{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XHQI52IP65PAO4MUYCCHDPZXTB","short_pith_number":"pith:XHQI52IP","schema_version":"1.0","canonical_sha256":"b9e08ee90ff75e077194c08471bf37986ec9cfb163554f01686b8fe311ccff13","source":{"kind":"arxiv","id":"2608.09417","version":1},"attestation_state":"computed","paper":{"title":"A Mechanistic Diagnostic of Rank Collapse in Post-Norm Decoder Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qingyu Han, Xiaodong Luo, Xingjian Wang, Yin Zhang","submitted_at":"2026-08-10T10:45:16Z","abstract_excerpt":"Deep decoder-only Transformers often replace the original Post-Norm architecture with Pre-Norm variants because Post-Norm training is highly sensitive to warmup and learning rate under conventional initialization schemes. Although prior work has identified rank collapse and gradient vanishing as related symptoms, it remains poorly understood how causal attention creates high-similarity representations and why training dynamics fail to repair them. We give a two-stage analysis of Post-Norm rank collapse using token similarity as a scalar state variable. First, at initialization, causal attentio"},"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":"2608.09417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T10:45:16Z","cross_cats_sorted":[],"title_canon_sha256":"e800c0490cc4469f854aaa63f86d6f8692ea9f4683d7a87b9c0c231878baf88b","abstract_canon_sha256":"9d36e6064d9e308f95e07b103c8920485516aed31207285327920bb8c42ee668"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:22:33.848098Z","signature_b64":"lJao/Wjd2K2Em5y3k9N2wnBwMuLQKBHBbSS6J3+U8FlFA3wsg2JNObZxtcufpxZGmE/yHUysMTC7d/6SLqh1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9e08ee90ff75e077194c08471bf37986ec9cfb163554f01686b8fe311ccff13","last_reissued_at":"2026-08-11T02:22:33.845902Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:22:33.845902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Mechanistic Diagnostic of Rank Collapse in Post-Norm Decoder Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qingyu Han, Xiaodong Luo, Xingjian Wang, Yin Zhang","submitted_at":"2026-08-10T10:45:16Z","abstract_excerpt":"Deep decoder-only Transformers often replace the original Post-Norm architecture with Pre-Norm variants because Post-Norm training is highly sensitive to warmup and learning rate under conventional initialization schemes. Although prior work has identified rank collapse and gradient vanishing as related symptoms, it remains poorly understood how causal attention creates high-similarity representations and why training dynamics fail to repair them. We give a two-stage analysis of Post-Norm rank collapse using token similarity as a scalar state variable. First, at initialization, causal attentio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09417","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/2608.09417/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":"2608.09417","created_at":"2026-08-11T02:22:33.846967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09417v1","created_at":"2026-08-11T02:22:33.846967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09417","created_at":"2026-08-11T02:22:33.846967+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHQI52IP65PA","created_at":"2026-08-11T02:22:33.846967+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHQI52IP65PAO4MU","created_at":"2026-08-11T02:22:33.846967+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHQI52IP","created_at":"2026-08-11T02:22:33.846967+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/XHQI52IP65PAO4MUYCCHDPZXTB","json":"https://pith.science/pith/XHQI52IP65PAO4MUYCCHDPZXTB.json","graph_json":"https://pith.science/api/pith-number/XHQI52IP65PAO4MUYCCHDPZXTB/graph.json","events_json":"https://pith.science/api/pith-number/XHQI52IP65PAO4MUYCCHDPZXTB/events.json","paper":"https://pith.science/paper/XHQI52IP"},"agent_actions":{"view_html":"https://pith.science/pith/XHQI52IP65PAO4MUYCCHDPZXTB","download_json":"https://pith.science/pith/XHQI52IP65PAO4MUYCCHDPZXTB.json","view_paper":"https://pith.science/paper/XHQI52IP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09417&json=true","fetch_graph":"https://pith.science/api/pith-number/XHQI52IP65PAO4MUYCCHDPZXTB/graph.json","fetch_events":"https://pith.science/api/pith-number/XHQI52IP65PAO4MUYCCHDPZXTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHQI52IP65PAO4MUYCCHDPZXTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHQI52IP65PAO4MUYCCHDPZXTB/action/storage_attestation","attest_author":"https://pith.science/pith/XHQI52IP65PAO4MUYCCHDPZXTB/action/author_attestation","sign_citation":"https://pith.science/pith/XHQI52IP65PAO4MUYCCHDPZXTB/action/citation_signature","submit_replication":"https://pith.science/pith/XHQI52IP65PAO4MUYCCHDPZXTB/action/replication_record"}},"created_at":"2026-08-11T02:22:33.846967+00:00","updated_at":"2026-08-11T02:22:33.846967+00:00"}