{
"nbformat": 4,
"nbformat_minor": 5,
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"version": "3.12.14"
},
"execution_note": "Code cells executed with Python via an AST-based offline notebook runner; outputs are actual stdout and rich MIME return values. No Jupyter package dependency."
},
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# The denominator inside a geospatial benchmark\n",
"\n",
"This notebook reruns the attached offline analysis. Place all bundle files in one directory and run from that directory. The default path uses Python’s standard library only. Published measurements, metadata and illustrative numerical probes are identified in the article and provenance. No model or API calls occur.\n"
],
"id": "cell-1"
},
{
"cell_type": "code",
"metadata": {},
"source": [
"import sys, json, runpy\n",
"from pathlib import Path\n",
"if str(Path.cwd()) not in sys.path:\n",
" sys.path.insert(0, str(Path.cwd()))\n",
"analysis = runpy.run_path('analyze.py', run_name='offline_analysis')\n",
"result = analysis['analyze']()\n",
"analysis['draw'](result)\n",
"print('All analysis assertions passed; figures and results regenerated.')\n",
"print(json.dumps(result, indent=2))\n"
],
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"All analysis assertions passed; figures and results regenerated.\n",
"{\n",
" \"k_counts\": {\n",
" \"1\": 10,\n",
" \"2\": 50,\n",
" \"3\": 15,\n",
" \"4\": 10\n",
" },\n",
" \"template_counts\": {\n",
" \"k1_location_extreme_coordinate\": 5,\n",
" \"k1_datacommons_variable_ratio\": 5,\n",
" \"k3_places_dc_location_farthest_from_landmark\": 5,\n",
" \"k2_climate_risk_ee_admin_water_stress\": 5,\n",
" \"k2_climate_risk_buffer_water_stress\": 4,\n",
" \"k4_weather_location_places_dc_centroid_distance\": 5,\n",
" \"k2_flood_forecast_inundation_area_pct\": 3,\n",
" \"k2_climate_risk_buffer_temp_diff\": 4,\n",
" \"k2_climate_risk_ee_admin_days_above_temp\": 5,\n",
" \"k3_historical_weather_location_places_isolation\": 10,\n",
" \"k2_places_location_poi_pair_ratio\": 5,\n",
" \"k4_weather_location_places_dc_poi_extremes_distance\": 5,\n",
" \"k2_places_dc_ratio_and_poi_count\": 5,\n",
" \"k2_places_location_poi_density_comparison\": 5,\n",
" \"k2_climate_risk_city_buffer_water_stress_diff\": 3,\n",
" \"k2_places_dc_superlative_state_variant\": 1,\n",
" \"k2_places_dc_superlative_substate\": 3,\n",
" \"k2_places_dc_stat_to_poi_ratio\": 4,\n",
" \"k2_places_location_annulus_ring_pois\": 3\n",
" },\n",
" \"canonical_template_count\": 18,\n",
" \"canonical_template_counts\": {\n",
" \"k1_location_extreme_coordinate\": 5,\n",
" \"k1_datacommons_variable_ratio\": 5,\n",
" \"k3_places_dc_location_farthest_from_landmark\": 5,\n",
" \"k2_climate_risk_ee_admin_water_stress\": 5,\n",
" \"k2_climate_risk_buffer_water_stress\": 4,\n",
" \"k4_weather_location_places_dc_centroid_distance\": 5,\n",
" \"k2_flood_forecast_inundation_area_pct\": 3,\n",
" \"k2_climate_risk_buffer_temp_diff\": 4,\n",
" \"k2_climate_risk_ee_admin_days_above_temp\": 5,\n",
" \"k3_historical_weather_location_places_isolation\": 10,\n",
" \"k2_places_location_poi_pair_ratio\": 5,\n",
" \"k4_weather_location_places_dc_poi_extremes_distance\": 5,\n",
" \"k2_places_dc_ratio_and_poi_count\": 5,\n",
" \"k2_places_location_poi_density_comparison\": 5,\n",
" \"k2_climate_risk_city_buffer_water_stress_diff\": 3,\n",
" \"k2_places_dc_superlative_substate\": 4,\n",
" \"k2_places_dc_stat_to_poi_ratio\": 4,\n",
" \"k2_places_location_annulus_ring_pois\": 3\n",
" },\n",
" \"snapshot_dates\": {\n",
" \"2026-09-15\": 73,\n",
" \"2026-09-29\": 1,\n",
" \"2026-09-23\": 11\n",
" },\n",
" \"answer_slot_counts\": {\n",
" \"answer_slots\": 179,\n",
" \"numeric_slots\": 113,\n",
" \"string_slots\": 66,\n",
" \"zero_numeric_slots\": 7,\n",
" \"negative_numeric_slots\": 5\n",
" },\n",
" \"domain_solvability\": {\n",
" \"Natural Hazards & Crisis Resilience\": {\n",
" \"beyond_current_toolset\": 7,\n",
" \"solvable\": 4\n",
" },\n",
" \"Public Health\": {\n",
" \"beyond_current_toolset\": 3,\n",
" \"solvable\": 2\n",
" },\n",
" \"Site Selection & Urban Planning\": {\n",
" \"solvable\": 4,\n",
" \"beyond_current_toolset\": 4\n",
" },\n",
" \"Operational & Commercial Utilities\": {\n",
" \"beyond_current_toolset\": 1\n",
" }\n",
" },\n",
" \"solvability\": {\n",
" \"beyond_current_toolset\": 15,\n",
" \"solvable\": 10\n",
" },\n",
" \"workflow_list_items\": {\n",
" \"min\": 13,\n",
" \"median\": 19,\n",
" \"max\": 40\n",
" },\n",
" \"domain_weights_dev\": {\n",
" \"Natural Hazards & Crisis Resilience\": 0.44,\n",
" \"Public Health\": 0.2,\n",
" \"Site Selection & Urban Planning\": 0.32,\n",
" \"Operational & Commercial Utilities\": 0.04\n",
" },\n",
" \"domain_weights_test\": {\n",
" \"Natural Hazards & Crisis Resilience\": 0.4605263157894737,\n",
" \"Public Health\": 0.2236842105263158,\n",
" \"Site Selection & Urban Planning\": 0.25,\n",
" \"Operational & Commercial Utilities\": 0.06578947368421052\n",
" },\n",
" \"k_weights_dev\": [\n",
" 0.11764705882352941,\n",
" 0.5882352941176471,\n",
" 0.17647058823529413,\n",
" 0.11764705882352941\n",
" ],\n",
" \"k_weights_test\": [\n",
" 0.14285714285714285,\n",
" 0.47619047619047616,\n",
" 0.23809523809523808,\n",
" 0.14285714285714285\n",
" ],\n",
" \"k_composition_max_pp\": 11.204481792717088,\n",
" \"illustrative_profile\": {\n",
" \"rates\": [\n",
" 0.9,\n",
" 0.8,\n",
" 0.6,\n",
" 0.4\n",
" ],\n",
" \"dev_percent\": 72.94117647058825,\n",
" \"heldout_mixture_percent\": 70.95238095238095,\n",
" \"gap_pp\": 1.988795518207298\n",
" },\n",
" \"numeric_probes\": [\n",
" {\n",
" \"case\": \"inside boundary\",\n",
" \"gold\": 100,\n",
" \"prediction\": 110,\n",
" \"score\": 1.0\n",
" },\n",
" {\n",
" \"case\": \"outside boundary\",\n",
" \"gold\": 100,\n",
" \"prediction\": 110.01,\n",
" \"score\": 0.8998999999999999\n",
" },\n",
" {\n",
" \"case\": \"zero exact\",\n",
" \"gold\": 0,\n",
" \"prediction\": 0,\n",
" \"score\": 1.0\n",
" },\n",
" {\n",
" \"case\": \"zero near miss\",\n",
" \"gold\": 0,\n",
" \"prediction\": 0.01,\n",
" \"score\": 0.0\n",
" },\n",
" {\n",
" \"case\": \"numeric JSON value\",\n",
" \"gold\": 1000,\n",
" \"prediction\": 1000,\n",
" \"score\": 1.0\n",
" },\n",
" {\n",
" \"case\": \"exponent in string\",\n",
" \"gold\": 1000,\n",
" \"prediction\": \"1e3\",\n",
" \"score\": 0.0010000000000000009\n",
" },\n",
" {\n",
" \"case\": \"comma in string\",\n",
" \"gold\": 1000,\n",
" \"prediction\": \"1,000\",\n",
" \"score\": 0.0010000000000000009\n",
" },\n",
" {\n",
" \"case\": \"negative boundary\",\n",
" \"gold\": -100,\n",
" \"prediction\": -110,\n",
" \"score\": 1.0\n",
" }\n",
" ],\n",
" \"registry_status\": \"All 110 dev IDs unique; 85 parsed/raw answers agree; no agent scores computed.\"\n",
"}\n"
]
}
],
"id": "cell-2"
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Regenerated figures\n",
"\n",
"The following rich SVG outputs come from files regenerated by the preceding code, not screenshots of an external result.\n"
],
"id": "cell-3"
},
{
"cell_type": "code",
"metadata": {},
"source": [
"class LocalSVG:\n",
" def __init__(self, filename):\n",
" self.filename = filename\n",
" def _repr_mimebundle_(self, include=None, exclude=None):\n",
" return {'image/svg+xml': Path(self.filename).read_text(), 'text/plain': self.filename}\n"
],
"execution_count": 2,
"outputs": [],
"id": "cell-4"
},
{
"cell_type": "code",
"metadata": {},
"source": [
"LocalSVG('composition.svg')\n"
],
"execution_count": 3,
"outputs": [
{
"output_type": "execute_result",
"data": {
"image/svg+xml": "",
"text/plain": "composition.svg"
},
"metadata": {},
"execution_count": 3
}
],
"id": "cell-5"
},
{
"cell_type": "code",
"metadata": {},
"source": [
"LocalSVG('numeric-tolerance.svg')\n"
],
"execution_count": 4,
"outputs": [
{
"output_type": "execute_result",
"data": {
"image/svg+xml": "",
"text/plain": "numeric-tolerance.svg"
},
"metadata": {},
"execution_count": 4
}
],
"id": "cell-6"
},
{
"cell_type": "code",
"metadata": {},
"source": [
"LocalSVG('solvability.svg')\n",
"\n",
"import base64\n",
"from pathlib import Path\n",
"print('__NOTEBOOK_IMAGE__svg+xml:' + base64.b64encode(Path('composition.svg').read_bytes()).decode())\n",
"print('__NOTEBOOK_IMAGE__svg+xml:' + base64.b64encode(Path('numeric-tolerance.svg').read_bytes()).decode())\n",
"print('__NOTEBOOK_IMAGE__svg+xml:' + base64.b64encode(Path('solvability.svg').read_bytes()).decode())\n"
],
"execution_count": 5,
"outputs": [
{
"output_type": "execute_result",
"data": {
"image/svg+xml": "",
"text/plain": "solvability.svg"
},
"metadata": {},
"execution_count": 5
}
],
"id": "cell-7"
}
]
}