{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3NUNWIRPB5LDPNPYOEDPDTBUVG","short_pith_number":"pith:3NUNWIRP","schema_version":"1.0","canonical_sha256":"db68db222f0f5637b5f87106f1cc34a99b50c314a19da4a82551788a78fd1271","source":{"kind":"arxiv","id":"2507.22349","version":1},"attestation_state":"computed","paper":{"title":"MSQ: Memory-Efficient Bit Sparsification Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongwei Wang, Huanrui Yang, Jinhee Kim, Jong Hwan Ko, Kang Eun Jeon, Seokho Han, Seoyeon Yoon","submitted_at":"2025-07-30T03:21:29Z","abstract_excerpt":"As deep neural networks (DNNs) see increased deployment on mobile and edge devices, optimizing model efficiency has become crucial. Mixed-precision quantization is widely favored, as it offers a superior balance between efficiency and accuracy compared to uniform quantization. However, finding the optimal precision for each layer is challenging. Recent studies utilizing bit-level sparsity have shown promise, yet they often introduce substantial training complexity and high GPU memory requirements. In this paper, we propose Memory-Efficient Bit Sparsification Quantization (MSQ), a novel approac"},"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":"2507.22349","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T03:21:29Z","cross_cats_sorted":[],"title_canon_sha256":"15e69f1e3139a9bd3dceb77183030111e61e07a86aca2cddc21a2b1dfdf7a5ca","abstract_canon_sha256":"5f602c9f89ceb54f10101f58136b864904a5fdd41ecbb77e67ffe3ccc5cf9265"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:39.690076Z","signature_b64":"DkliPId6rLJQUB8k9JKV+5YfNgjggFEt87qQr2L8oAb7/jbuNXpTyltT0+iYF7IpTqlg3e0PJ0/xZ5WRix+fAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db68db222f0f5637b5f87106f1cc34a99b50c314a19da4a82551788a78fd1271","last_reissued_at":"2026-07-05T11:45:39.689608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:39.689608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSQ: Memory-Efficient Bit Sparsification Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongwei Wang, Huanrui Yang, Jinhee Kim, Jong Hwan Ko, Kang Eun Jeon, Seokho Han, Seoyeon Yoon","submitted_at":"2025-07-30T03:21:29Z","abstract_excerpt":"As deep neural networks (DNNs) see increased deployment on mobile and edge devices, optimizing model efficiency has become crucial. Mixed-precision quantization is widely favored, as it offers a superior balance between efficiency and accuracy compared to uniform quantization. However, finding the optimal precision for each layer is challenging. Recent studies utilizing bit-level sparsity have shown promise, yet they often introduce substantial training complexity and high GPU memory requirements. In this paper, we propose Memory-Efficient Bit Sparsification Quantization (MSQ), a novel approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22349","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/2507.22349/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":"2507.22349","created_at":"2026-07-05T11:45:39.689667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22349v1","created_at":"2026-07-05T11:45:39.689667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22349","created_at":"2026-07-05T11:45:39.689667+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NUNWIRPB5LD","created_at":"2026-07-05T11:45:39.689667+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NUNWIRPB5LDPNPY","created_at":"2026-07-05T11:45:39.689667+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NUNWIRP","created_at":"2026-07-05T11:45:39.689667+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/3NUNWIRPB5LDPNPYOEDPDTBUVG","json":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG.json","graph_json":"https://pith.science/api/pith-number/3NUNWIRPB5LDPNPYOEDPDTBUVG/graph.json","events_json":"https://pith.science/api/pith-number/3NUNWIRPB5LDPNPYOEDPDTBUVG/events.json","paper":"https://pith.science/paper/3NUNWIRP"},"agent_actions":{"view_html":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG","download_json":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG.json","view_paper":"https://pith.science/paper/3NUNWIRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22349&json=true","fetch_graph":"https://pith.science/api/pith-number/3NUNWIRPB5LDPNPYOEDPDTBUVG/graph.json","fetch_events":"https://pith.science/api/pith-number/3NUNWIRPB5LDPNPYOEDPDTBUVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG/action/storage_attestation","attest_author":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG/action/author_attestation","sign_citation":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG/action/citation_signature","submit_replication":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG/action/replication_record"}},"created_at":"2026-07-05T11:45:39.689667+00:00","updated_at":"2026-07-05T11:45:39.689667+00:00"}