{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZI5LNTU3J5N4FJVTYPQLWUVJAF","short_pith_number":"pith:ZI5LNTU3","schema_version":"1.0","canonical_sha256":"ca3ab6ce9b4f5bc2a6b3c3e0bb52a9015d599f887d4df641abf654615bbdd68b","source":{"kind":"arxiv","id":"1812.04210","version":1},"attestation_state":"computed","paper":{"title":"A Main/Subsidiary Network Framework for Simplifying Binary Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Su, Xin Dong, Yinghao Xu, Yudian Li","submitted_at":"2018-12-11T03:55:00Z","abstract_excerpt":"To reduce memory footprint and run-time latency, techniques such as neural network pruning and binarization have been explored separately. However, it is unclear how to combine the best of the two worlds to get extremely small and efficient models. In this paper, we, for the first time, define the filter-level pruning problem for binary neural networks, which cannot be solved by simply migrating existing structural pruning methods for full-precision models. A novel learning-based approach is proposed to prune filters in our main/subsidiary network framework, where the main network is responsib"},"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":"1812.04210","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-11T03:55:00Z","cross_cats_sorted":[],"title_canon_sha256":"768c1966f990eaa22d039e694c6f7e3f64a5f0d27490c94eaab31d3349981c1b","abstract_canon_sha256":"0e273282f82a7b3643a9802a2a3e9368ff72d76bd6a831629abac4d2aa8c23c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:35.206113Z","signature_b64":"0tZSAcA7aLHxiaqztK9Yh9x7MMGEVOvFJ0jDG3ETtuPUx56GsIu2ugH6GZTkddVT8jqYxTvLud+j1o3G2CyuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca3ab6ce9b4f5bc2a6b3c3e0bb52a9015d599f887d4df641abf654615bbdd68b","last_reissued_at":"2026-05-17T23:58:35.205466Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:35.205466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Main/Subsidiary Network Framework for Simplifying Binary Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Su, Xin Dong, Yinghao Xu, Yudian Li","submitted_at":"2018-12-11T03:55:00Z","abstract_excerpt":"To reduce memory footprint and run-time latency, techniques such as neural network pruning and binarization have been explored separately. However, it is unclear how to combine the best of the two worlds to get extremely small and efficient models. In this paper, we, for the first time, define the filter-level pruning problem for binary neural networks, which cannot be solved by simply migrating existing structural pruning methods for full-precision models. A novel learning-based approach is proposed to prune filters in our main/subsidiary network framework, where the main network is responsib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04210","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":"1812.04210","created_at":"2026-05-17T23:58:35.205579+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.04210v1","created_at":"2026-05-17T23:58:35.205579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04210","created_at":"2026-05-17T23:58:35.205579+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZI5LNTU3J5N4","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZI5LNTU3J5N4FJVT","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZI5LNTU3","created_at":"2026-05-18T12:33:07.085635+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/ZI5LNTU3J5N4FJVTYPQLWUVJAF","json":"https://pith.science/pith/ZI5LNTU3J5N4FJVTYPQLWUVJAF.json","graph_json":"https://pith.science/api/pith-number/ZI5LNTU3J5N4FJVTYPQLWUVJAF/graph.json","events_json":"https://pith.science/api/pith-number/ZI5LNTU3J5N4FJVTYPQLWUVJAF/events.json","paper":"https://pith.science/paper/ZI5LNTU3"},"agent_actions":{"view_html":"https://pith.science/pith/ZI5LNTU3J5N4FJVTYPQLWUVJAF","download_json":"https://pith.science/pith/ZI5LNTU3J5N4FJVTYPQLWUVJAF.json","view_paper":"https://pith.science/paper/ZI5LNTU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.04210&json=true","fetch_graph":"https://pith.science/api/pith-number/ZI5LNTU3J5N4FJVTYPQLWUVJAF/graph.json","fetch_events":"https://pith.science/api/pith-number/ZI5LNTU3J5N4FJVTYPQLWUVJAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZI5LNTU3J5N4FJVTYPQLWUVJAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZI5LNTU3J5N4FJVTYPQLWUVJAF/action/storage_attestation","attest_author":"https://pith.science/pith/ZI5LNTU3J5N4FJVTYPQLWUVJAF/action/author_attestation","sign_citation":"https://pith.science/pith/ZI5LNTU3J5N4FJVTYPQLWUVJAF/action/citation_signature","submit_replication":"https://pith.science/pith/ZI5LNTU3J5N4FJVTYPQLWUVJAF/action/replication_record"}},"created_at":"2026-05-17T23:58:35.205579+00:00","updated_at":"2026-05-17T23:58:35.205579+00:00"}