---
title: "In the Effective Rank metric, regular MTP training collapsed the output matrix from 496 to 131,… — post author — DecisionGateway"
description: "statement by post author, recorded 2026-11-05 — verbatim quote and source citation."
canonical_url: "https://dgw.tmarket.io/claims/01a1e1ee-cad6-7a16-a096-11c8854a7260"
meta:
  "og:description": "statement by post author, recorded 2026-11-05 — verbatim quote and source citation."
  "og:image": "https://dgw.tmarket.io/og.jpg"
  "og:image:alt": "White network of connected nodes crossed by a timeline on black"
  "og:image:height": "1024"
  "og:image:width": "1024"
  "og:title": "In the Effective Rank metric, regular MTP training collapsed the output matrix from 496 to 131,… — post author — DecisionGateway"
  "twitter:image": "https://dgw.tmarket.io/og.jpg"
---

> Index of every page on this site: [llms.txt](https://dgw.tmarket.io/llms.txt)

statementSaid on 2026-11-05

# **In the Effective Rank metric, regular MTP training collapsed the output matrix from 496 to 131, while Soft-MTP kept it high and stable at 437.**

A statement by post author, said on 2026-11-05. Statements are as reported by the cited publishers — not verified by DecisionGateway.

> *במדד דרגה אפקטיבית (Effective Rank) שבודק כמה ממדים במטריצה באמת פעילים, אימון MTP רגיל ריסק את המטריצה מ-496 ל-131 (קריסת ממדים מפוארת), בעוד ש-Soft-MTP שמר אותה גבוהה ויציבה על 437.*

mathyaiwithmikePublished 2026-11-05 [ Read source](https://t.me/mathyaiwithmike/1302)

## **Discussion**

## **Related claims**

[**If you train models with MTP architecture, stop injecting noisy CE gradients and instead add the Soft-MTP line of code.**מייק · commitment](https://dgw.tmarket.io/claims/01a1e1ee-4898-7ced-9f43-9f192a44b50c) [**When decomposing the standard MTP gradient (trained with standard Cross-Entropy), two opposing forces are hidden inside: a useful self-distillation signal and a residual noise component.**post author · statement](https://dgw.tmarket.io/claims/01a1e1ee-c9b5-7ec8-958e-20cbda9fe423) [**MTP not only improves performance in math and code, but also provides built-in draft heads for inference acceleration via Speculative Decoding.**post author · statement](https://dgw.tmarket.io/claims/01a1e1ee-c8fd-7400-9123-603ba0e22ca1) [**MIT researchers discovered that despite everyone using MTP, no one noticed a built-in mathematical bug in the training process.**post author · investigation](https://dgw.tmarket.io/claims/01a1e1ee-c94e-7286-b56f-53a1d78ff717) [**Raising reasoning effort improves average benchmark scores but produces painful performance drops at the individual task level; tasks solved easily and cheaply at Low fail at High or xHigh.**החוקרים · investigation](https://dgw.tmarket.io/claims/01a1e1f0-c538-7447-9bb7-8a8e30295ed6) [**Large AI labs train models with MTP, but 80% of the gradient they backpropagate to the model is static noise that interferes with learning.**post author · allegation](https://dgw.tmarket.io/claims/01a1e1ee-c8cc-76f8-a0cf-fdc0d5c6fade)

[All claims](https://dgw.tmarket.io/claims)

```json
{"@context":"https://schema.org","@graph":[{"@id":"https://dgw.tmarket.io/#website","@type":"WebSite","description":"Decisions, events and falsifiable forecasts from 4,500+ Telegram channels — every claim cited. Read free.","name":"DecisionGateway","url":"https://dgw.tmarket.io/","publisher":{"@id":"https://dgw.tmarket.io/#identity"}},{"@id":"https://dgw.tmarket.io/claims/01a1e1ee-cad6-7a16-a096-11c8854a7260#webpage","@type":"WebPage","description":"statement by post author, recorded 2026-11-05 — verbatim quote and source citation.","name":"In the Effective Rank metric, regular MTP training collapsed the output matrix from 496 to 131,… — post author — DecisionGateway","url":"https://dgw.tmarket.io/claims/01a1e1ee-cad6-7a16-a096-11c8854a7260","breadcrumb":{"@id":"https://dgw.tmarket.io/claims/01a1e1ee-cad6-7a16-a096-11c8854a7260#breadcrumb"},"isPartOf":{"@id":"https://dgw.tmarket.io/#website"},"potentialAction":[{"@type":"ReadAction","target":["https://dgw.tmarket.io/claims/01a1e1ee-cad6-7a16-a096-11c8854a7260"]}]},{"@id":"https://dgw.tmarket.io/#identity","@type":"Organization","name":"DecisionGateway","url":"https://dgw.tmarket.io"},{"@id":"https://dgw.tmarket.io/claims/01a1e1ee-cad6-7a16-a096-11c8854a7260#breadcrumb","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","name":"Home","item":"https://dgw.tmarket.io","position":1},{"@type":"ListItem","name":"Claims","item":"https://dgw.tmarket.io/claims","position":2},{"@type":"ListItem","name":"In the Effective Rank metric, regular MTP training…","position":3}]},{"@id":"https://dgw.tmarket.io/claims/01a1e1ee-cad6-7a16-a096-11c8854a7260#/schema/quotation/1","@type":"Quotation","dateCreated":"2026-11-05","isBasedOn":"https://t.me/mathyaiwithmike/1302","text":"במדד דרגה אפקטיבית (Effective Rank) שבודק כמה ממדים במטריצה באמת פעילים, אימון MTP רגיל ריסק את המטריצה מ-496 ל-131 (קריסת ממדים מפוארת), בעוד ש-Soft-MTP שמר אותה גבוהה ויציבה על 437.","url":"/claims/01a1e1ee-cad6-7a16-a096-11c8854a7260"}]}
```

## Sitemap

See the full [sitemap](https://dgw.tmarket.io/sitemap.md) for all pages.
