a7889254558053db008","abstract_canon_sha256":"b687a83ec97d3bcce98e2ef838dd2f73da2edf5efd9cb99fb2a35954517d2594"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:47.103462Z","signature_b64":"hIdttX/p0q6NUkrQjz3uxROC9rOPkklIF6eOh2MvNkvoOrU1ANuttKz3SdlTBUUoJeVjfKagAojO9YgJ3x9QCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e196513ca655cbd9444b2107ce44fb4f650e46e1ad670179623ac4aaff743bac","last_reissued_at":"2026-07-05T05:42:47.102871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:47.102871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Elastic-Link for Binarized Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enhua Wu, Jie Hu, Mengze Zeng, Vince Tan, Zhilin Lu, Ziheng Wu","submitted_at":"2021-12-19T13:49:29Z","abstract_excerpt":"Recent work has shown that Binarized Neural Networks (BNNs) are able to greatly reduce computational costs and memory footprints, facilitating model deployment on resource-constrained devices. However, in comparison to their full-precision counterparts, BNNs suffer from severe accuracy degradation. Research aiming to reduce this accuracy gap has thus far largely focused on specific network architectures with few or no 1x1 convolutional layers, for which standard binarization methods do not work well. Because 1x1 convolutions are common in the design of modern architectures (e.g. GoogleNet, Res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10149","kind":"arxiv","version":2},"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/2112.10149/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":"2112.10149","created_at":"2026-07-05T05:42:47.102942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.10149v2","created_at":"2026-07-05T05:42:47.102942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10149","created_at":"2026-07-05T05:42:47.102942+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GLFCPFGKXF5","created_at":"2026-07-05T05:42:47.102942+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GLFCPFGKXF5SRCL","created_at":"2026-07-05T05:42:47.102942+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GLFCPFG","created_at":"2026-07-05T05:42:47.102942+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/4GLFCPFGKXF5SRCLEED44RH3J5","json":"https://pith.science/pith/4GLFCPFGKXF5SRCLEED44RH3J5.json","graph_json":"https://pith.science/api/pith-number/4GLFCPFGKXF5SRCLEED44RH3J5/graph.json","events_json":"https://pith.science/api/pith-number/4GLFCPFGKXF5SRCLEED44RH3J5/events.json","paper":"https://pith.science/paper/4GLFCPFG"},"agent_actions":{"view_html":"https://pith.science/pith/4GLFCPFGKXF5SRCLEED44RH3J5","download_json":"https://pith.science/pith/4GLFCPFGKXF5SRCLEED44RH3J5.json","view_paper":"https://pith.science/paper/4GLFCPFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.10149&json=true","fetch_graph":"https://pith.science/api/pith-number/4GLFCPFGKXF5SRCLEED44RH3J5/graph.json","fetch_events":"https://pith.science/api/pith-number/4GLFCPFGKXF5SRCLEED44RH3J5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GLFCPFGKXF5SRCLEED44RH3J5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GLFCPFGKXF5SRCLEED44RH3J5/action/storage_attestation","attest_author":"https://pith.science/pith/4GLFCPFGKXF5SRCLEED44RH3J5/action/author_attestation","sign_citation":"https://pith.science/pith/4GLFCPFGKXF5SRCLEED44RH3J5/action/citation_signature","submit_replication":"https://pith.science/pith/4GLFCPFGKXF5SRCLEED44RH3J5/action/replication_record"}},"created_at":"2026-07-05T05:42:47.102942+00:00","updated_at":"2026-07-05T05:42:47.102942+00:00"}