mikyo.one / IOTA / The Macrocosmos papers
The Macrocosmos papersFour papers · August 2024 to April 2026
Updated 29 Sep 2026
A reading list, explained

How Macrocosmos got from a contest to liquid training

These are all the research papers the Macrocosmos team has published, each explained for people who know AI models exist but have never looked at how one is built. Macrocosmos runs IOTA, the training network on Bittensor subnet 9, and calls its approach liquid training: one model trained across scattered, mismatched machines over the public internet.inferred

Read in order, three of the papers tell one story. In 2024, miners each trained a whole model and the best one was paid. In 2025, one model was split across many miners, each paid for their part. In 2026, the handoff between those miners was made small enough for ordinary internet links. The fourth paper is a side track on how to pay miners for work no one can score. Below, each one is laid out as its first page, annotated.

statedthe paper says itinferredmy arithmetic or reading of the paper

The desk · four first pages, in the order they were written

Pick a page, swipe, or use ← and →

    Who cites whom

    From each paper's reference list · hover or tap a node

    cites a team papercites an outside workrelated, not in the reference list
    Papers
    4every one Macrocosmos listsstated
    On arXiv
    2the others self-publishedstated
    Span
    20 monthsAug 2024 to Apr 2026inferred
    Named authors
    7Cruz on all three that name peopleinferred
    Compression reached
    128xprimer and ResBM, counted differentlystated
    All four as a table · newest first
    PaperDateAuthorsIn one lineWhat it gave IOTA and OrionFull text
    ResBM: Residual Bottleneck Models for Low-Bandwidth Pipeline Parallelism13 Apr 2026Aboudib, Lopez Portillo A., Brady, CruzA learned encoder and decoder at each pipeline boundary shrink the handoff 128x while the residual path stays intact.The compression block behind the Orion runs; Orion-100B used it at 64x.statedarXiv 2604.11947Read →
    Generative Adversarial Mining on Decentralized Networks9 Jan 2026Quinque, Brady, CruzPay miners for quality no one can score, by making them guess whether a miner or the validator wrote each answer.Nothing directly: it is the pay rule for Apex, subnet 1. It describes IOTA as "code attestation".Wayback copyRead →
    Incentivised Orchestrated Training Architecture (IOTA): A Technical Primer for Release16 Jul 2025Quinque, Aboudib, Fonau, Lopez Portillo Alcocer, McCrindle, CruzOne model split across many miners, paid per verified backward pass, merged by butterfly all-reduce.The architecture itself: orchestrator, pay rule, merge, and the first bottleneck block.statedarXiv 2507.17766Read →
    LLM Pretraining: The Use-Case Blockchain Has Been Waiting For?Aug 2024Macrocosmos, Taoverse, Const, Datura (no individuals named)Subnet 9 as a winner-takes-all contest in which each miner pretrains a whole model, up to 7B.The starting point: the primer cites it as reference [1] and names its two flaws.statedmacrocosmos.ai PDFRead →

    Where to start

    New to how models are trained: start with ResBM. Its first chapter explains pretraining, the training loop and pipeline parallelism from scratch, and the other pages link back to it.

    Following IOTA's history: read the training line in order, SN9, then the primer, then ResBM, then the runs in the Orion Register.

    Interested in incentive design: Generative Adversarial Mining stands on its own.

    How this list was made

    A paper is included if Macrocosmos is its affiliation. The four here are exactly the four in the Research menu on macrocosmos.ai, checked on 29 September 2026 against arXiv searches for each author, an arXiv full-text search for "Macrocosmos", and Semantic Scholar.stated

    The first pages above are drawn, not scanned: titles, authors and affiliations are the papers' own; each abstract is paraphrased in my words, and the grey lines stand in for body text. The citation map reads each paper's reference list.

    Every explainer was written from the full text. Corrections to connect@mikyo.one.