{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JTCELKEJLJHS3FEFVTRRK34N25","short_pith_number":"pith:JTCELKEJ","canonical_record":{"source":{"id":"2507.09394","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-12T20:31:07Z","cross_cats_sorted":[],"title_canon_sha256":"c34a4357fd1b40678bdbed2fc75d7463434435f91b4fb1900c1dabc41329607b","abstract_canon_sha256":"6cacfdf61b04f91f85ba394298d22d1edb690af070641444b0399bcbeb8edb81"},"schema_version":"1.0"},"canonical_sha256":"4cc445a8895a4f2d9485ace3156f8dd7750db1929cbd9e2ea3088063b8d1f9b0","source":{"kind":"arxiv","id":"2507.09394","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09394","created_at":"2026-07-05T11:36:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09394v1","created_at":"2026-07-05T11:36:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09394","created_at":"2026-07-05T11:36:08Z"},{"alias_kind":"pith_short_12","alias_value":"JTCELKEJLJHS","created_at":"2026-07-05T11:36:08Z"},{"alias_kind":"pith_short_16","alias_value":"JTCELKEJLJHS3FEF","created_at":"2026-07-05T11:36:08Z"},{"alias_kind":"pith_short_8","alias_value":"JTCELKEJ","created_at":"2026-07-05T11:36:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JTCELKEJLJHS3FEFVTRRK34N25","target":"record","payload":{"canonical_record":{"source":{"id":"2507.09394","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-12T20:31:07Z","cross_cats_sorted":[],"title_canon_sha256":"c34a4357fd1b40678bdbed2fc75d7463434435f91b4fb1900c1dabc41329607b","abstract_canon_sha256":"6cacfdf61b04f91f85ba394298d22d1edb690af070641444b0399bcbeb8edb81"},"schema_version":"1.0"},"canonical_sha256":"4cc445a8895a4f2d9485ace3156f8dd7750db1929cbd9e2ea3088063b8d1f9b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:08.354509Z","signature_b64":"owWTUaC8r1y5KzS/js1Dsp03Gwf4CSIUB2j1Ea7sbJBb2cfqd102MFLGffvKIkQKhiHuRMKrOFLE3Me2uCdbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cc445a8895a4f2d9485ace3156f8dd7750db1929cbd9e2ea3088063b8d1f9b0","last_reissued_at":"2026-07-05T11:36:08.354030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:08.354030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.09394","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":"2026-07-05T11:36:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KhvKa7kCKzkbKKn7LmarrRU3rVt5STVJjB2gKwcYWKRX6NtnODt6pC86bgp7tV5eCq4RJfqwJCYLFiQN20KZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:08:34.269223Z"},"content_sha256":"46ef3165a96cb2fc9b078985cb1394c63e7ee25e8ba992f24a2fba3d164e0273","schema_version":"1.0","event_id":"sha256:46ef3165a96cb2fc9b078985cb1394c63e7ee25e8ba992f24a2fba3d164e0273"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JTCELKEJLJHS3FEFVTRRK34N25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Random Matrix Theory Perspective on the Learning Dynamics of Multi-head Latent Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brandon Reagen, Nandan Kumar Jha","submitted_at":"2025-07-12T20:31:07Z","abstract_excerpt":"In this work, we study how multi-head latent attention (MLA), a popular strategy for compressing key/value memory, affects a transformer's internal capacity during pretraining. Using a lightweight suite of Marchenko-Pastur (MP) diagnostics, we analyze the spectrum of the $W_{Q}W_{K}^\\top$ gram matrix throughout training, comparing three variants: the standard multi-head attention (MHA) baseline, MLA-PreRoPE with rotary applied before compression, and MLA-Decoupled, which shares a single rotary sub-vector across all heads. Our random matrix analysis reveals \\textbf{three key findings:} \\textbf{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09394","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/2507.09394/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":"2026-07-05T11:36:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7zpbuCzhoU2NpXOogGwUaT5BurFSFXtOXbijOdrCu6fWZWSJQ4YspFmFW62QC9xebL56Pm87HLvNNCnpMcXICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:08:34.269896Z"},"content_sha256":"a731193b3f7d0724bd27da96f7193074b99b777acb30da2527a48dc158deaacb","schema_version":"1.0","event_id":"sha256:a731193b3f7d0724bd27da96f7193074b99b777acb30da2527a48dc158deaacb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTCELKEJLJHS3FEFVTRRK34N25/bundle.json","state_url":"https://pith.science/pith/JTCELKEJLJHS3FEFVTRRK34N25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTCELKEJLJHS3FEFVTRRK34N25/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":"2026-08-22T07:08:34Z","links":{"resolver":"https://pith.science/pith/JTCELKEJLJHS3FEFVTRRK34N25","bundle":"https://pith.science/pith/JTCELKEJLJHS3FEFVTRRK34N25/bundle.json","state":"https://pith.science/pith/JTCELKEJLJHS3FEFVTRRK34N25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTCELKEJLJHS3FEFVTRRK34N25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JTCELKEJLJHS3FEFVTRRK34N25","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":"6cacfdf61b04f91f85ba394298d22d1edb690af070641444b0399bcbeb8edb81","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-12T20:31:07Z","title_canon_sha256":"c34a4357fd1b40678bdbed2fc75d7463434435f91b4fb1900c1dabc41329607b"},"schema_version":"1.0","source":{"id":"2507.09394","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09394","created_at":"2026-07-05T11:36:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09394v1","created_at":"2026-07-05T11:36:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09394","created_at":"2026-07-05T11:36:08Z"},{"alias_kind":"pith_short_12","alias_value":"JTCELKEJLJHS","created_at":"2026-07-05T11:36:08Z"},{"alias_kind":"pith_short_16","alias_value":"JTCELKEJLJHS3FEF","created_at":"2026-07-05T11:36:08Z"},{"alias_kind":"pith_short_8","alias_value":"JTCELKEJ","created_at":"2026-07-05T11:36:08Z"}],"graph_snapshots":[{"event_id":"sha256:a731193b3f7d0724bd27da96f7193074b99b777acb30da2527a48dc158deaacb","target":"graph","created_at":"2026-07-05T11:36:08Z","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/2507.09394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we study how multi-head latent attention (MLA), a popular strategy for compressing key/value memory, affects a transformer's internal capacity during pretraining. Using a lightweight suite of Marchenko-Pastur (MP) diagnostics, we analyze the spectrum of the $W_{Q}W_{K}^\\top$ gram matrix throughout training, comparing three variants: the standard multi-head attention (MHA) baseline, MLA-PreRoPE with rotary applied before compression, and MLA-Decoupled, which shares a single rotary sub-vector across all heads. Our random matrix analysis reveals \\textbf{three key findings:} \\textbf{","authors_text":"Brandon Reagen, Nandan Kumar Jha","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-12T20:31:07Z","title":"A Random Matrix Theory Perspective on the Learning Dynamics of Multi-head Latent Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09394","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":"sha256:46ef3165a96cb2fc9b078985cb1394c63e7ee25e8ba992f24a2fba3d164e0273","target":"record","created_at":"2026-07-05T11:36:08Z","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":"6cacfdf61b04f91f85ba394298d22d1edb690af070641444b0399bcbeb8edb81","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-12T20:31:07Z","title_canon_sha256":"c34a4357fd1b40678bdbed2fc75d7463434435f91b4fb1900c1dabc41329607b"},"schema_version":"1.0","source":{"id":"2507.09394","kind":"arxiv","version":1}},"canonical_sha256":"4cc445a8895a4f2d9485ace3156f8dd7750db1929cbd9e2ea3088063b8d1f9b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cc445a8895a4f2d9485ace3156f8dd7750db1929cbd9e2ea3088063b8d1f9b0","first_computed_at":"2026-07-05T11:36:08.354030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:08.354030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"owWTUaC8r1y5KzS/js1Dsp03Gwf4CSIUB2j1Ea7sbJBb2cfqd102MFLGffvKIkQKhiHuRMKrOFLE3Me2uCdbBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:08.354509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09394","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46ef3165a96cb2fc9b078985cb1394c63e7ee25e8ba992f24a2fba3d164e0273","sha256:a731193b3f7d0724bd27da96f7193074b99b777acb30da2527a48dc158deaacb"],"state_sha256":"fce3752a56e711e819ae145efea449be689849405d5782a58dc1e5958c802a4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yc5Z7NGNSsshaKoQBZGOc58DeG0XpIpmNMke17YpNv2LLMOxHtW0D7iQYA/p9+1L8/2sL8ZDmbOQ6cMzF0HpCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T07:08:34.274317Z","bundle_sha256":"fabe8bf058ccd09e118907c0f6e1c708c729b60ed07e976cff1d43e3206d0f4c"}}