{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KE2G23X6VXCI522UUREEZDKSO6","short_pith_number":"pith:KE2G23X6","schema_version":"1.0","canonical_sha256":"51346d6efeadc48eeb54a4484c8d5277959c6adbb8b9a19a7deb5c4d0d6e7414","source":{"kind":"arxiv","id":"2208.14286","version":1},"attestation_state":"computed","paper":{"title":"ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Zhang, Cong Guo, Fan Yang, Jingwen Leng, Minyi Guo, Yuhao Zhu, Yunxin Liu, Zihan Liu","submitted_at":"2022-08-30T14:12:49Z","abstract_excerpt":"Quantization is a technique to reduce the computation and memory cost of DNN models, which are getting increasingly large. Existing quantization solutions use fixed-point integer or floating-point types, which have limited benefits, as both require more bits to maintain the accuracy of original models. On the other hand, variable-length quantization uses low-bit quantization for normal values and high-precision for a fraction of outlier values. Even though this line of work brings algorithmic benefits, it also introduces significant hardware overheads due to variable-length encoding and decodi"},"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":"2208.14286","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-30T14:12:49Z","cross_cats_sorted":[],"title_canon_sha256":"7c227d78d3ac91fbf024d0dd75eb90475c4aeb7e75eccf2d87906eff3f6e0f9c","abstract_canon_sha256":"6620bf130c7c674f65ffdb29964df94c8c0f676ef8096dec7d362227a330d85e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:10.733435Z","signature_b64":"Zef0LcblxAMiwwRs8qsOCdzpro8ydfPWSM4vLcAShR/4iUHpVrBRSMYilrcmDRPRlFRG/oZU2CWuqCrcUq5eBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51346d6efeadc48eeb54a4484c8d5277959c6adbb8b9a19a7deb5c4d0d6e7414","last_reissued_at":"2026-07-05T04:53:10.732950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:10.732950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Zhang, Cong Guo, Fan Yang, Jingwen Leng, Minyi Guo, Yuhao Zhu, Yunxin Liu, Zihan Liu","submitted_at":"2022-08-30T14:12:49Z","abstract_excerpt":"Quantization is a technique to reduce the computation and memory cost of DNN models, which are getting increasingly large. Existing quantization solutions use fixed-point integer or floating-point types, which have limited benefits, as both require more bits to maintain the accuracy of original models. On the other hand, variable-length quantization uses low-bit quantization for normal values and high-precision for a fraction of outlier values. Even though this line of work brings algorithmic benefits, it also introduces significant hardware overheads due to variable-length encoding and decodi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14286","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/2208.14286/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":"2208.14286","created_at":"2026-07-05T04:53:10.733010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.14286v1","created_at":"2026-07-05T04:53:10.733010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14286","created_at":"2026-07-05T04:53:10.733010+00:00"},{"alias_kind":"pith_short_12","alias_value":"KE2G23X6VXCI","created_at":"2026-07-05T04:53:10.733010+00:00"},{"alias_kind":"pith_short_16","alias_value":"KE2G23X6VXCI522U","created_at":"2026-07-05T04:53:10.733010+00:00"},{"alias_kind":"pith_short_8","alias_value":"KE2G23X6","created_at":"2026-07-05T04:53:10.733010+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/KE2G23X6VXCI522UUREEZDKSO6","json":"https://pith.science/pith/KE2G23X6VXCI522UUREEZDKSO6.json","graph_json":"https://pith.science/api/pith-number/KE2G23X6VXCI522UUREEZDKSO6/graph.json","events_json":"https://pith.science/api/pith-number/KE2G23X6VXCI522UUREEZDKSO6/events.json","paper":"https://pith.science/paper/KE2G23X6"},"agent_actions":{"view_html":"https://pith.science/pith/KE2G23X6VXCI522UUREEZDKSO6","download_json":"https://pith.science/pith/KE2G23X6VXCI522UUREEZDKSO6.json","view_paper":"https://pith.science/paper/KE2G23X6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.14286&json=true","fetch_graph":"https://pith.science/api/pith-number/KE2G23X6VXCI522UUREEZDKSO6/graph.json","fetch_events":"https://pith.science/api/pith-number/KE2G23X6VXCI522UUREEZDKSO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KE2G23X6VXCI522UUREEZDKSO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KE2G23X6VXCI522UUREEZDKSO6/action/storage_attestation","attest_author":"https://pith.science/pith/KE2G23X6VXCI522UUREEZDKSO6/action/author_attestation","sign_citation":"https://pith.science/pith/KE2G23X6VXCI522UUREEZDKSO6/action/citation_signature","submit_replication":"https://pith.science/pith/KE2G23X6VXCI522UUREEZDKSO6/action/replication_record"}},"created_at":"2026-07-05T04:53:10.733010+00:00","updated_at":"2026-07-05T04:53:10.733010+00:00"}