{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SXMJKKYOAM5ZO2ZLCAGWWAZQWU","short_pith_number":"pith:SXMJKKYO","schema_version":"1.0","canonical_sha256":"95d8952b0e033b976b2b100d6b0330b50ae14c43067ac47a87c9c0ce10046d2d","source":{"kind":"arxiv","id":"1908.04680","version":3},"attestation_state":"computed","paper":{"title":"Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations","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, Jing Liu, Lingqiao Liu, Mingkui Tan","submitted_at":"2019-08-10T11:48:55Z","abstract_excerpt":"This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may result in substantial accuracy loss. To address this, we propose three practical approaches, including (i) progressive quantization; (ii) stochastic precision; and (iii) joint knowledge distillation to improve the network training. First, for progressive quantization, we propose two schemes to progressively find good local minima. Specifically, we propose t"},"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":"1908.04680","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-08-10T11:48:55Z","cross_cats_sorted":[],"title_canon_sha256":"162d0a54505f4ff7f0f347159c6b135a36647e40fbb1d0356b303052da307645","abstract_canon_sha256":"cbfd25ceb5cbbc03e5ec446bcaef9bfe6955e9c9865728efbd8e6ee5e6046376"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:07.661475Z","signature_b64":"40jmp2QbhAuo3RfwlUSmK+FEHy9NxLwUSuDaZMSjci4lbk9PatDi211ekUmV10mmKJcvMV39TLfOh/rirSpTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95d8952b0e033b976b2b100d6b0330b50ae14c43067ac47a87c9c0ce10046d2d","last_reissued_at":"2026-07-05T02:46:07.660950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:07.660950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations","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, Jing Liu, Lingqiao Liu, Mingkui Tan","submitted_at":"2019-08-10T11:48:55Z","abstract_excerpt":"This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may result in substantial accuracy loss. To address this, we propose three practical approaches, including (i) progressive quantization; (ii) stochastic precision; and (iii) joint knowledge distillation to improve the network training. First, for progressive quantization, we propose two schemes to progressively find good local minima. Specifically, we propose t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04680","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.04680/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":"1908.04680","created_at":"2026-07-05T02:46:07.661011+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04680v3","created_at":"2026-07-05T02:46:07.661011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04680","created_at":"2026-07-05T02:46:07.661011+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXMJKKYOAM5Z","created_at":"2026-07-05T02:46:07.661011+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXMJKKYOAM5ZO2ZL","created_at":"2026-07-05T02:46:07.661011+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXMJKKYO","created_at":"2026-07-05T02:46:07.661011+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/SXMJKKYOAM5ZO2ZLCAGWWAZQWU","json":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU.json","graph_json":"https://pith.science/api/pith-number/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/graph.json","events_json":"https://pith.science/api/pith-number/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/events.json","paper":"https://pith.science/paper/SXMJKKYO"},"agent_actions":{"view_html":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU","download_json":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU.json","view_paper":"https://pith.science/paper/SXMJKKYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04680&json=true","fetch_graph":"https://pith.science/api/pith-number/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/graph.json","fetch_events":"https://pith.science/api/pith-number/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/action/storage_attestation","attest_author":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/action/author_attestation","sign_citation":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/action/citation_signature","submit_replication":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/action/replication_record"}},"created_at":"2026-07-05T02:46:07.661011+00:00","updated_at":"2026-07-05T02:46:07.661011+00:00"}