{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EIC2GHPTBGT5FG5O4LPBJ6YC42","short_pith_number":"pith:EIC2GHPT","schema_version":"1.0","canonical_sha256":"2205a31df309a7d29baee2de14fb02e6b994c001f81c4739abbb3675b6832092","source":{"kind":"arxiv","id":"2206.04459","version":3},"attestation_state":"computed","paper":{"title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Eric Xing, Jeffry Wicaksana, Kwang-Ting Cheng, Shichao Li, Xianghong Hu, Xijie Huang, Zechun Liu, Zhiqiang Shen","submitted_at":"2022-06-09T12:38:18Z","abstract_excerpt":"In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports mixed bitwidth arithmetic operations, recent research on mixed precision quantization (MPQ) begins to fully leverage the capacity of representation by searching optimized bitwidths for different layers and modules in a network. However, previous studies mainly search the MPQ strategy in a costly scheme using reinforcement learning, neural architecture search, etc., or simply utilize partial prior knowledge for bitwidth assignm"},"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":"2206.04459","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T12:38:18Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"427c22dd22599dd11ff65452ce3eac279fe094dd77533ef32f61d760a1f8b23a","abstract_canon_sha256":"d6a4d40f88b3d860763c842cde9031f648d7dc9b1b58fd9fe9c84379f4b708c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:52.997709Z","signature_b64":"APx87mHat6MH4zYb8aEifFi9XHEAGFFe9ArZJjpsYVE5/cDEDkWTc673yEucx/hQuxzmqGa+XPIFtyvs45wABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2205a31df309a7d29baee2de14fb02e6b994c001f81c4739abbb3675b6832092","last_reissued_at":"2026-07-05T04:38:52.997258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:52.997258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Eric Xing, Jeffry Wicaksana, Kwang-Ting Cheng, Shichao Li, Xianghong Hu, Xijie Huang, Zechun Liu, Zhiqiang Shen","submitted_at":"2022-06-09T12:38:18Z","abstract_excerpt":"In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports mixed bitwidth arithmetic operations, recent research on mixed precision quantization (MPQ) begins to fully leverage the capacity of representation by searching optimized bitwidths for different layers and modules in a network. However, previous studies mainly search the MPQ strategy in a costly scheme using reinforcement learning, neural architecture search, etc., or simply utilize partial prior knowledge for bitwidth assignm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04459","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/2206.04459/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":"2206.04459","created_at":"2026-07-05T04:38:52.997324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04459v3","created_at":"2026-07-05T04:38:52.997324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04459","created_at":"2026-07-05T04:38:52.997324+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIC2GHPTBGT5","created_at":"2026-07-05T04:38:52.997324+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIC2GHPTBGT5FG5O","created_at":"2026-07-05T04:38:52.997324+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIC2GHPT","created_at":"2026-07-05T04:38:52.997324+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/EIC2GHPTBGT5FG5O4LPBJ6YC42","json":"https://pith.science/pith/EIC2GHPTBGT5FG5O4LPBJ6YC42.json","graph_json":"https://pith.science/api/pith-number/EIC2GHPTBGT5FG5O4LPBJ6YC42/graph.json","events_json":"https://pith.science/api/pith-number/EIC2GHPTBGT5FG5O4LPBJ6YC42/events.json","paper":"https://pith.science/paper/EIC2GHPT"},"agent_actions":{"view_html":"https://pith.science/pith/EIC2GHPTBGT5FG5O4LPBJ6YC42","download_json":"https://pith.science/pith/EIC2GHPTBGT5FG5O4LPBJ6YC42.json","view_paper":"https://pith.science/paper/EIC2GHPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04459&json=true","fetch_graph":"https://pith.science/api/pith-number/EIC2GHPTBGT5FG5O4LPBJ6YC42/graph.json","fetch_events":"https://pith.science/api/pith-number/EIC2GHPTBGT5FG5O4LPBJ6YC42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIC2GHPTBGT5FG5O4LPBJ6YC42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIC2GHPTBGT5FG5O4LPBJ6YC42/action/storage_attestation","attest_author":"https://pith.science/pith/EIC2GHPTBGT5FG5O4LPBJ6YC42/action/author_attestation","sign_citation":"https://pith.science/pith/EIC2GHPTBGT5FG5O4LPBJ6YC42/action/citation_signature","submit_replication":"https://pith.science/pith/EIC2GHPTBGT5FG5O4LPBJ6YC42/action/replication_record"}},"created_at":"2026-07-05T04:38:52.997324+00:00","updated_at":"2026-07-05T04:38:52.997324+00:00"}