-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdashboard.html
More file actions
780 lines (768 loc) · 31.6 KB
/
dashboard.html
File metadata and controls
780 lines (768 loc) · 31.6 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Research Swarm Dashboard</title>
<script src="https://cdn.jsdelivr.net/npm/chart.js@4.4.4/dist/chart.umd.min.js"></script>
<style>
* { margin: 0; padding: 0; box-sizing: border-box; }
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', system-ui, sans-serif;
background: #0d1117;
color: #e6edf3;
padding: 24px;
}
h1 {
font-size: 28px;
margin-bottom: 8px;
background: linear-gradient(90deg, #58a6ff, #bc8cff);
-webkit-background-clip: text;
-webkit-text-fill-color: transparent;
}
.subtitle { color: #8b949e; margin-bottom: 24px; font-size: 14px; }
.stats-grid {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(160px, 1fr));
gap: 12px;
margin-bottom: 24px;
}
.stat-card {
background: #161b22;
border: 1px solid #30363d;
border-radius: 8px;
padding: 16px;
}
.stat-card .label { color: #8b949e; font-size: 12px; text-transform: uppercase; }
.stat-card .value { font-size: 28px; font-weight: 700; margin-top: 4px; }
.stat-card .trend { font-size: 12px; margin-top: 4px; }
.trend-up { color: #3fb950; }
.trend-down { color: #f85149; }
.trend-flat { color: #8b949e; }
.charts-grid {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(480px, 1fr));
gap: 16px;
margin-bottom: 24px;
}
.chart-card {
background: #161b22;
border: 1px solid #30363d;
border-radius: 8px;
padding: 16px;
}
.chart-card h3 { font-size: 14px; color: #8b949e; margin-bottom: 12px; }
canvas { max-height: 280px; }
table {
width: 100%;
border-collapse: collapse;
font-size: 13px;
}
th {
text-align: left;
padding: 8px 12px;
border-bottom: 2px solid #30363d;
color: #8b949e;
font-weight: 600;
}
td {
padding: 8px 12px;
border-bottom: 1px solid #21262d;
}
tr:hover { background: #161b22; }
.topic-cell { max-width: 300px; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }
.status-keep { color: #3fb950; font-weight: 600; }
.status-discard { color: #f85149; font-weight: 600; }
.section-title {
font-size: 18px;
margin: 24px 0 12px;
padding-bottom: 8px;
border-bottom: 1px solid #30363d;
}
.ablation-note {
background: #161b22;
border-left: 3px solid #58a6ff;
padding: 12px 16px;
margin-bottom: 24px;
font-size: 13px;
line-height: 1.6;
border-radius: 0 8px 8px 0;
}
.ablation-note strong { color: #58a6ff; }
</style>
</head>
<body>
<h1>Research Swarm Dashboard</h1>
<p class="subtitle">
32 successful runs | Last updated: 2026-03-14 17:21
| Latest: ? agents
</p>
<div class="ablation-note">
<strong>Ablation Finding (Run 20-31):</strong> Agent-count ablation across 4 configs (14/10/8/7 agents)
and 3 topics showed <strong>8 agents match 14-agent quality</strong> (6.1 vs 5.9 avg)
with higher actionability (5.3 vs 4.3). Swarm restructured from 14 to 8 agents.
Dropped: bench-scout, memory-researcher, eval-researcher, infra-researcher, codebase-auditor, gap-analyst.
</div>
<div class="stats-grid">
<div class="stat-card">
<div class="label">Avg Quality</div>
<div class="value">6.2</div>
<div class="trend trend-down">
Latest: 6.8
</div>
</div>
<div class="stat-card">
<div class="label">Best Quality</div>
<div class="value">7.2</div>
</div>
<div class="stat-card">
<div class="label">Best Actionability</div>
<div class="value">8.0</div>
</div>
<div class="stat-card">
<div class="label">Best Factuality</div>
<div class="value">7.0</div>
</div>
<div class="stat-card">
<div class="label">Total Runs</div>
<div class="value">32</div>
</div>
<div class="stat-card">
<div class="label">Avg Wall Clock</div>
<div class="value">597s</div>
</div>
<div class="stat-card">
<div class="label">Total Cost</div>
<div class="value">$1.79</div>
<div class="trend trend-flat">Avg: $0.0559/run</div>
</div>
</div>
<div class="charts-grid">
<div class="chart-card">
<h3>Quality Scores Over Time</h3>
<canvas id="qualityChart"></canvas>
</div>
<div class="chart-card">
<h3>Factuality & Actionability</h3>
<canvas id="factChart"></canvas>
</div>
<div class="chart-card">
<h3>Overlap Ratio (%)</h3>
<canvas id="overlapChart"></canvas>
</div>
<div class="chart-card">
<h3>Wall Clock (seconds) & Agent Count</h3>
<canvas id="perfChart"></canvas>
</div>
<div class="chart-card">
<h3>Cost per Run (USD)</h3>
<canvas id="costChart"></canvas>
</div>
</div>
<h2 class="section-title">Run History</h2>
<table>
<thead>
<tr>
<th>#</th>
<th>Topic</th>
<th>Agents</th>
<th>Quality</th>
<th>Action.</th>
<th>Fact.</th>
<th>Overlap</th>
<th>Wall</th>
<th>Cost</th>
<th>Status</th>
</tr>
</thead>
<tbody>
<tr>
<td>1</td>
<td class="topic-cell" title="Reducing agent timeout failures and optimizing task decomposition in multi-agent LLM pipelines 2025-2026">Reducing agent timeout failures and optimizing tas</td>
<td>11</td>
<td>7.0</td>
<td>7.0</td>
<td>0.0</td>
<td>69%</td>
<td>584s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>2</td>
<td class="topic-cell" title="Reducing hallucination and improving factual accuracy in multi-agent LLM research systems 2025-2026">Reducing hallucination and improving factual accur</td>
<td>11</td>
<td>7.0</td>
<td>7.0</td>
<td>0.0</td>
<td>62%</td>
<td>709s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>3</td>
<td class="topic-cell" title="Reducing hallucination and improving factual accuracy in multi-agent LLM research systems 2025-2026">Reducing hallucination and improving factual accur</td>
<td>11</td>
<td>6.3</td>
<td>7.0</td>
<td>0.0</td>
<td>74%</td>
<td>619s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>4</td>
<td class="topic-cell" title="Reducing applied agent failures and improving context-to-action conversion in multi-agent research pipelines 2025-2026">Reducing applied agent failures and improving cont</td>
<td>11</td>
<td>6.5</td>
<td>7.0</td>
<td>4.0</td>
<td>76%</td>
<td>709s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>5</td>
<td class="topic-cell" title="Semantic similarity detection and redundancy elimination in parallel multi-agent research outputs 2025-2026">Semantic similarity detection and redundancy elimi</td>
<td>11</td>
<td>5.8</td>
<td>6.0</td>
<td>4.0</td>
<td>58%</td>
<td>671s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>6</td>
<td class="topic-cell" title="Optimal multi-agent coordination patterns for LLM-based code generation systems 2025-2026">Optimal multi-agent coordination patterns for LLM-</td>
<td>11</td>
<td>6.8</td>
<td>7.0</td>
<td>6.0</td>
<td>5%</td>
<td>737s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>7</td>
<td class="topic-cell" title="Grounding multi-agent LLM systems with tool-augmented search and citation verification 2025-2026">Grounding multi-agent LLM systems with tool-augmen</td>
<td>11</td>
<td>6.0</td>
<td>6.0</td>
<td>5.0</td>
<td>28%</td>
<td>682s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>8</td>
<td class="topic-cell" title="Automated evaluation frameworks for multi-agent LLM systems 2025-2026">Automated evaluation frameworks for multi-agent LL</td>
<td>11</td>
<td>4.5</td>
<td>6.0</td>
<td>3.0</td>
<td>0%</td>
<td>370s</td>
<td>—</td>
<td class="status-discard">DISCARD</td>
</tr>
<tr>
<td>9</td>
<td class="topic-cell" title="Automated evaluation frameworks for multi-agent LLM systems 2025-2026">Automated evaluation frameworks for multi-agent LL</td>
<td>11</td>
<td>7.0</td>
<td>8.0</td>
<td>5.0</td>
<td>53%</td>
<td>639s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>10</td>
<td class="topic-cell" title="Priority-aware context compression and information routing for multi-phase agent pipelines 2025-2026">Priority-aware context compression and information</td>
<td>11</td>
<td>6.5</td>
<td>7.0</td>
<td>4.0</td>
<td>33%</td>
<td>764s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>11</td>
<td class="topic-cell" title="Techniques for reducing latency and improving reliability in LLM-based autonomous coding agents 2025-2026">Techniques for reducing latency and improving reli</td>
<td>11</td>
<td>6.5</td>
<td>7.0</td>
<td>5.0</td>
<td>71%</td>
<td>647s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>12</td>
<td class="topic-cell" title="Lightweight semantic deduplication techniques for multi-agent research outputs 2025-2026">Lightweight semantic deduplication techniques for </td>
<td>11</td>
<td>6.2</td>
<td>7.0</td>
<td>4.0</td>
<td>46%</td>
<td>626s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>13</td>
<td class="topic-cell" title="Improving factuality in multi-agent LLM research pipelines 2025-2026">Improving factuality in multi-agent LLM research p</td>
<td>11</td>
<td>7.2</td>
<td>8.0</td>
<td>6.0</td>
<td>100%</td>
<td>763s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>14</td>
<td class="topic-cell" title="Optimal number of agents in multi-agent LLM systems: scaling laws, diminishing returns, and agent count ablation studies 2024-2026">Optimal number of agents in multi-agent LLM system</td>
<td>11</td>
<td>6.2</td>
<td>7.0</td>
<td>4.0</td>
<td>55%</td>
<td>541s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>15</td>
<td class="topic-cell" title="Techniques for reducing hallucination in retrieval-augmented generation systems 2025-2026">Techniques for reducing hallucination in retrieval</td>
<td>11</td>
<td>5.5</td>
<td>3.0</td>
<td>5.0</td>
<td>0%</td>
<td>452s</td>
<td>—</td>
<td class="status-discard">DISCARD</td>
</tr>
<tr>
<td>16</td>
<td class="topic-cell" title="Efficient fine-tuning methods for large language models on consumer hardware 2025">Efficient fine-tuning methods for large language m</td>
<td>11</td>
<td>6.0</td>
<td>3.0</td>
<td>6.0</td>
<td>0%</td>
<td>528s</td>
<td>—</td>
<td class="status-discard">DISCARD</td>
</tr>
<tr>
<td>17</td>
<td class="topic-cell" title="Code generation evaluation benchmarks and automated testing for LLM outputs 2025-2026">Code generation evaluation benchmarks and automate</td>
<td>11</td>
<td>6.2</td>
<td>7.0</td>
<td>5.0</td>
<td>14%</td>
<td>562s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>18</td>
<td class="topic-cell" title="Techniques for reducing hallucination in retrieval-augmented generation systems 2025-2026">Techniques for reducing hallucination in retrieval</td>
<td>7</td>
<td>6.0</td>
<td>6.0</td>
<td>5.0</td>
<td>5%</td>
<td>601s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>19</td>
<td class="topic-cell" title="Efficient fine-tuning methods for large language models on consumer hardware 2025">Efficient fine-tuning methods for large language m</td>
<td>7</td>
<td>4.5</td>
<td>2.0</td>
<td>5.0</td>
<td>0%</td>
<td>480s</td>
<td>—</td>
<td class="status-discard">DISCARD</td>
</tr>
<tr>
<td>20</td>
<td class="topic-cell" title="Code generation evaluation benchmarks and automated testing for LLM outputs 2025-2026">Code generation evaluation benchmarks and automate</td>
<td>7</td>
<td>6.5</td>
<td>6.0</td>
<td>6.0</td>
<td>47%</td>
<td>632s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>21</td>
<td class="topic-cell" title="Techniques for reducing hallucination in retrieval-augmented generation systems 2025-2026">Techniques for reducing hallucination in retrieval</td>
<td>5</td>
<td>6.5</td>
<td>6.0</td>
<td>6.0</td>
<td>7%</td>
<td>603s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>22</td>
<td class="topic-cell" title="Efficient fine-tuning methods for large language models on consumer hardware 2025">Efficient fine-tuning methods for large language m</td>
<td>5</td>
<td>5.5</td>
<td>4.0</td>
<td>5.0</td>
<td>0%</td>
<td>438s</td>
<td>—</td>
<td class="status-discard">DISCARD</td>
</tr>
<tr>
<td>23</td>
<td class="topic-cell" title="Code generation evaluation benchmarks and automated testing for LLM outputs 2025-2026">Code generation evaluation benchmarks and automate</td>
<td>5</td>
<td>6.2</td>
<td>6.0</td>
<td>5.0</td>
<td>-14%</td>
<td>548s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>24</td>
<td class="topic-cell" title="Techniques for reducing hallucination in retrieval-augmented generation systems 2025-2026">Techniques for reducing hallucination in retrieval</td>
<td>4</td>
<td>6.0</td>
<td>7.0</td>
<td>4.0</td>
<td>7%</td>
<td>467s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>25</td>
<td class="topic-cell" title="Efficient fine-tuning methods for large language models on consumer hardware 2025">Efficient fine-tuning methods for large language m</td>
<td>4</td>
<td>6.5</td>
<td>6.0</td>
<td>6.0</td>
<td>8%</td>
<td>620s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>26</td>
<td class="topic-cell" title="Code generation evaluation benchmarks and automated testing for LLM outputs 2025-2026">Code generation evaluation benchmarks and automate</td>
<td>4</td>
<td>5.8</td>
<td>6.0</td>
<td>5.0</td>
<td>0%</td>
<td>584s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>27</td>
<td class="topic-cell" title="Chain-of-thought prompting techniques 2025">Chain-of-thought prompting techniques 2025</td>
<td>5</td>
<td>6.0</td>
<td>6.0</td>
<td>5.0</td>
<td>23%</td>
<td>537s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>28</td>
<td class="topic-cell" title="Speculative decoding for multi-agent systems">Speculative decoding for multi-agent systems</td>
<td>5</td>
<td>6.5</td>
<td>6.0</td>
<td>6.0</td>
<td>0%</td>
<td>628s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>29</td>
<td class="topic-cell" title="Autonomous agent self-improvement via recursive code editing">Autonomous agent self-improvement via recursive co</td>
<td>5</td>
<td>5.5</td>
<td>6.0</td>
<td>4.0</td>
<td>38%</td>
<td>673s</td>
<td>—</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>30</td>
<td class="topic-cell" title="Chain-of-thought prompting techniques 2025">Chain-of-thought prompting techniques 2025</td>
<td>5</td>
<td>7.0</td>
<td>7.0</td>
<td>7.0</td>
<td>23%</td>
<td>502s</td>
<td>$0.60</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>31</td>
<td class="topic-cell" title="Speculative decoding for multi-agent systems">Speculative decoding for multi-agent systems</td>
<td>5</td>
<td>7.0</td>
<td>7.0</td>
<td>7.0</td>
<td>0%</td>
<td>441s</td>
<td>$0.56</td>
<td class="status-keep">KEEP</td>
</tr>
<tr>
<td>32</td>
<td class="topic-cell" title="Autonomous agent self-improvement via recursive code editing">Autonomous agent self-improvement via recursive co</td>
<td>5</td>
<td>6.8</td>
<td>6.0</td>
<td>7.0</td>
<td>100%</td>
<td>737s</td>
<td>$0.63</td>
<td class="status-keep">KEEP</td>
</tr>
</tbody>
</table>
<script>
const labels = ["Run 1", "Run 2", "Run 3", "Run 4", "Run 5", "Run 6", "Run 7", "Run 8", "Run 9", "Run 10", "Run 11", "Run 12", "Run 13", "Run 14", "Run 15", "Run 16", "Run 17", "Run 18", "Run 19", "Run 20", "Run 21", "Run 22", "Run 23", "Run 24", "Run 25", "Run 26", "Run 27", "Run 28", "Run 29", "Run 30", "Run 31", "Run 32"];
const topics = ["Reducing agent timeout failures and opti", "Reducing hallucination and improving fac", "Reducing hallucination and improving fac", "Reducing applied agent failures and impr", "Semantic similarity detection and redund", "Optimal multi-agent coordination pattern", "Grounding multi-agent LLM systems with t", "Automated evaluation frameworks for mult", "Automated evaluation frameworks for mult", "Priority-aware context compression and i", "Techniques for reducing latency and impr", "Lightweight semantic deduplication techn", "Improving factuality in multi-agent LLM ", "Optimal number of agents in multi-agent ", "Techniques for reducing hallucination in", "Efficient fine-tuning methods for large ", "Code generation evaluation benchmarks an", "Techniques for reducing hallucination in", "Efficient fine-tuning methods for large ", "Code generation evaluation benchmarks an", "Techniques for reducing hallucination in", "Efficient fine-tuning methods for large ", "Code generation evaluation benchmarks an", "Techniques for reducing hallucination in", "Efficient fine-tuning methods for large ", "Code generation evaluation benchmarks an", "Chain-of-thought prompting techniques 20", "Speculative decoding for multi-agent sys", "Autonomous agent self-improvement via re", "Chain-of-thought prompting techniques 20", "Speculative decoding for multi-agent sys", "Autonomous agent self-improvement via re"];
const chartDefaults = {
responsive: true,
maintainAspectRatio: true,
plugins: {
legend: { labels: { color: '#8b949e', font: { size: 11 } } },
tooltip: {
callbacks: {
title: (items) => topics[items[0].dataIndex] || labels[items[0].dataIndex]
}
}
},
scales: {
x: { ticks: { color: '#484f58', font: { size: 10 } }, grid: { color: '#21262d' } },
y: { ticks: { color: '#484f58' }, grid: { color: '#21262d' } }
}
};
// Quality chart
new Chart(document.getElementById('qualityChart'), {
type: 'line',
data: {
labels: labels,
datasets: [
{
label: 'Avg Quality',
data: [7.0, 7.0, 6.3, 6.5, 5.8, 6.8, 6.0, 4.5, 7.0, 6.5, 6.5, 6.2, 7.2, 6.2, 5.5, 6.0, 6.2, 6.0, 4.5, 6.5, 6.5, 5.5, 6.2, 6.0, 6.5, 5.8, 6.0, 6.5, 5.5, 7.0, 7.0, 6.8],
borderColor: '#58a6ff',
backgroundColor: 'rgba(88,166,255,0.1)',
fill: true,
tension: 0.3,
},
{
label: '3-Run Average',
data: [7.0, 7.0, 6.77, 6.6, 6.2, 6.37, 6.2, 5.77, 5.83, 6.0, 6.67, 6.4, 6.63, 6.53, 6.3, 5.9, 5.9, 6.07, 5.57, 5.67, 5.83, 6.17, 6.07, 5.9, 6.23, 6.1, 6.1, 6.1, 6.0, 6.33, 6.5, 6.93],
borderColor: '#bc8cff',
borderDash: [5, 5],
pointRadius: 0,
tension: 0.3,
},
{
label: 'Coverage',
data: [8.0, 8.0, 7.0, 8.0, 7.0, 7.0, 7.0, 4.0, 8.0, 8.0, 7.0, 7.0, 8.0, 7.0, 7.0, 8.0, 7.0, 7.0, 6.0, 7.0, 7.0, 6.0, 7.0, 6.0, 7.0, 6.0, 7.0, 7.0, 6.0, 7.0, 7.0, 7.0],
borderColor: '#3fb950',
borderWidth: 1,
pointRadius: 2,
tension: 0.3,
},
{
label: 'Accuracy',
data: [6.0, 6.0, 5.0, 7.0, 6.0, 7.0, 6.0, 5.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 6.0, 6.0, 5.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 6.0, 6.0, 7.0, 6.0, 7.0, 7.0, 7.0],
borderColor: '#d29922',
borderWidth: 1,
pointRadius: 2,
tension: 0.3,
}
]
},
options: { ...chartDefaults, scales: { ...chartDefaults.scales, y: { ...chartDefaults.scales.y, min: 0, max: 10 } } }
});
// Factuality & Actionability
new Chart(document.getElementById('factChart'), {
type: 'line',
data: {
labels: labels,
datasets: [
{
label: 'Actionability',
data: [7.0, 7.0, 7.0, 7.0, 6.0, 7.0, 6.0, 6.0, 8.0, 7.0, 7.0, 7.0, 8.0, 7.0, 3.0, 3.0, 7.0, 6.0, 2.0, 6.0, 6.0, 4.0, 6.0, 7.0, 6.0, 6.0, 6.0, 6.0, 6.0, 7.0, 7.0, 6.0],
borderColor: '#3fb950',
backgroundColor: 'rgba(63,185,80,0.1)',
fill: true,
tension: 0.3,
},
{
label: 'Factuality',
data: [0, 0, 0, 4.0, 4.0, 6.0, 5.0, 3.0, 5.0, 4.0, 5.0, 4.0, 6.0, 4.0, 5.0, 6.0, 5.0, 5.0, 5.0, 6.0, 6.0, 5.0, 5.0, 4.0, 6.0, 5.0, 5.0, 6.0, 4.0, 7.0, 7.0, 7.0],
borderColor: '#f85149',
backgroundColor: 'rgba(248,81,73,0.1)',
fill: true,
tension: 0.3,
},
{
label: 'Action. 3-Run Avg',
data: [7.0, 7.0, 7.0, 7.0, 6.67, 6.67, 6.33, 6.33, 6.67, 7.0, 7.33, 7.0, 7.33, 7.33, 6.0, 4.33, 4.33, 5.33, 5.0, 4.67, 4.67, 5.33, 5.33, 5.67, 6.33, 6.33, 6.0, 6.0, 6.0, 6.33, 6.67, 6.67],
borderColor: '#3fb950',
borderDash: [5, 5],
pointRadius: 0,
tension: 0.3,
},
{
label: 'Fact. 3-Run Avg',
data: [0.0, 0.0, 0.0, 1.33, 2.67, 4.67, 5.0, 4.67, 4.33, 4.0, 4.67, 4.33, 5.0, 4.67, 5.0, 5.0, 5.33, 5.33, 5.0, 5.33, 5.67, 5.67, 5.33, 4.67, 5.0, 5.0, 5.33, 5.33, 5.0, 5.67, 6.0, 7.0],
borderColor: '#f85149',
borderDash: [5, 5],
pointRadius: 0,
tension: 0.3,
}
]
},
options: { ...chartDefaults, scales: { ...chartDefaults.scales, y: { ...chartDefaults.scales.y, min: 0, max: 10 } } }
});
// Overlap chart
new Chart(document.getElementById('overlapChart'), {
type: 'bar',
data: {
labels: labels,
datasets: [{
label: 'Overlap %',
data: [69.2, 62.5, 73.7, 75.6, 58.3, 5.4, 27.8, 0.0, 52.6, 33.3, 71.4, 45.7, 100.0, 54.8, 0.0, 0.0, 13.9, 5.0, 0.0, 47.4, 6.7, 0.0, -14.3, 6.7, 7.7, 0.0, 23.1, 0.0, 37.5, 23.1, 0.0, 100.0],
backgroundColor: (ctx) => {
const v = ctx.raw;
if (v > 60) return 'rgba(248,81,73,0.6)';
if (v > 40) return 'rgba(210,153,34,0.6)';
return 'rgba(63,185,80,0.6)';
},
borderRadius: 4,
}]
},
options: { ...chartDefaults, scales: { ...chartDefaults.scales, y: { ...chartDefaults.scales.y, min: 0, max: 100 } } }
});
// Performance chart (wall clock + agent count)
new Chart(document.getElementById('perfChart'), {
type: 'line',
data: {
labels: labels,
datasets: [
{
label: 'Wall Clock (s)',
data: [584.0, 709.0, 619.0, 709.0, 671.0, 737.0, 682.0, 370.0, 639.0, 764.0, 647.0, 626.0, 763.0, 541.0, 452.0, 528.0, 562.0, 601.0, 480.0, 632.0, 603.0, 438.0, 548.0, 467.0, 620.0, 584.0, 537.0, 628.0, 673.0, 502.0, 441.0, 737.0],
borderColor: '#d29922',
backgroundColor: 'rgba(210,153,34,0.1)',
fill: true,
tension: 0.3,
yAxisID: 'y',
},
{
label: 'Agent Count',
data: [11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 7, 7, 7, 5, 5, 5, 4, 4, 4, 5, 5, 5, 5, 5, 5],
borderColor: '#bc8cff',
borderWidth: 2,
pointRadius: 4,
tension: 0,
yAxisID: 'y1',
},
{
label: 'Applied Success %',
data: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
borderColor: '#58a6ff',
borderWidth: 1,
pointRadius: 2,
tension: 0.3,
yAxisID: 'y1',
}
]
},
options: {
...chartDefaults,
scales: {
x: chartDefaults.scales.x,
y: { ...chartDefaults.scales.y, position: 'left', title: { display: true, text: 'Seconds', color: '#8b949e' } },
y1: { ...chartDefaults.scales.y, position: 'right', min: 0, max: 20, title: { display: true, text: 'Count / %', color: '#8b949e' }, grid: { drawOnChartArea: false } }
}
}
});
// Cost chart (USD per run)
new Chart(document.getElementById('costChart'), {
type: 'bar',
data: {
labels: labels,
datasets: [
{
label: 'Cost (USD)',
data: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.6032, 0.5575, 0.6316],
backgroundColor: 'rgba(63,185,80,0.5)',
borderColor: '#3fb950',
borderWidth: 1,
borderRadius: 4,
yAxisID: 'y',
},
{
label: '3-Run Avg',
data: [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.2, 0.39, 0.6],
type: 'line',
borderColor: '#bc8cff',
borderDash: [5, 5],
pointRadius: 0,
tension: 0.3,
yAxisID: 'y',
}
]
},
options: {
...chartDefaults,
scales: {
...chartDefaults.scales,
y: { ...chartDefaults.scales.y, min: 0, title: { display: true, text: 'USD', color: '#8b949e' } }
}
}
});
</script>
</body>
</html>