{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PCUROFJ3NP2BXPM6BK2AMSCFQV","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":"048bf64fb3cae2100c666ac2543e088f5fb77258e21dfceb7c6df187d8ab69a9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T16:45:56Z","title_canon_sha256":"a3f0d08d59584d1d45999f076501f46bbf2b9074d9a494d614601bf5ccfb85d1"},"schema_version":"1.0","source":{"id":"2605.16165","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16165","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16165v1","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16165","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"pith_short_12","alias_value":"PCUROFJ3NP2B","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"pith_short_16","alias_value":"PCUROFJ3NP2BXPM6","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"pith_short_8","alias_value":"PCUROFJ3","created_at":"2026-05-20T00:01:55Z"}],"graph_snapshots":[{"event_id":"sha256:7611452832710f0e8185332565549a420194624bf8cbf081e35e1f556c62cb63","target":"graph","created_at":"2026-05-20T00:01:55Z","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":[{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T18:21:56.372264Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:31.034385Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"external_links","ran_at":"2026-05-19T17:31:47.003238Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.433531Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.16165/integrity.json","findings":[],"snapshot_sha256":"4db0a6308319809513b6898e8bfadcada9af9d88477a7e08bd265669a7bf624b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive next-token training offers a unified formulation for image generation and text understanding, but it also creates strong modality competition that destabilizes optimization and limits large-batch scaling. We show that first-order optimizers such as AdamW are vulnerable to cross-modality gradient heterogeneity, while second-order preconditioning, particularly SOAP, provides a more stable basis for multimodal alignment. Building on this insight, we propose \\emph{ML-FOP-SOAP}, a second-order optimization framework with Multi-Level Variance Correction. Our Fisher-Orthogonal Projecti","authors_text":"Wes Armour, Yishun Lu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T16:45:56Z","title":"Second-Order Multi-Level Variance Correction for Modality Competition in Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16165","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":"sha256:204842ee634c6515e67145bfbb0e1a2f1112103511bd7bd51d52b81bd4d12d8d","target":"record","created_at":"2026-05-20T00:01:55Z","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":"048bf64fb3cae2100c666ac2543e088f5fb77258e21dfceb7c6df187d8ab69a9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T16:45:56Z","title_canon_sha256":"a3f0d08d59584d1d45999f076501f46bbf2b9074d9a494d614601bf5ccfb85d1"},"schema_version":"1.0","source":{"id":"2605.16165","kind":"arxiv","version":1}},"canonical_sha256":"78a917153b6bf41bbd9e0ab4064845855d063da1352f286aef200709c7c6d198","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78a917153b6bf41bbd9e0ab4064845855d063da1352f286aef200709c7c6d198","first_computed_at":"2026-05-20T00:01:55.739517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:55.739517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jV/jNK4Jcu50C4j8KW5XkmNrKqzBpas93v/Qqd3DmrSVO90QFwLu5mD6fhcT+D4G0ubqahFGON7Nvd8likbCAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:55.740333Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16165","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:204842ee634c6515e67145bfbb0e1a2f1112103511bd7bd51d52b81bd4d12d8d","sha256:7611452832710f0e8185332565549a420194624bf8cbf081e35e1f556c62cb63"],"state_sha256":"70b56285821de73c6919462d030e3bedb30950d7973a1c4eec34bbdc92ce73cd"}