Add university-extension variety trials: Illinois VT + Iowa ICPT + Ohio OCPT (+123 trial docs)

Independent third-party performance data — land-grant programs that test every
entered brand side-by-side with replication + LSD stats. This is the legitimate
way to get Pioneer / DEKALB / Brevant / Channel performance the corpus can't
scrape directly (data_type=trial, results[] shape; falls through the trial
chunker).

- illinois_vt_trials (30 docs, 1,392 rows) — U of Illinois VT. Per-region XLSX
  (openpyxl), corn + soy + WHEAT, 2024+2025. Rich per-site agronomic metadata;
  corn-following-corn vs -soybean kept distinct.
- iowa_icpt_trials (24 docs, 674 rows) — Iowa State ICPT. ASP.NET GridView
  (viewstate postback for year/district), corn + soy by district x season.
- ohio_ocpt_trials (69 docs, 4,647 rows) — OSU/CFAES OCPT. Report PDF
  (pdfplumber; per-site column groups split by header Yield-token count +
  x-coord footnote bucketing), corn + soy per site, 2024+2025.

91 distinct seed brands across the three; majors confirmed present in the
independent rankings: DEKALB 395, Golden Harvest 249, Channel 241, NK 212,
Xitavo 135, LG 103, Pioneer 88, Asgrow 59. (A brand only appears where it
ENTERED a given program — e.g. Brevant not in Iowa, DEKALB/Channel not in
Illinois — true negatives, not parse gaps.)

- rag/chunk.py: gated `include_region` on _render_gh_plot_chunk; the 3 university
  sources route through it so the region/district is in the embedded chunk +
  labeled "variety trial (cross-vendor, independent third-party)". Existing plot
  sources (gh/lg/agrigold/proharvest) unchanged.
- requirements.txt: openpyxl (Illinois XLSX; scrape-time only).
- sources.json + README/CLAUDE/lessons: registered + attributed; lessons
  trial-data + Pioneer entries updated (Pioneer/DEKALB performance now available
  indirectly via these trials).

Validation: all 123 chunk via rag.chunk.chunks_from_trial (0 errors), 0
out-of-range yields, 0 dup keys. Public land-grant data; attribution recorded in
each tos_note. CI rebuilds the index from the committed corpus.
This commit is contained in:
2026-06-10 08:35:50 -04:00
parent 0bac06b7b6
commit 54094a0d43
255 changed files with 105410 additions and 13 deletions
@@ -0,0 +1,62 @@
# Soybean yield trial — University of Illinois VT, Region 4, IL 2024
- **Publisher:** University of Illinois Variety Testing (independent cross-vendor trial)
- **Crop:** Soybean
- **State:** IL
- **Year:** 2024
- **Region:** Region 4
- **Rotation:** corn following soybean
- **Cooperator / host:** Dennnis Brown
- **County:** Fayette
- **Sites:** St Peter, Belleville
- **Soil type:** Bluford-Damstadt silt loam
- **Tillage:** Field Cultivator, Vertical till
- **Planted:** 2024-05-21
- **Harvested:** 2024-10-23
- **Source XLSX:** https://vt.cropsci.illinois.edu/wp-content/uploads/2024/11/2024-Region-4.xlsx
- **Index page:** https://vt.cropsci.illinois.edu/soybeans/
---
## Results (ranked by regional yield)
| Rank | Brand | Product | Traits | Yield | Lodging | Height | Protein | Oil |
|---|---|---|---|---|---|---|---|---|
| 1 | AgVenture | AV 45B2E | HT:EN ST:Be | 73.71 | 4.867 | 37.168 | 33.2013 | 20.7479 |
| 2 | AgVenture | AV 41Y5E | HT:EN ST:Bs | 72.718 | 3.191 | 33.201 | 33.9174 | 20.8434 |
| 3 | AgVenture | AV 44B2E | HT:EN ST:Be | 72.516 | 4.099 | 36.747 | 32.9277 | 21.1774 |
| 4 | NuTech | 39N08E | HT:EN ST:B | 72.235 | 2.853 | 34.733 | 34.3206 | 21.0405 |
| 5 | AgVenture | AV 39B2E | HT:EN ST:Be | 72.079 | 2.833 | 34.275 | 34.2098 | 21.0019 |
| 6 | Burrus | 4134E | HT:EN ST:Bs | 72.023 | 2.968 | 30.879 | 33.8065 | 21.2062 |
| 7 | AgVenture | AV 43B2BE | HT:EN ST:Be | 71.939 | 2.993 | 32.924 | 34.9087 | 20.4439 |
| 8 | Baird Seed | Illini 4300N | HT:CV ST:B | 70.835 | 1.668 | 29.124 | 33.3516 | 21.8014 |
| 9 | AgVenture | AV 48B2E | HT:EN ST:Be | 70.707 | 4.838 | 36.138 | 33.4624 | 20.6619 |
| 10 | Baird Seed | Illini 4221N | HT:CV ST:B | 69.249 | 3.686 | 31.38 | 33.5127 | 21.3613 |
| 11 | Dyna-Gro | S37XF15 | HT:RX ST:Bs | 69.081 | 2.749 | 30.951 | 32.7448 | 20.9353 |
| 12 | Dyna-Gro | S38EN75 | HT:EN ST:Bs | 68.369 | 0.834 | 27.788 | 34.3 | 20.9333 |
| 13 | Hoffman | H43E25 | HT:EN ST:B | 68.268 | 5.704 | 38.673 | 34.2226 | 20.8766 |
| 14 | AgVenture | AV 36B2E | HT:EN ST:Be | 67.831 | 2.167 | 31.69 | 34.5834 | 20.4167 |
| 15 | Benson Hill | BH39A232 | HT:CV ST:Bs | 66.782 | 3.29 | 32.004 | 34.0395 | 20.5629 |
| 16 | Benson Hill | BH39A150 | HT:CV ST:Bs | 66.707 | 2.989 | 35.763 | 34.66 | 20.2792 |
| 17 | Hoffman | H38E25 | HT:EN ST:B | 66.559 | 1.412 | 30.549 | 33.2207 | 21.2407 |
| 18 | AgVenture | AV 47Y6E | HT:EN ST:Bs | 66.055 | 3.157 | 37.011 | 33.6655 | 20.7406 |
| 19 | Hoffman | H393N | HT:CV ST:B | 65.782 | 1.8 | 33.962 | 33.972 | 20.7812 |
| 20 | DONMARIO | DM36F84S | HT:RF ST:B | 65.737 | 2.126 | 33.528 | 33.636 | 21.149 |
| 21 | AgVenture | AV 42A1E | HT:EN ST:Bs | 65.253 | 2.752 | 34.26 | 34.6855 | 20.4842 |
| 22 | NuTech | 36N06E | HT:EN ST:B | 65.217 | 2 | 30.594 | 33.3 | 21.0833 |
| 23 | DONMARIO | DM38E54 | HT:EN ST:B | 65.177 | 1.833 | 33.385 | 33.9167 | 21.1167 |
| 24 | Hoffman | H42E25 | HT:EN ST:B | 63.588 | 3.501 | 33.858 | 33.1056 | 21.3696 |
| 25 | AgVenture | AV 38A1E | HT:EN ST:Bs | 63.183 | 0 | 30.598 | 34.5167 | 21.35 |
| 26 | Dyna-gro | S41XF65 | HT:XF ST:Bs | 61.836 | 3.608 | 34.569 | 33.9273 | 20.4493 |
| 27 | DONMARIO | DM36E94 | HT:EN ST:B | 61.642 | 1.834 | 30.314 | 34.0834 | 21.45 |
| 28 | Benson Hill | BX38F550 | HT:CV ST:Bs | 61.622 | 3.296 | 36.342 | 37.885 | 18.3353 |
| 29 | Benson Hill | BH37U222 | HT:CV ST:Bs | 59.747 | 2.5 | 34.228 | 40.4167 | 17.45 |
| 30 | Baird Seed | Illini 3849N | HT:CV ST:B | 59.703 | 2.667 | 29.56 | 31.9333 | 22.35 |
| 31 | Benson Hill | BX36Q861 | HT:CV ST:Bs | 59.05 | 1.334 | 31.453 | 40.9167 | 16.8833 |
| 32 | Baird Seed | Illini 3855N | HT:CV ST:B | 58.22 | 1.834 | 29.077 | 33.5667 | 20.9833 |
| 33 | Benson Hill | BH37U221 | HT:CV ST:Bs | 58.215 | 2.167 | 33.307 | 38.45 | 18.4 |
| 34 | Benson Hill | BH37Q218 | HT:CV ST:Bs | 56.758 | 2.334 | 32.469 | 37.9667 | 18.7 |
| 35 | Benson Hill | BH37U206 | HT:CV ST:Bs | 56.498 | 1.667 | 29.386 | 38.95 | 17.95 |
| 36 | Benson Hill | BX37Q467 | HT:CV ST:Bs | 53.756 | 1.833 | 33.308 | 38.9167 | 18.3 |
| 37 | Benson Hill | BH37U205 | HT:CV ST:Bs | 50.815 | 2.293 | 32.432 | 41.4027 | 16.774 |
| 38 | Baird Seed | Illini 3546N | HT:CV ST:B | 47.243 | 2.167 | 30.166 | 34.6 | 20.4833 |