{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZZXSUEZH6EXBJ2EHOETU2CB52J","short_pith_number":"pith:ZZXSUEZH","schema_version":"1.0","canonical_sha256":"ce6f2a1327f12e14e88771274d083dd27335a14ad03a8ed16fdcdbd12dcc96df","source":{"kind":"arxiv","id":"1709.04344","version":3},"attestation_state":"computed","paper":{"title":"Flexible Network Binarization with Layer-wise Priority","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Ni, Hongteng Xu, Lixue Zhuang, Yi Xu","submitted_at":"2017-09-13T14:14:15Z","abstract_excerpt":"How to effectively approximate real-valued parameters with binary codes plays a central role in neural network binarization. In this work, we reveal an important fact that binarizing different layers has a widely-varied effect on the compression ratio of network and the loss of performance. Based on this fact, we propose a novel and flexible neural network binarization method by introducing the concept of layer-wise priority which binarizes parameters in inverse order of their layer depth. In each training step, our method selects a specific network layer, minimizes the discrepancy between the"},"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":"1709.04344","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-13T14:14:15Z","cross_cats_sorted":[],"title_canon_sha256":"037966e2b254f098ce2b051c0b620cf68f067b2a52ad65ec3174412e4c9bad44","abstract_canon_sha256":"3e6002bbc1328b2aac692a829dadfb9ac3757f634913e80018a78162e7d82de7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:13.986955Z","signature_b64":"1QSHSN+ZLGyMggp+gHxQ0owzgULIROFusDVFLa5gnpgO/nTGGaeiIb5pugWpAVEvDCdS2RAV/kgcbgVyL20CCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce6f2a1327f12e14e88771274d083dd27335a14ad03a8ed16fdcdbd12dcc96df","last_reissued_at":"2026-05-18T00:23:13.986365Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:13.986365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flexible Network Binarization with Layer-wise Priority","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Ni, Hongteng Xu, Lixue Zhuang, Yi Xu","submitted_at":"2017-09-13T14:14:15Z","abstract_excerpt":"How to effectively approximate real-valued parameters with binary codes plays a central role in neural network binarization. In this work, we reveal an important fact that binarizing different layers has a widely-varied effect on the compression ratio of network and the loss of performance. Based on this fact, we propose a novel and flexible neural network binarization method by introducing the concept of layer-wise priority which binarizes parameters in inverse order of their layer depth. In each training step, our method selects a specific network layer, minimizes the discrepancy between the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04344","kind":"arxiv","version":3},"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":"1709.04344","created_at":"2026-05-18T00:23:13.986465+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.04344v3","created_at":"2026-05-18T00:23:13.986465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04344","created_at":"2026-05-18T00:23:13.986465+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZXSUEZH6EXB","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZXSUEZH6EXBJ2EH","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZXSUEZH","created_at":"2026-05-18T12:31:59.375834+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/ZZXSUEZH6EXBJ2EHOETU2CB52J","json":"https://pith.science/pith/ZZXSUEZH6EXBJ2EHOETU2CB52J.json","graph_json":"https://pith.science/api/pith-number/ZZXSUEZH6EXBJ2EHOETU2CB52J/graph.json","events_json":"https://pith.science/api/pith-number/ZZXSUEZH6EXBJ2EHOETU2CB52J/events.json","paper":"https://pith.science/paper/ZZXSUEZH"},"agent_actions":{"view_html":"https://pith.science/pith/ZZXSUEZH6EXBJ2EHOETU2CB52J","download_json":"https://pith.science/pith/ZZXSUEZH6EXBJ2EHOETU2CB52J.json","view_paper":"https://pith.science/paper/ZZXSUEZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.04344&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZXSUEZH6EXBJ2EHOETU2CB52J/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZXSUEZH6EXBJ2EHOETU2CB52J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZXSUEZH6EXBJ2EHOETU2CB52J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZXSUEZH6EXBJ2EHOETU2CB52J/action/storage_attestation","attest_author":"https://pith.science/pith/ZZXSUEZH6EXBJ2EHOETU2CB52J/action/author_attestation","sign_citation":"https://pith.science/pith/ZZXSUEZH6EXBJ2EHOETU2CB52J/action/citation_signature","submit_replication":"https://pith.science/pith/ZZXSUEZH6EXBJ2EHOETU2CB52J/action/replication_record"}},"created_at":"2026-05-18T00:23:13.986465+00:00","updated_at":"2026-05-18T00:23:13.986465+00:00"}