1{2 "results/tables/E1_core_primary.csv": {3 "sources": [4 "runs/raw/E1_core.jsonl"5 ],6 "script": "src/wp30/analysis/analyze.py",7 "generated_utc": "2026-10-30T09:02:37.609345Z",8 "note": "per-condition quality (cluster bootstrap CI) and resource medians"9 },10 "results/tables/E1_core_failures.csv": {11 "sources": [12 "runs/raw/E1_core.jsonl"13 ],14 "script": "src/wp30/analysis/analyze.py",15 "generated_utc": "2026-10-30T09:02:37.611126Z",16 "note": "attempt status counts by method"17 },18 "results/tables/E1_core_by_question_type.csv": {19 "sources": [20 "runs/raw/E1_core.jsonl"21 ],22 "script": "src/wp30/analysis/analyze.py",23 "generated_utc": "2026-10-30T09:02:37.730657Z",24 "note": "synthetic accuracy by question type"25 },26 "results/tables/E1_core_primary_tests.csv": {27 "sources": [28 "runs/raw/E1_core.jsonl"29 ],30 "script": "src/wp30/analysis/analyze.py",31 "generated_utc": "2026-10-30T09:02:37.786568Z",32 "note": "registered primary comparisons, paired, cluster bootstrap, Holm"33 },34 "results/figures/fig2_quality_vs_bytes.pdf": {35 "sources": [36 "runs/raw/E1_core.jsonl"37 ],38 "script": "src/wp30/analysis/analyze.py",39 "generated_utc": "2026-10-30T09:02:38.459020Z",40 "note": "points = conditions; x = median payload bytes; y = mean quality"41 },42 "results/figures/fig2_quality_vs_bytes.png": {43 "sources": [44 "runs/raw/E1_core.jsonl"45 ],46 "script": "src/wp30/analysis/analyze.py",47 "generated_utc": "2026-10-30T09:02:38.666585Z",48 "note": "points = conditions; x = median payload bytes; y = mean quality"49 },50 "results/figures/figA_quality_vs_bytes_blind.pdf": {51 "sources": [52 "runs/raw/E1_core.jsonl"53 ],54 "script": "src/wp30/analysis/analyze.py",55 "generated_utc": "2026-10-30T09:02:39.176959Z",56 "note": "points = conditions; x = median payload bytes; y = mean quality"57 },58 "results/figures/figA_quality_vs_bytes_blind.png": {59 "sources": [60 "runs/raw/E1_core.jsonl"61 ],62 "script": "src/wp30/analysis/analyze.py",63 "generated_utc": "2026-10-30T09:02:39.359044Z",64 "note": "points = conditions; x = median payload bytes; y = mean quality"65 },66 "results/figures/figA_quality_vs_bytes_aware.pdf": {67 "sources": [68 "runs/raw/E1_core.jsonl"69 ],70 "script": "src/wp30/analysis/analyze.py",71 "generated_utc": "2026-10-30T09:02:39.746284Z",72 "note": "points = conditions; x = median payload bytes; y = mean quality"73 },74 "results/figures/figA_quality_vs_bytes_aware.png": {75 "sources": [76 "runs/raw/E1_core.jsonl"77 ],78 "script": "src/wp30/analysis/analyze.py",79 "generated_utc": "2026-10-30T09:02:39.940182Z",80 "note": "points = conditions; x = median payload bytes; y = mean quality"81 },82 "results/figures/fig3_quality_vs_latency_memory.pdf": {83 "sources": [84 "runs/raw/E1_core.jsonl"85 ],86 "script": "src/wp30/analysis/analyze.py",87 "generated_utc": "2026-10-30T09:02:40.285980Z",88 "note": ""89 },90 "results/figures/fig3_quality_vs_latency_memory.png": {91 "sources": [92 "runs/raw/E1_core.jsonl"93 ],94 "script": "src/wp30/analysis/analyze.py",95 "generated_utc": "2026-10-30T09:02:40.475124Z",96 "note": ""97 },98 "results/figures/fig4_latency_decomposition.pdf": {99 "sources": [100 "runs/raw/E1_core.jsonl"101 ],102 "script": "src/wp30/analysis/analyze.py",103 "generated_utc": "2026-10-30T09:02:40.560198Z",104 "note": ""105 },106 "results/figures/fig4_latency_decomposition.png": {107 "sources": [108 "runs/raw/E1_core.jsonl"109 ],110 "script": "src/wp30/analysis/analyze.py",111 "generated_utc": "2026-10-30T09:02:40.620070Z",112 "note": ""113 },114 "results/figures/fig5_handoffs.pdf": {115 "sources": [116 "runs/raw/E4_core.jsonl"117 ],118 "script": "src/wp30/analysis/analyze.py",119 "generated_utc": "2026-10-30T09:02:45.615826Z",120 "note": "means over documents; chains defined in configs/chains*.yaml"121 },122 "results/figures/fig5_handoffs.png": {123 "sources": [124 "runs/raw/E4_core.jsonl"125 ],126 "script": "src/wp30/analysis/analyze.py",127 "generated_utc": "2026-10-30T09:02:45.675774Z",128 "note": "means over documents; chains defined in configs/chains*.yaml"129 },130 "results/tables/E4_core_handoffs.csv": {131 "sources": [132 "runs/raw/E4_core.jsonl"133 ],134 "script": "src/wp30/analysis/analyze.py",135 "generated_utc": "2026-10-30T09:02:45.778336Z",136 "note": "repeated handoffs"137 },138 "results/tables/E4_core_h4_primary_tests.csv": {139 "sources": [140 "runs/raw/E4_core.jsonl"141 ],142 "script": "src/wp30/analysis/analyze.py",143 "generated_utc": "2026-10-30T09:02:45.791552Z",144 "note": "registered primary comparisons, paired, cluster bootstrap, Holm"145 },146 "results/tables/E5_core_fanin.csv": {147 "sources": [148 "runs/raw/E5_core.jsonl"149 ],150 "script": "src/wp30/analysis/analyze.py",151 "generated_utc": "2026-10-30T09:02:45.898241Z",152 "note": "fan-in by method and question type"153 },154 "results/figures/fig6_breakeven.pdf": {155 "sources": [156 "runs/raw/E6_core.jsonl"157 ],158 "script": "src/wp30/analysis/analyze.py",159 "generated_utc": "2026-10-30T09:02:45.992041Z",160 "note": "left = measured (medians, p25-p75); right = analytic model from measured bandwidth and prefill slope; dashed 10 Gb/s is hypothetical"161 },162 "results/figures/fig6_breakeven.png": {163 "sources": [164 "runs/raw/E6_core.jsonl"165 ],166 "script": "src/wp30/analysis/analyze.py",167 "generated_utc": "2026-10-30T09:02:46.065845Z",168 "note": "left = measured (medians, p25-p75); right = analytic model from measured bandwidth and prefill slope; dashed 10 Gb/s is hypothetical"169 },170 "results/tables/E6_network.csv": {171 "sources": [172 "runs/raw/E6_core.jsonl"173 ],174 "script": "src/wp30/analysis/analyze.py",175 "generated_utc": "2026-10-30T09:02:46.070991Z",176 "note": "two-node transfer measurements"177 },178 "results/tables/ED_hosted.csv": {179 "sources": [180 "runs/raw/ED_hosted_core.jsonl"181 ],182 "script": "src/wp30/analysis/analyze.py",183 "generated_utc": "2026-10-30T09:02:46.140839Z",184 "note": "hosted receivers; cost estimated from provider price tables"185 },186 "results/tables/E3_core_transfer.csv": {187 "sources": [188 "runs/raw/E3_core.jsonl",189 "runs/raw/E3_core_sender.jsonl"190 ],191 "script": "src/wp30/analysis/analyze.py",192 "generated_utc": "2026-10-30T09:02:46.269308Z",193 "note": "same-family mapper transfer vs text handoffs and references"194 },195 "results/tables/E3_core_primary_tests.csv": {196 "sources": [197 "runs/raw/E3_core.jsonl",198 "runs/raw/E3_core_sender.jsonl"199 ],200 "script": "src/wp30/analysis/analyze.py",201 "generated_utc": "2026-10-30T09:02:46.347449Z",202 "note": "registered primary comparisons, paired, cluster bootstrap, Holm"203 },204 "results/tables/E7_qtypes.csv": {205 "sources": [206 "runs/raw/E7_qtypes.jsonl"207 ],208 "script": "src/wp30/analysis/analyze.py",209 "generated_utc": "2026-10-30T09:02:46.532910Z",210 "note": "EXPLORATORY: question types 6-15 on synthetic test documents"211 },212 "results/figures/figA_qtypes_exploratory.pdf": {213 "sources": [214 "runs/raw/E7_qtypes.jsonl"215 ],216 "script": "src/wp30/analysis/analyze.py",217 "generated_utc": "2026-10-30T09:02:46.612438Z",218 "note": "exploratory extension A-004"219 },220 "results/figures/figA_qtypes_exploratory.png": {221 "sources": [222 "runs/raw/E7_qtypes.jsonl"223 ],224 "script": "src/wp30/analysis/analyze.py",225 "generated_utc": "2026-10-30T09:02:46.668848Z",226 "note": "exploratory extension A-004"227 },228 "results/figures/fig7_router.pdf": {229 "sources": [230 "results/tables/E8_router_summary.csv",231 "runs/raw/E1_core.jsonl",232 "runs/checkpoints/router_policy.json"233 ],234 "script": "src/wp30/analysis/analyze.py",235 "generated_utc": "2026-10-30T09:02:46.768937Z",236 "note": "oracle = infeasible upper reference"237 },238 "results/figures/fig7_router.png": {239 "sources": [240 "results/tables/E8_router_summary.csv",241 "runs/raw/E1_core.jsonl",242 "runs/checkpoints/router_policy.json"243 ],244 "script": "src/wp30/analysis/analyze.py",245 "generated_utc": "2026-10-30T09:02:46.853258Z",246 "note": "oracle = infeasible upper reference"247 }248}