{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BPX74T5CGVHWU7Q2OIJMXGDCB3","short_pith_number":"pith:BPX74T5C","schema_version":"1.0","canonical_sha256":"0beffe4fa2354f6a7e1a7212cb98620ef4b5e598a13a9e1ae93448a750153119","source":{"kind":"arxiv","id":"2206.12794","version":1},"attestation_state":"computed","paper":{"title":"CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Steps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alberto A. Del Barrio, HyunJin Kim, Jungwoo Shin","submitted_at":"2022-06-26T05:54:12Z","abstract_excerpt":"This paper proposes a training method having multiple cyclic training for achieving enhanced performance in low-bit quantized convolutional neural networks (CNNs). Quantization is a popular method for obtaining lightweight CNNs, where the initialization with a pretrained model is widely used to overcome degraded performance in low-resolution quantization. However, large quantization errors between real values and their low-bit quantized ones cause difficulties in achieving acceptable performance for complex networks and large datasets. The proposed training method softly delivers the knowledge"},"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":"2206.12794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T05:54:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ca526239c1f1989bebfbc503d66c6259e1b9ccd3b9a54798fa06a3288151a9a7","abstract_canon_sha256":"c3d747219040f7c0b97fff1d5a789424c0527940f4aecfb1f8819e0942a35645"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:59.372715Z","signature_b64":"kuRnzx447HdTs4pdz2DjKH5rd/jgIxirhnHwM85/5/4iSZ2fjY+ee79mXSxWFLR8S8tOkgsFfk6IrCA08S+gDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0beffe4fa2354f6a7e1a7212cb98620ef4b5e598a13a9e1ae93448a750153119","last_reissued_at":"2026-07-05T04:34:59.372311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:59.372311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Steps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alberto A. Del Barrio, HyunJin Kim, Jungwoo Shin","submitted_at":"2022-06-26T05:54:12Z","abstract_excerpt":"This paper proposes a training method having multiple cyclic training for achieving enhanced performance in low-bit quantized convolutional neural networks (CNNs). Quantization is a popular method for obtaining lightweight CNNs, where the initialization with a pretrained model is widely used to overcome degraded performance in low-resolution quantization. However, large quantization errors between real values and their low-bit quantized ones cause difficulties in achieving acceptable performance for complex networks and large datasets. The proposed training method softly delivers the knowledge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12794","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/2206.12794/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":"2206.12794","created_at":"2026-07-05T04:34:59.372380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.12794v1","created_at":"2026-07-05T04:34:59.372380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12794","created_at":"2026-07-05T04:34:59.372380+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPX74T5CGVHW","created_at":"2026-07-05T04:34:59.372380+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPX74T5CGVHWU7Q2","created_at":"2026-07-05T04:34:59.372380+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPX74T5C","created_at":"2026-07-05T04:34:59.372380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16776","citing_title":"PQCAD-DM: Progressive Quantization and Calibration-Assisted Distillation for Extremely Efficient Diffusion Model","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BPX74T5CGVHWU7Q2OIJMXGDCB3","json":"https://pith.science/pith/BPX74T5CGVHWU7Q2OIJMXGDCB3.json","graph_json":"https://pith.science/api/pith-number/BPX74T5CGVHWU7Q2OIJMXGDCB3/graph.json","events_json":"https://pith.science/api/pith-number/BPX74T5CGVHWU7Q2OIJMXGDCB3/events.json","paper":"https://pith.science/paper/BPX74T5C"},"agent_actions":{"view_html":"https://pith.science/pith/BPX74T5CGVHWU7Q2OIJMXGDCB3","download_json":"https://pith.science/pith/BPX74T5CGVHWU7Q2OIJMXGDCB3.json","view_paper":"https://pith.science/paper/BPX74T5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.12794&json=true","fetch_graph":"https://pith.science/api/pith-number/BPX74T5CGVHWU7Q2OIJMXGDCB3/graph.json","fetch_events":"https://pith.science/api/pith-number/BPX74T5CGVHWU7Q2OIJMXGDCB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPX74T5CGVHWU7Q2OIJMXGDCB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPX74T5CGVHWU7Q2OIJMXGDCB3/action/storage_attestation","attest_author":"https://pith.science/pith/BPX74T5CGVHWU7Q2OIJMXGDCB3/action/author_attestation","sign_citation":"https://pith.science/pith/BPX74T5CGVHWU7Q2OIJMXGDCB3/action/citation_signature","submit_replication":"https://pith.science/pith/BPX74T5CGVHWU7Q2OIJMXGDCB3/action/replication_record"}},"created_at":"2026-07-05T04:34:59.372380+00:00","updated_at":"2026-07-05T04:34:59.372380+00:00"}