claude-turing 2.4.0 → 3.0.0

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "turing",
-  "version": "2.4.0",
-  "description": "Autonomous ML research harness — the autoresearch loop as a formal protocol. 36 commands, 2 specialized agents, model composition (ensemble + pipeline stitch + warm-start), deep analysis (experiment diff + live training monitor + regression gate), experiment orchestration (batch queue + smart retry + branching), literature integration + paper drafting, production model export, performance profiling, smart checkpoints, experiment intelligence, statistical rigor, tree-search hypothesis exploration, cost-performance frontier, model cards, model registry, hypothesis database with novelty guard, anti-cheating guardrails, and the taste-leverage loop. Inspired by Karpathy's autoresearch and the scientific method itself.",
+  "version": "3.0.0",
+  "description": "Autonomous ML research harness — the autoresearch loop as a formal protocol. 41 commands, 2 specialized agents, meta-intelligence (cross-project knowledge transfer + methodology audit), scaling & efficiency (scaling laws + compute budget + model distillation), model composition (ensemble + pipeline stitch + warm-start), deep analysis (experiment diff + live training monitor + regression gate), experiment orchestration (batch queue + smart retry + branching), literature integration + paper drafting, production model export, performance profiling, smart checkpoints, experiment intelligence, statistical rigor, tree-search hypothesis exploration, cost-performance frontier, model cards, model registry, hypothesis database with novelty guard, anti-cheating guardrails, and the taste-leverage loop. Inspired by Karpathy's autoresearch and the scientific method itself.",
   "author": {
     "name": "pragnition"
   },

package/README.md

@@ -347,6 +347,11 @@ The index (`hypotheses.yaml`) is the lightweight queue. The detail files (`hypot
 | `/turing:ensemble [--top-k]` | Automated ensemble — voting, stacking, blending from top-K models |
 | `/turing:stitch <action>` | Pipeline composition — show, swap, cache, and run stages independently |
 | `/turing:warm <exp-id>` | Warm-start from prior model — load checkpoint, freeze layers, adjust LR |
+| `/turing:scale [--axis]` | Scaling law estimator — power-law fit, full-scale predictions, diminishing returns verdict |
+| `/turing:budget <action>` | Compute budget manager — set limits, track allocation, auto-shift explore/exploit |
+| `/turing:distill <exp-id>` | Model compression — distill teacher into smaller student with accuracy/size tradeoff |
+| `/turing:transfer [--from]` | Cross-project knowledge transfer — find similar projects, surface what worked |
+| `/turing:audit [--strict]` | Pre-submission methodology audit — data leakage, baselines, seeds, ablations, reproducibility |
 
 And for fully hands-off operation:
 
@@ -531,11 +536,11 @@ Each project gets independent config, data, experiments, models, and agent memor
 
 ## Architecture of Turing Itself
 
-36 commands, 2 agents, 10 config files, 55 template scripts, model registry, artifact contract, cost-performance frontier, model cards, tree-search exploration, statistical rigor, experiment intelligence, performance profiling, smart checkpoints, production model export, literature integration, paper section drafting, experiment orchestration (queue + retry + fork), deep analysis (diff + watch + regress), model composition (ensemble + stitch + warm), 16 ADRs. See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for the full codemap.
+41 commands, 2 agents, 10 config files, 60 template scripts, model registry, artifact contract, cost-performance frontier, model cards, tree-search exploration, statistical rigor, experiment intelligence, performance profiling, smart checkpoints, production model export, literature integration, paper section drafting, experiment orchestration (queue + retry + fork), deep analysis (diff + watch + regress), model composition (ensemble + stitch + warm), scaling & efficiency (scale + budget + distill), meta-intelligence (transfer + audit), 16 ADRs. See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for the full codemap.
 
 ```
 turing/
-├── commands/              35 skill files (core + taste-leverage + reporting + exploration + statistical rigor + experiment intelligence + performance + deployment + research workflow + orchestration + deep analysis + model composition)
+├── commands/              40 skill files (core + taste-leverage + reporting + exploration + statistical rigor + experiment intelligence + performance + deployment + research workflow + orchestration + deep analysis + model composition + scaling & efficiency + meta-intelligence)
 ├── agents/                2 agents (researcher: read/write, evaluator: read-only)
 ├── config/                8 files (lifecycle, taxonomy, archetypes, novelty aliases)
 ├── templates/             Scaffolded into user projects by /turing:init

package/commands/audit.md

@@ -0,0 +1,56 @@
+---
+name: audit
+description: Pre-submission methodology audit — catch data leakage, missing baselines, cherry-picked seeds, and incomplete ablations before a reviewer does.
+disable-model-invocation: true
+argument-hint: "[--strict] [--checklist neurips]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+A reviewer checklist you run before submitting. Catches methodology mistakes that cause desk rejections.
+
+## Steps
+
+1. **Activate environment:**
+   ```bash
+   source .venv/bin/activate
+   ```
+
+2. **Parse arguments from `$ARGUMENTS`:**
+   - `--strict` — treat warnings as failures
+   - `--checklist neurips|icml|iclr` — add venue-specific checks
+   - `--json` — raw JSON output
+
+3. **Run methodology audit:**
+   ```bash
+   python scripts/methodology_audit.py $ARGUMENTS
+   ```
+
+4. **Checks performed:**
+   - **Data leakage** (critical): verify prepare.py/evaluate.py separation
+   - **CV strategy** (critical): verify appropriate cross-validation for data type
+   - **Seed sensitivity** (high): seed studies exist for best experiments
+   - **Ablation completeness** (high): ablation studies performed
+   - **Baseline comparison** (high): simple baselines in experiment log
+   - **Reproducibility** (high): best result successfully reproduced
+   - **Hyperparameter budget** (medium): total tuning cost documented
+   - **Regression stability** (medium): regression checks performed
+
+5. **Verdicts:**
+   - **PASS** — ready for submission
+   - **PASS (with warnings)** — address before submission
+   - **NEEDS WORK** — fix failures first
+   - **FAIL** — critical issues found
+
+6. **Actions:** each failure suggests the `/turing:` command to fix it
+
+7. **Venue checklists:** `--checklist neurips` adds NeurIPS-specific checks (broader impact, reproducibility checklist, code availability)
+
+8. **Saved output:** report in `experiments/audits/audit-YYYY-MM-DD.yaml`
+
+## Examples
+
+```
+/turing:audit                          # Standard audit
+/turing:audit --strict                 # Warnings become failures
+/turing:audit --checklist neurips      # NeurIPS submission checklist
+```

package/commands/budget.md

@@ -0,0 +1,52 @@
+---
+name: budget
+description: Compute budget manager — set experiment/time limits, track allocation across explore/exploit phases, auto-shift modes, hard stop.
+disable-model-invocation: true
+argument-hint: "<set|status|reset> [--experiments 50] [--hours 8]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Set a compute ceiling and let the system optimize within it. Prevents runaway experiment loops.
+
+## Steps
+
+1. **Activate environment:**
+   ```bash
+   source .venv/bin/activate
+   ```
+
+2. **Parse arguments from `$ARGUMENTS`:**
+   - First argument is action: `set`, `status`, `reset`, or `check`
+   - `--experiments 50` — max experiment count
+   - `--hours 8` — max wall-clock hours
+   - `--json` — raw JSON output
+
+3. **Run budget manager:**
+   ```bash
+   python scripts/budget_manager.py $ARGUMENTS
+   ```
+
+4. **Actions:**
+   - **set:** create a budget with experiment and/or time constraints
+   - **status:** show usage, burn rate, projected exhaustion, allocation breakdown
+   - **reset:** deactivate the current budget
+   - **check:** returns whether another experiment is allowed (used by `/turing:train`)
+
+5. **Budget allocation policy:**
+   - **0-50% budget:** EXPLORE — try diverse hypotheses
+   - **50-80% budget:** MIXED — explore promising, exploit best
+   - **80-100% budget:** EXPLOIT ONLY — refine the winner
+   - **100% budget:** HARD STOP — `/turing:train` refuses new experiments
+
+6. **Budget state** stored in `experiment_state.yaml` under the `budget` key.
+
+7. **If no budget exists:** `/turing:train` runs without limits.
+
+## Examples
+
+```
+/turing:budget set --experiments 50 --hours 8   # Set both constraints
+/turing:budget set --experiments 30             # Experiment count only
+/turing:budget status                           # Show usage and projections
+/turing:budget reset                            # Remove budget limits
+```

package/commands/distill.md

@@ -0,0 +1,56 @@
+---
+name: distill
+description: Model compression via distillation — train a smaller student model to match a larger teacher's predictions.
+disable-model-invocation: true
+argument-hint: "<teacher-exp-id> [--compression 4] [--method soft-labels]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Compress a large model into a smaller, faster one for production. Measures the accuracy/size/latency tradeoff.
+
+## Steps
+
+1. **Activate environment:**
+   ```bash
+   source .venv/bin/activate
+   ```
+
+2. **Parse arguments from `$ARGUMENTS`:**
+   - First argument is teacher experiment ID (required)
+   - `--compression 4` — compression ratio (default: 4x)
+   - `--method soft_labels|feature_matching|dataset_distillation` — distillation method
+   - `--target-latency 5` — auto-adjust compression to meet latency target (ms)
+   - `--json` — raw JSON output
+
+3. **Run distillation planner:**
+   ```bash
+   python scripts/model_distiller.py $ARGUMENTS
+   ```
+
+4. **Report includes:**
+   - Teacher model metrics
+   - Auto-selected student architecture (fewer trees/layers/width)
+   - Estimated size reduction and latency improvement
+   - Distillation configuration (temperature, alpha, loss function)
+   - Verdict: EXCELLENT / ACCEPTABLE / MARGINAL / TOO MUCH LOSS
+
+5. **Student selection by model type:**
+   - **Tree models:** fewer estimators, shallower depth
+   - **Neural networks:** fewer layers, narrower hidden dims
+   - **scikit-learn:** simpler model family (RandomForest → DecisionTree)
+
+6. **Distillation methods:**
+   - **soft_labels:** train on teacher's probability outputs with temperature scaling
+   - **feature_matching:** align intermediate representations (neural only)
+   - **dataset_distillation:** train on teacher-labeled synthetic data
+
+7. **Saved output:** report written to `experiments/distillations/distill-<exp-id>.yaml`
+
+## Examples
+
+```
+/turing:distill exp-042                              # 4x compression, soft labels
+/turing:distill exp-042 --compression 8              # Aggressive compression
+/turing:distill exp-042 --method feature_matching    # Neural feature alignment
+/turing:distill exp-042 --target-latency 5           # Meet 5ms latency target
+```

package/commands/scale.md

@@ -0,0 +1,55 @@
+---
+name: scale
+description: Scaling law estimator — run small experiments at different sizes, fit a power law, and predict full-scale performance before committing compute.
+disable-model-invocation: true
+argument-hint: "[--axis data|compute|params] [--points 4] [--analyze results.yaml]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Predict full-scale performance from a handful of small experiments. Answers "is it worth training on the full dataset?" in 30 minutes instead of 3 days.
+
+## Steps
+
+1. **Activate environment:**
+   ```bash
+   source .venv/bin/activate
+   ```
+
+2. **Parse arguments from `$ARGUMENTS`:**
+   - `--axis data|compute|params` — scaling axis (default: data)
+   - `--points 4` — number of scale points (default: 4)
+   - `--analyze results.yaml` — analyze existing results instead of planning
+   - `--plot` — include ASCII scaling plot
+   - `--json` — raw JSON output
+
+3. **Plan or analyze:**
+   - **Plan mode (default):** generates scale point configs to run
+     ```bash
+     python scripts/scaling_estimator.py --axis data --points 4
+     ```
+   - **Analyze mode:** fits power law to completed results
+     ```bash
+     python scripts/scaling_estimator.py --analyze experiments/scaling/results.yaml
+     ```
+
+4. **Scaling axes:**
+   - **data:** train on 10%, 25%, 50%, 75% of dataset
+   - **compute:** train for 10%, 25%, 50%, 75% of max epochs
+   - **params:** scale model size (fewer estimators, shallower depth)
+
+5. **After planning:** run each scale point experiment, record results in YAML, then use `--analyze` to fit the curve
+
+6. **Report includes:**
+   - Power law fit: `metric = a × n^b` with R²
+   - Predictions for 100%, 150%, 200% scale
+   - Verdict: DIMINISHING RETURNS / MARGINAL GAINS / WORTH SCALING
+
+7. **Saved output:** report written to `experiments/scaling/scale-YYYY-MM-DD.yaml`
+
+## Examples
+
+```
+/turing:scale                                  # Plan: data axis, 4 points
+/turing:scale --axis compute --points 3        # Plan: compute axis, 3 points
+/turing:scale --analyze results.yaml --plot    # Analyze with ASCII plot
+```

package/commands/transfer.md

@@ -0,0 +1,54 @@
+---
+name: transfer
+description: Cross-project knowledge transfer — find similar prior projects and surface what worked. Builds institutional ML memory.
+disable-model-invocation: true
+argument-hint: "[--from project-path] [--auto]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Find similar prior projects and surface what worked. "Last time you had tabular classification with class imbalance, LightGBM beat everything by 3%."
+
+## Steps
+
+1. **Activate environment:**
+   ```bash
+   source .venv/bin/activate
+   ```
+
+2. **Parse arguments from `$ARGUMENTS`:**
+   - `--from ~/projects/fraud-detection` — transfer from a specific project
+   - `--auto` — auto-queue hypotheses from recommendations
+   - `--index ~/.turing/project_index.yaml` — custom index path
+   - `--json` — raw JSON output
+
+3. **Run knowledge transfer:**
+   ```bash
+   python scripts/knowledge_transfer.py $ARGUMENTS
+   ```
+
+4. **Report includes:**
+   - Similar prior projects ranked by similarity score
+   - Per project: task type, winner model, key insights
+   - Suggested hypotheses from winning strategies
+   - Auto-queued hypotheses (with `--auto`)
+
+5. **Similarity matching** uses:
+   - Task type (classification/regression) — highest weight
+   - Dataset size (log-scale comparison)
+   - Feature types (tabular/image/text)
+   - Class balance characteristics
+   - Dimensionality
+
+6. **Project index** at `~/.turing/project_index.yaml` — local only, never uploaded
+
+7. **If no similar projects found:** suggest running on more projects first or specifying one with `--from`
+
+8. **Saved output:** report in `experiments/transfers/transfer-*.yaml`
+
+## Examples
+
+```
+/turing:transfer                                    # Search index for similar projects
+/turing:transfer --from ~/projects/fraud-detection  # Transfer from specific project
+/turing:transfer --auto                             # Auto-queue hypotheses
+```

package/commands/turing.md

@@ -45,6 +45,11 @@ You are the Turing ML research router. Detect the user's intent and route to the
 | "ensemble", "combine models", "voting", "stacking", "blending", "merge models" | `/turing:ensemble` | Compose |
 | "stitch", "pipeline", "swap stage", "cache stage", "pipeline composition" | `/turing:stitch` | Compose |
 | "warm", "warm start", "fine-tune", "continue training", "transfer learning", "from checkpoint" | `/turing:warm` | Compose |
+| "scale", "scaling law", "how much data", "is more data worth it", "power law", "data efficiency" | `/turing:scale` | Analyze |
+| "budget", "compute budget", "how many experiments", "spending limit", "stop after" | `/turing:budget` | Manage |
+| "distill", "compress", "smaller model", "student model", "knowledge distillation", "model compression" | `/turing:distill` | Deploy |
+| "transfer", "what worked before", "similar project", "cross-project", "institutional knowledge", "prior projects" | `/turing:transfer` | Research |
+| "audit", "methodology check", "pre-submission", "reviewer checklist", "data leakage", "missing baselines" | `/turing:audit` | Validate |
 
 ## Sub-commands
 
@@ -86,6 +91,11 @@ You are the Turing ML research router. Detect the user's intent and route to the
 | `/turing:ensemble [--top-k] [--methods]` | Automated ensemble: voting, weighted voting, stacking, blending from top-K models | (inline) |
 | `/turing:stitch <action> [stage]` | Pipeline composition: show/swap/cache/run stages independently | (inline) |
 | `/turing:warm <exp-id>` | Warm-start from prior model: load checkpoint, freeze layers, adjust LR | (inline) |
+| `/turing:scale [--axis]` | Scaling law estimator: fit power law, predict full-scale performance | (inline) |
+| `/turing:budget <action>` | Compute budget manager: set limits, track allocation, auto-shift modes | (inline) |
+| `/turing:distill <exp-id>` | Model compression: distill teacher into smaller student model | (inline) |
+| `/turing:transfer [--from]` | Cross-project knowledge transfer: find similar prior projects, surface what worked | (inline) |
+| `/turing:audit [--strict]` | Pre-submission methodology audit: data leakage, baselines, seeds, ablations, reproducibility | (inline) |
 
 ## Proactive Detection
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-turing",
-  "version": "2.4.0",
+  "version": "3.0.0",
   "type": "module",
   "description": "Autonomous ML research harness for Claude Code. The autoresearch loop as a formal protocol — iteratively trains, evaluates, and improves ML models with structured experiment tracking, convergence detection, immutable evaluation infrastructure, and safety guardrails.",
   "bin": {

package/src/install.js

@@ -27,6 +27,8 @@ const SUB_COMMANDS = [
   "lit", "paper", "queue", "retry", "fork",
   "diff", "watch", "regress",
   "ensemble", "stitch", "warm",
+  "scale", "budget", "distill",
+  "transfer", "audit",
 ];
 
 export async function install(opts = {}) {

package/src/verify.js

@@ -50,6 +50,11 @@ const EXPECTED_COMMANDS = [
   "ensemble/SKILL.md",
   "stitch/SKILL.md",
   "warm/SKILL.md",
+  "scale/SKILL.md",
+  "budget/SKILL.md",
+  "distill/SKILL.md",
+  "transfer/SKILL.md",
+  "audit/SKILL.md",
 ];
 
 const EXPECTED_AGENTS = ["ml-researcher.md", "ml-evaluator.md"];