ML theory library
PublishedA connected library of ML, statistics, probability, optimization, and frontier-model topics with prerequisites, examples, failure modes, exercises, and references.
Browse topicsProjects
TheoremPath is a graph-backed ML research learning system.
The public project is not one page or one app. It is the topic library, prerequisite graph, evidence ledger, learner loop, practice standard, and iOS companion moving through content-depth, learner-loop, evidence, and release gates.
Built and maintained by Robby Sneiderman. Last reviewed: July 29, 2026
Review the system
A short route through the implementation, its evidence limits, the formal work, and the live learner loop.
- 01System designRead how the graph, content records, diagnostics, and browser labs fit together.
- 02Evidence boundariesCheck which claims are source-backed, Lean-mapped, smoke-tested, or data-insufficient.
- 03Formal methodsInspect the public Lean declarations, proof scope, axioms, and pinned toolchain.
- 04Live learner loopRun the diagnostic that maps answers to skills and prerequisite gaps.
Reading paths
LiveText-first theorem trails for moving from foundations to frontier reading with claims, sources, and failure checks.
Open pathsEvidence dashboard
Live receiptsA public boundary page for source grounding, Lean mappings, diagnostic links, trail coverage, learner-loop receipts, and sparse calibration status.
Open evidencePractice standard
PublishedA standard for turning study into code, derivations, baselines, ablations, plots, paper maps, and short technical reports.
View standardDiagnostic and review loop
BetaSigned-in diagnostics, saved topics, review entry points, and profile state are wired. Effectiveness and item calibration still need more real learner data.
Run diagnosticLearner-loop and iOS continuity
Beta-approved buildVersion 1.1.0 build 4 is valid in App Store Connect and approved for external TestFlight. Tester rollout, privacy labels, listing verification, and source-to-build reconciliation remain release gates.
See receiptsFlagship ML pages
The current content work is centered on a small set of high-value ML pages. Each should connect theory, examples, failure modes, and evidence boundaries.
Evidence boundary
The project is strongest when each claim names its evidence type. Working software, source mappings, formal wrappers, and signed-in smoke receipts are different kinds of proof. They should not be blended into a single vague quality claim.
| Layer | Boundary |
|---|---|
| Implemented | Topic graph, governed claims, source locators, Q-matrix rows, diagnostic items, FSRS-style review state, signed-in state, saved topics, review endpoints, and iOS API continuity. |
| Measured today | Route coverage, production smoke receipts, learner-loop API reads/writes, proof-asset captures, and live sparse diagnostic rows. |
| Not claimed yet | Retention lift, calibrated IRT ability estimates, item discrimination, broad PFA effectiveness, causal mastery proof from the Q-matrix, or a public claim that every page is Lean verified. |
What comes next
The launch candidate should keep moving on content depth, evidence integrity, signed-in flows, iOS readiness, and a demo packet built from the real product.
- Collect enough real signed-in attempts for item calibration rather than fitting sparse data.
- Keep flagship ML pages source-backed with examples, failure modes, and diagrams.
- Re-run web and iOS signed-in continuity after auth, learner-state, or release-shell changes.
- Prepare a product demo packet from real screenshots and flows, not staged claims.