Keyboard shortcuts

Press ← or → to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Appendix: The SAITO Closed Learner-Loop

Source: the original AIDLE proposal’s own framing, reused here rather than redrawn. First appeared in ~/txt/aidle/2026-06-03-codip-saito-lab-setup.md (English) and ~/txt/aidle/2026-05-28-saito-uebersicht-de.md (the German version, same figure). Reproduced verbatim as a diagram, not reinterpreted.

flowchart LR
    WHO["<b>WHO</b><br/>is being asked?<br/><i>learner state</i><br/><i>over weeks-to-months</i>"]
    WHEN["<b>WHEN</b><br/>to ask?<br/><i>spacing, retrieval,</i><br/><i>transfer intervals</i>"]
    WHAT["<b>WHAT</b><br/>to ask?<br/><i>productive difficulty,</i><br/><i>scaffolded questions</i>"]
    L((Learner))

    WHO --> WHEN
    WHEN --> WHAT
    WHAT --> L
    L -- "interaction trace +<br/>outcome measurement<br/>weeks later" --> WHO

Fig. 1 — SAITO’s closed learner-loop. The three guiding questions aren’t parallel; they’re sequential and feedback-coupled: learner state (WHO) drives the right moment (WHEN), which produces the next scaffolded question (WHAT); the outcome signal weeks later updates WHO.

What each box actually is, and what SAIL has actually built

The original AIDLE proposal names three implementation components, one per question:

QuestionComponentWhat it isStatus in SAIL, as of this compendium
WHAT to askSSA — Socratic Scaffold AgentDecides what to say on a given turn: ask a generative question, or stay silentBuilt and live. This is sail-judge — the whole subject of the Bandit-Arm Design, Goodhart Taxonomy & GAT chapter.
WHO is being askedSTM — Skill Trajectory ModelA longitudinal model of a learner’s state — knowledge, metacognitive accuracy, position in their own skill development — over weeks to monthsNew territory, not built. Skill Trajectory Models is a scaffold stub, not a design.
WHEN to askTSS — Temporal Scaffolding SchedulerDecides the right moment for the next question, review, or transfer task — spacing and retrieval-practice timing over days/weeks, not within one exchangeNot started at all. No compendium section covers it yet. A cross-repo asset scan explicitly found “no precedent found anywhere” for TSS, the same greenfield status as GAT enforcement.

Worth being precise about what this appendix is and isn’t: it’s the original pathway, reused so readers have the same map the AIDLE proposal itself used — not a claim that SAIL has built, or is currently building, all three legs. Right now, exactly one of three is real. The loop’s own feedback arrow — “interaction trace + outcome measurement weeks later” — is itself SAITO’s central bet (measurable capability gain, not immediate helpfulness), and is the thing the pre-registered mini-study (sail-1uq0) exists to actually measure, once it runs.