{
  "generated_by": "paper/make-figures.mjs",
  "setup": {
    "claude_versions": {
      "wireless-101": "2.1.301 (Claude Code)",
      "stats-101": "2.1.301 (Claude Code)",
      "stats-101-planned": "2.1.302 (Claude Code)"
    },
    "ollama_version": "0.40.5",
    "machine": "Apple M4 Max, 64 GB",
    "plugin_version": "3.1.0",
    "git_commit": "ae03c20",
    "timeout_min": {
      "wireless-101": 120,
      "stats-101": 120,
      "stats-101-planned": 240
    },
    "budget_usd": 20,
    "judge_model": "claude-opus-5-5",
    "runs": [
      {
        "task": "wireless-101",
        "run_id": "20261016-000644",
        "title": "Wireless 101, Module 1"
      },
      {
        "task": "stats-101",
        "run_id": "20261016-063639-stats-101",
        "title": "STATS 101 — Module 1: Data, Samples and Describing Data"
      },
      {
        "task": "stats-101-planned",
        "run_id": "20261016-214018-stats-101-planned",
        "title": "STATS 101 — Module 1: Data, Samples and Describing Data"
      }
    ],
    "cost_note": "cost_usd is the Claude CLI API list-price figure; local (Ollama) runs are $0 per token"
  },
  "plan": {
    "task": "stats-101-planned",
    "planner": "claude-opus-5-5",
    "wall_min": 23.33,
    "wall_seconds": 1400,
    "cost_usd": 5.046,
    "turns": 51,
    "output_tokens": 101973,
    "plan_kb": 94,
    "plan_slides": 30,
    "patched": "after planning: D set to $PWD (was the planner temp folder) and the deck renamed deck.html, to match the build prompt"
  },
  "rows": [
    {
      "task": "wireless-101",
      "label": "opus",
      "model_name": "Opus 5.5",
      "model": "claude-opus-5-5",
      "provider": "anthropic",
      "finished": true,
      "status": "finished",
      "cli_reported_finished": true,
      "exit_code": 0,
      "terminal_reason": "completed",
      "wall_min": 11.73,
      "api_min": 9.95,
      "cost_usd": 2.8786,
      "turns": 34,
      "tool_calls": 32,
      "output_tokens": 63296,
      "slides": 30,
      "notes": 30,
      "diagrams": 13,
      "animated": 19,
      "placeholders": 3,
      "words_on_slides": 1616,
      "words_in_notes": 3042,
      "has_quiz": true,
      "checker_pass": true,
      "checker_issues": 0,
      "judge_overall": 9,
      "judge_accuracy": 5,
      "judge_coverage": 5,
      "judge_teaching": 5,
      "judge_visual": 4,
      "judge_diagrams": 5,
      "judge_notes": 5,
      "judge_requirements": 5,
      "wrong_claims": 2,
      "wrong_claims_major": 0,
      "invented_claims": 5,
      "invented_claims_untrue": 0,
      "ui_issues": 4,
      "ui_issues_major": 0,
      "major_mistakes": 0,
      "judge_cost_usd": 0.7094,
      "partial_slides": null,
      "partial_notes": null,
      "partial_files": null,
      "wrote_plan_md": true,
      "template_deck": null
    },
    {
      "task": "wireless-101",
      "label": "sonnet",
      "model_name": "Sonnet 5.5",
      "model": "claude-sonnet-5-5",
      "provider": "anthropic",
      "finished": true,
      "status": "finished",
      "cli_reported_finished": true,
      "exit_code": 0,
      "terminal_reason": "completed",
      "wall_min": 5.45,
      "api_min": 4.4,
      "cost_usd": 0.8992,
      "turns": 29,
      "tool_calls": 27,
      "output_tokens": 38188,
      "slides": 30,
      "notes": 30,
      "diagrams": 10,
      "animated": 14,
      "placeholders": 2,
      "words_on_slides": 1419,
      "words_in_notes": 2236,
      "has_quiz": true,
      "checker_pass": true,
      "checker_issues": 0,
      "judge_overall": 9,
      "judge_accuracy": 5,
      "judge_coverage": 5,
      "judge_teaching": 4,
      "judge_visual": 4,
      "judge_diagrams": 4,
      "judge_notes": 5,
      "judge_requirements": 5,
      "wrong_claims": 0,
      "wrong_claims_major": 0,
      "invented_claims": 3,
      "invented_claims_untrue": 0,
      "ui_issues": 7,
      "ui_issues_major": 0,
      "major_mistakes": 0,
      "judge_cost_usd": 0.6843,
      "partial_slides": null,
      "partial_notes": null,
      "partial_files": null,
      "wrote_plan_md": false,
      "template_deck": null
    },
    {
      "task": "wireless-101",
      "label": "haiku",
      "model_name": "Haiku 5.5",
      "model": "claude-haiku-5-5",
      "provider": "anthropic",
      "finished": true,
      "status": "finished",
      "cli_reported_finished": true,
      "exit_code": 0,
      "terminal_reason": "completed",
      "wall_min": 7.08,
      "api_min": 5.37,
      "cost_usd": 0.2447,
      "turns": 37,
      "tool_calls": 35,
      "output_tokens": 68384,
      "slides": 29,
      "notes": 29,
      "diagrams": 4,
      "animated": 14,
      "placeholders": 3,
      "words_on_slides": 1466,
      "words_in_notes": 1763,
      "has_quiz": true,
      "checker_pass": true,
      "checker_issues": 0,
      "judge_overall": 7,
      "judge_accuracy": 4,
      "judge_coverage": 4,
      "judge_teaching": 4,
      "judge_visual": 3,
      "judge_diagrams": 3,
      "judge_notes": 5,
      "judge_requirements": 5,
      "wrong_claims": 5,
      "wrong_claims_major": 1,
      "invented_claims": 4,
      "invented_claims_untrue": 1,
      "ui_issues": 7,
      "ui_issues_major": 1,
      "major_mistakes": 2,
      "judge_cost_usd": 0.7056,
      "partial_slides": null,
      "partial_notes": null,
      "partial_files": null,
      "wrote_plan_md": true,
      "template_deck": null
    },
    {
      "task": "wireless-101",
      "label": "qwen-local",
      "model_name": "qwen3.8 27B",
      "model": "qwen3.8:27b-mlx",
      "provider": "ollama",
      "finished": false,
      "status": "timed out",
      "cli_reported_finished": false,
      "exit_code": 143,
      "terminal_reason": null,
      "wall_min": 120,
      "api_min": null,
      "cost_usd": 0,
      "turns": null,
      "tool_calls": 19,
      "output_tokens": null,
      "slides": null,
      "notes": null,
      "diagrams": null,
      "animated": null,
      "placeholders": null,
      "words_on_slides": null,
      "words_in_notes": null,
      "has_quiz": null,
      "checker_pass": null,
      "checker_issues": null,
      "judge_overall": null,
      "judge_accuracy": null,
      "judge_coverage": null,
      "judge_teaching": null,
      "judge_visual": null,
      "judge_diagrams": null,
      "judge_notes": null,
      "judge_requirements": null,
      "wrong_claims": null,
      "wrong_claims_major": null,
      "invented_claims": null,
      "invented_claims_untrue": null,
      "ui_issues": null,
      "ui_issues_major": null,
      "major_mistakes": null,
      "judge_cost_usd": 0.4483,
      "partial_slides": 0,
      "partial_notes": 0,
      "partial_files": [],
      "wrote_plan_md": true,
      "template_deck": {
        "note": "deck.html was still the skill template when the run stopped; checker and judge scored the template",
        "slides": 21,
        "checker_pass": true,
        "judge_overall": 1
      }
    },
    {
      "task": "stats-101",
      "label": "opus",
      "model_name": "Opus 5.5",
      "model": "claude-opus-5-5",
      "provider": "anthropic",
      "finished": true,
      "status": "finished",
      "cli_reported_finished": true,
      "exit_code": 0,
      "terminal_reason": "completed",
      "wall_min": 11.23,
      "api_min": 8.85,
      "cost_usd": 2.7854,
      "turns": 32,
      "tool_calls": 31,
      "output_tokens": 56857,
      "slides": 30,
      "notes": 30,
      "diagrams": 11,
      "animated": 20,
      "placeholders": 2,
      "words_on_slides": 1513,
      "words_in_notes": 2962,
      "has_quiz": true,
      "checker_pass": true,
      "checker_issues": 0,
      "judge_overall": 9,
      "judge_accuracy": 5,
      "judge_coverage": 5,
      "judge_teaching": 5,
      "judge_visual": 4,
      "judge_diagrams": 5,
      "judge_notes": 5,
      "judge_requirements": 5,
      "wrong_claims": 1,
      "wrong_claims_major": 0,
      "invented_claims": 6,
      "invented_claims_untrue": 0,
      "ui_issues": 4,
      "ui_issues_major": 0,
      "major_mistakes": 0,
      "judge_cost_usd": 0.6565,
      "partial_slides": null,
      "partial_notes": null,
      "partial_files": null,
      "wrote_plan_md": true,
      "template_deck": null
    },
    {
      "task": "stats-101",
      "label": "sonnet",
      "model_name": "Sonnet 5.5",
      "model": "claude-sonnet-5-5",
      "provider": "anthropic",
      "finished": true,
      "status": "finished",
      "cli_reported_finished": true,
      "exit_code": 0,
      "terminal_reason": "completed",
      "wall_min": 5.4,
      "api_min": 3.87,
      "cost_usd": 0.7012,
      "turns": 22,
      "tool_calls": 21,
      "output_tokens": 29603,
      "slides": 29,
      "notes": 29,
      "diagrams": 7,
      "animated": 14,
      "placeholders": 2,
      "words_on_slides": 1392,
      "words_in_notes": 1682,
      "has_quiz": true,
      "checker_pass": true,
      "checker_issues": 0,
      "judge_overall": 9,
      "judge_accuracy": 5,
      "judge_coverage": 5,
      "judge_teaching": 5,
      "judge_visual": 4,
      "judge_diagrams": 5,
      "judge_notes": 5,
      "judge_requirements": 5,
      "wrong_claims": 0,
      "wrong_claims_major": 0,
      "invented_claims": 4,
      "invented_claims_untrue": 0,
      "ui_issues": 6,
      "ui_issues_major": 1,
      "major_mistakes": 1,
      "judge_cost_usd": 0.6107,
      "partial_slides": null,
      "partial_notes": null,
      "partial_files": null,
      "wrote_plan_md": true,
      "template_deck": null
    },
    {
      "task": "stats-101",
      "label": "haiku",
      "model_name": "Haiku 5.5",
      "model": "claude-haiku-5-5",
      "provider": "anthropic",
      "finished": true,
      "status": "finished",
      "cli_reported_finished": true,
      "exit_code": 0,
      "terminal_reason": "completed",
      "wall_min": 8.73,
      "api_min": 6.8,
      "cost_usd": 0.3163,
      "turns": 46,
      "tool_calls": 45,
      "output_tokens": 90031,
      "slides": 29,
      "notes": 29,
      "diagrams": 7,
      "animated": 10,
      "placeholders": 2,
      "words_on_slides": 1606,
      "words_in_notes": 1973,
      "has_quiz": true,
      "checker_pass": true,
      "checker_issues": 0,
      "judge_overall": 7,
      "judge_accuracy": 4,
      "judge_coverage": 4,
      "judge_teaching": 4,
      "judge_visual": 3,
      "judge_diagrams": 4,
      "judge_notes": 5,
      "judge_requirements": 4,
      "wrong_claims": 1,
      "wrong_claims_major": 0,
      "invented_claims": 3,
      "invented_claims_untrue": 0,
      "ui_issues": 6,
      "ui_issues_major": 2,
      "major_mistakes": 2,
      "judge_cost_usd": 0.7397,
      "partial_slides": null,
      "partial_notes": null,
      "partial_files": null,
      "wrote_plan_md": false,
      "template_deck": null
    },
    {
      "task": "stats-101",
      "label": "qwen-local",
      "model_name": "qwen3.8 27B",
      "model": "qwen3.8:27b-mlx",
      "provider": "ollama",
      "finished": false,
      "status": "timed out",
      "cli_reported_finished": false,
      "exit_code": 143,
      "terminal_reason": null,
      "wall_min": 120,
      "api_min": null,
      "cost_usd": 0,
      "turns": null,
      "tool_calls": 22,
      "output_tokens": null,
      "slides": null,
      "notes": null,
      "diagrams": null,
      "animated": null,
      "placeholders": null,
      "words_on_slides": null,
      "words_in_notes": null,
      "has_quiz": null,
      "checker_pass": null,
      "checker_issues": null,
      "judge_overall": null,
      "judge_accuracy": null,
      "judge_coverage": null,
      "judge_teaching": null,
      "judge_visual": null,
      "judge_diagrams": null,
      "judge_notes": null,
      "judge_requirements": null,
      "wrong_claims": null,
      "wrong_claims_major": null,
      "invented_claims": null,
      "invented_claims_untrue": null,
      "ui_issues": null,
      "ui_issues_major": null,
      "major_mistakes": null,
      "judge_cost_usd": 0.4194,
      "partial_slides": 20,
      "partial_notes": 17,
      "partial_files": [
        "part1.html",
        "part2.html"
      ],
      "wrote_plan_md": false,
      "template_deck": {
        "note": "deck.html was still the skill template when the run stopped; checker and judge scored the template",
        "slides": 21,
        "checker_pass": true,
        "judge_overall": 1
      }
    },
    {
      "task": "stats-101-planned",
      "label": "qwen-local",
      "model_name": "qwen3.8 27B",
      "model": "qwen3.8:27b-mlx",
      "provider": "ollama",
      "finished": false,
      "status": "API error",
      "cli_reported_finished": false,
      "exit_code": 1,
      "terminal_reason": "api_error",
      "wall_min": 61.05,
      "api_min": 61.02,
      "cost_usd": 0,
      "turns": 13,
      "tool_calls": 9,
      "output_tokens": 11099,
      "slides": null,
      "notes": null,
      "diagrams": null,
      "animated": null,
      "placeholders": null,
      "words_on_slides": null,
      "words_in_notes": null,
      "has_quiz": null,
      "checker_pass": null,
      "checker_issues": null,
      "judge_overall": null,
      "judge_accuracy": null,
      "judge_coverage": null,
      "judge_teaching": null,
      "judge_visual": null,
      "judge_diagrams": null,
      "judge_notes": null,
      "judge_requirements": null,
      "wrong_claims": null,
      "wrong_claims_major": null,
      "invented_claims": null,
      "invented_claims_untrue": null,
      "ui_issues": null,
      "ui_issues_major": null,
      "major_mistakes": null,
      "judge_cost_usd": null,
      "partial_slides": 10,
      "partial_notes": 10,
      "partial_files": [
        "01-opening.html"
      ],
      "wrote_plan_md": null,
      "template_deck": null
    },
    {
      "task": "stats-101-planned",
      "label": "qwen-moe",
      "model_name": "qwen3.6 35B-A3B",
      "model": "qwen3.6:35b-a3b",
      "provider": "ollama",
      "finished": true,
      "status": "finished",
      "cli_reported_finished": true,
      "exit_code": 0,
      "terminal_reason": "completed",
      "wall_min": 20.12,
      "api_min": 19.62,
      "cost_usd": 0,
      "turns": 31,
      "tool_calls": 30,
      "output_tokens": 70144,
      "slides": 30,
      "notes": 30,
      "diagrams": 10,
      "animated": 20,
      "placeholders": 2,
      "words_on_slides": 1458,
      "words_in_notes": 2830,
      "has_quiz": true,
      "checker_pass": true,
      "checker_issues": 0,
      "judge_overall": 9,
      "judge_accuracy": 5,
      "judge_coverage": 5,
      "judge_teaching": 5,
      "judge_visual": 4,
      "judge_diagrams": 4,
      "judge_notes": 4,
      "judge_requirements": 5,
      "wrong_claims": 0,
      "wrong_claims_major": 0,
      "invented_claims": 4,
      "invented_claims_untrue": 0,
      "ui_issues": 5,
      "ui_issues_major": 0,
      "major_mistakes": 1,
      "judge_cost_usd": 0.702,
      "partial_slides": null,
      "partial_notes": null,
      "partial_files": null,
      "wrote_plan_md": null,
      "template_deck": null
    },
    {
      "task": "stats-101-planned",
      "label": "gemma",
      "model_name": "gemma4 26B",
      "model": "gemma4:26b-mlx",
      "provider": "ollama",
      "finished": false,
      "status": "stopped early",
      "cli_reported_finished": true,
      "exit_code": 0,
      "terminal_reason": "completed",
      "wall_min": 72.57,
      "api_min": 72.55,
      "cost_usd": 0,
      "turns": 18,
      "tool_calls": 17,
      "output_tokens": 54053,
      "slides": null,
      "notes": null,
      "diagrams": null,
      "animated": null,
      "placeholders": null,
      "words_on_slides": null,
      "words_in_notes": null,
      "has_quiz": null,
      "checker_pass": null,
      "checker_issues": null,
      "judge_overall": null,
      "judge_accuracy": null,
      "judge_coverage": null,
      "judge_teaching": null,
      "judge_visual": null,
      "judge_diagrams": null,
      "judge_notes": null,
      "judge_requirements": null,
      "wrong_claims": null,
      "wrong_claims_major": null,
      "invented_claims": null,
      "invented_claims_untrue": null,
      "ui_issues": null,
      "ui_issues_major": null,
      "major_mistakes": null,
      "judge_cost_usd": null,
      "partial_slides": 10,
      "partial_notes": 10,
      "partial_files": [
        "01-opening.html"
      ],
      "wrote_plan_md": null,
      "template_deck": null
    }
  ]
}