{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3NUNWIRPB5LDPNPYOEDPDTBUVG","short_pith_number":"pith:3NUNWIRP","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"},"canonical_sha256":"db68db222f0f5637b5f87106f1cc34a99b50c314a19da4a82551788a78fd1271","source":{"kind":"arxiv","id":"2507.22349","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22349","created_at":"2026-07-05T11:45:39Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22349v1","created_at":"2026-07-05T11:45:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22349","created_at":"2026-07-05T11:45:39Z"},{"alias_kind":"pith_short_12","alias_value":"3NUNWIRPB5LD","created_at":"2026-07-05T11:45:39Z"},{"alias_kind":"pith_short_16","alias_value":"3NUNWIRPB5LDPNPY","created_at":"2026-07-05T11:45:39Z"},{"alias_kind":"pith_short_8","alias_value":"3NUNWIRP","created_at":"2026-07-05T11:45:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3NUNWIRPB5LDPNPYOEDPDTBUVG","target":"record","payload":{"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"},"canonical_sha256":"db68db222f0f5637b5f87106f1cc34a99b50c314a19da4a82551788a78fd1271","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"},"source_kind":"arxiv","source_id":"2507.22349","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:45:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AmBu69jBX410XP+8Y3U3PRK0KTC5n8pKuPOdpagh51OK1AeLcki1TUlrF0dcoDnT4JnBDcwYa2UUPSOL677rBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:29:33.867486Z"},"content_sha256":"36f384996c70ff28342c481e44bd3367833d8f1ada1bb7633efe867ce0192342","schema_version":"1.0","event_id":"sha256:36f384996c70ff28342c481e44bd3367833d8f1ada1bb7633efe867ce0192342"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3NUNWIRPB5LDPNPYOEDPDTBUVG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:45:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dm4piivjEXMA7yVynUdwSwZM81dn5ubZR1zOT4SDPysT7jXcNX1RxfZ1JCvqUHqnbqrJvH2LXsSsZ0aVMFSjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:29:33.867998Z"},"content_sha256":"89d721f13158c930769594d8cb249f3042ae94bdc8bd11d7c3c3128ac188034b","schema_version":"1.0","event_id":"sha256:89d721f13158c930769594d8cb249f3042ae94bdc8bd11d7c3c3128ac188034b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG/bundle.json","state_url":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T16:29:33Z","links":{"resolver":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG","bundle":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG/bundle.json","state":"https://pith.science/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3NUNWIRPB5LDPNPYOEDPDTBUVG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3NUNWIRPB5LDPNPYOEDPDTBUVG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5f602c9f89ceb54f10101f58136b864904a5fdd41ecbb77e67ffe3ccc5cf9265","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T03:21:29Z","title_canon_sha256":"15e69f1e3139a9bd3dceb77183030111e61e07a86aca2cddc21a2b1dfdf7a5ca"},"schema_version":"1.0","source":{"id":"2507.22349","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22349","created_at":"2026-07-05T11:45:39Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22349v1","created_at":"2026-07-05T11:45:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22349","created_at":"2026-07-05T11:45:39Z"},{"alias_kind":"pith_short_12","alias_value":"3NUNWIRPB5LD","created_at":"2026-07-05T11:45:39Z"},{"alias_kind":"pith_short_16","alias_value":"3NUNWIRPB5LDPNPY","created_at":"2026-07-05T11:45:39Z"},{"alias_kind":"pith_short_8","alias_value":"3NUNWIRP","created_at":"2026-07-05T11:45:39Z"}],"graph_snapshots":[{"event_id":"sha256:89d721f13158c930769594d8cb249f3042ae94bdc8bd11d7c3c3128ac188034b","target":"graph","created_at":"2026-07-05T11:45:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.22349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongwei Wang, Huanrui Yang, Jinhee Kim, Jong Hwan Ko, Kang Eun Jeon, Seokho Han, Seoyeon Yoon","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T03:21:29Z","title":"MSQ: Memory-Efficient Bit Sparsification Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22349","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:36f384996c70ff28342c481e44bd3367833d8f1ada1bb7633efe867ce0192342","target":"record","created_at":"2026-07-05T11:45:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5f602c9f89ceb54f10101f58136b864904a5fdd41ecbb77e67ffe3ccc5cf9265","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T03:21:29Z","title_canon_sha256":"15e69f1e3139a9bd3dceb77183030111e61e07a86aca2cddc21a2b1dfdf7a5ca"},"schema_version":"1.0","source":{"id":"2507.22349","kind":"arxiv","version":1}},"canonical_sha256":"db68db222f0f5637b5f87106f1cc34a99b50c314a19da4a82551788a78fd1271","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db68db222f0f5637b5f87106f1cc34a99b50c314a19da4a82551788a78fd1271","first_computed_at":"2026-07-05T11:45:39.689608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:39.689608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DkliPId6rLJQUB8k9JKV+5YfNgjggFEt87qQr2L8oAb7/jbuNXpTyltT0+iYF7IpTqlg3e0PJ0/xZ5WRix+fAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:39.690076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22349","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36f384996c70ff28342c481e44bd3367833d8f1ada1bb7633efe867ce0192342","sha256:89d721f13158c930769594d8cb249f3042ae94bdc8bd11d7c3c3128ac188034b"],"state_sha256":"b93d901f7f76bb952a4735332e202af720c9c1d666b2308f3e153dd0c4b0b650"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qToT+pa4OYKDPHTKX4nN6PeP+dFpkro2lllhhMip3sk7q7hpOsP1L2tvkv9NvtQ8V4JJV/kLCIhNeM9kiAyEAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:29:33.872754Z","bundle_sha256":"5989dec788814a8e05549d1633dbbc1e36c97148bdaedbbac7924f892ca0c022"}}