{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q6A7JRSAZFBU5PBU4DELPNJPF4","short_pith_number":"pith:Q6A7JRSA","schema_version":"1.0","canonical_sha256":"8781f4c640c9434ebc34e0c8b7b52f2f3e1fc0b4663c1edd982f09d4be728fde","source":{"kind":"arxiv","id":"2606.14187","version":2},"attestation_state":"computed","paper":{"title":"Zeta: Dual Whitening for Matrix Optimization via Coordinate-Adaptive Preconditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Kaiwen Chen, Linxiao Li, Mingkui Tan, Qiuwu Chen, Shuhai Zhang, Yifan Zhang, Ying Sun, Yuchen Li, Zimo Liu","submitted_at":"2026-06-12T07:10:17Z","abstract_excerpt":"Large-scale neural network training increasingly relies on matrix-aware optimizers that exploit the structure of weight parameters beyond element-wise adaptation. However, existing matrix-aware methods such as Muon have an underappreciated vulnerability: their core operation, Newton-Schulz iteration, depends critically on input conditioning, yet the raw momentum matrices exhibit severe coordinate-wise scale heterogeneity. In this paper, we first verify this scale heterogeneity through a chi-square uniformity test, showing that intra-matrix scale imbalance is prevalent across Transformer layers"},"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":"2606.14187","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-12T07:10:17Z","cross_cats_sorted":[],"title_canon_sha256":"eead7383afe4d5ea5fb957f2325c5c4e50c23e37b656d7cf2ec686d301551dac","abstract_canon_sha256":"64ace18a111423d74718aa8158af159bc1447268c5ac66e140a5ac535412a833"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:00.761709Z","signature_b64":"9IFDra4+EB8xgI5s1SCVIR49dsh2wQYUo+7togznVCeRlG2SWQxv0uhK/MserHcKJcMVPIuqGxL8ODtDmI3UBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8781f4c640c9434ebc34e0c8b7b52f2f3e1fc0b4663c1edd982f09d4be728fde","last_reissued_at":"2026-06-19T16:10:00.761367Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:00.761367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zeta: Dual Whitening for Matrix Optimization via Coordinate-Adaptive Preconditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Kaiwen Chen, Linxiao Li, Mingkui Tan, Qiuwu Chen, Shuhai Zhang, Yifan Zhang, Ying Sun, Yuchen Li, Zimo Liu","submitted_at":"2026-06-12T07:10:17Z","abstract_excerpt":"Large-scale neural network training increasingly relies on matrix-aware optimizers that exploit the structure of weight parameters beyond element-wise adaptation. However, existing matrix-aware methods such as Muon have an underappreciated vulnerability: their core operation, Newton-Schulz iteration, depends critically on input conditioning, yet the raw momentum matrices exhibit severe coordinate-wise scale heterogeneity. In this paper, we first verify this scale heterogeneity through a chi-square uniformity test, showing that intra-matrix scale imbalance is prevalent across Transformer layers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.14187","kind":"arxiv","version":2},"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/2606.14187/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":"2606.14187","created_at":"2026-06-19T16:10:00.761428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.14187v2","created_at":"2026-06-19T16:10:00.761428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.14187","created_at":"2026-06-19T16:10:00.761428+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6A7JRSAZFBU","created_at":"2026-06-19T16:10:00.761428+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6A7JRSAZFBU5PBU","created_at":"2026-06-19T16:10:00.761428+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6A7JRSA","created_at":"2026-06-19T16:10:00.761428+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/Q6A7JRSAZFBU5PBU4DELPNJPF4","json":"https://pith.science/pith/Q6A7JRSAZFBU5PBU4DELPNJPF4.json","graph_json":"https://pith.science/api/pith-number/Q6A7JRSAZFBU5PBU4DELPNJPF4/graph.json","events_json":"https://pith.science/api/pith-number/Q6A7JRSAZFBU5PBU4DELPNJPF4/events.json","paper":"https://pith.science/paper/Q6A7JRSA"},"agent_actions":{"view_html":"https://pith.science/pith/Q6A7JRSAZFBU5PBU4DELPNJPF4","download_json":"https://pith.science/pith/Q6A7JRSAZFBU5PBU4DELPNJPF4.json","view_paper":"https://pith.science/paper/Q6A7JRSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.14187&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6A7JRSAZFBU5PBU4DELPNJPF4/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6A7JRSAZFBU5PBU4DELPNJPF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6A7JRSAZFBU5PBU4DELPNJPF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6A7JRSAZFBU5PBU4DELPNJPF4/action/storage_attestation","attest_author":"https://pith.science/pith/Q6A7JRSAZFBU5PBU4DELPNJPF4/action/author_attestation","sign_citation":"https://pith.science/pith/Q6A7JRSAZFBU5PBU4DELPNJPF4/action/citation_signature","submit_replication":"https://pith.science/pith/Q6A7JRSAZFBU5PBU4DELPNJPF4/action/replication_record"}},"created_at":"2026-06-19T16:10:00.761428+00:00","updated_at":"2026-06-19T16:10:00.761428+00:00"}