Spaces:
Running
Running
| """Name the two evaluation tracks (user, 2026-10-01): the Research Track (20 scenes) and the Full Benchmark (160 scenes). | |
| The page's Text-to-Scene results are the Research Track's; the case-count strip states the two tracks. | |
| Each step asserts it found what it edits. | |
| python3 scripts/tracks.py | |
| """ | |
| from __future__ import annotations | |
| import re | |
| from pathlib import Path | |
| from bs4 import BeautifulSoup | |
| ROOT = Path(__file__).resolve().parent.parent | |
| V = "20261005tracks" | |
| def one(found, what): | |
| assert found, f"not found: {what}" | |
| return found | |
| def main(): | |
| p = ROOT / "index.html" | |
| soup = BeautifulSoup(p.read_text(), "html.parser") | |
| frag = lambda html: BeautifulSoup(html, "html.parser") | |
| # the case-count strip: the two tracks | |
| av = one(soup.find(class_="availability"), "availability strip") | |
| av.clear() | |
| av.append(frag('<span><b>20</b> scenes in the <strong>Research Track</strong>: affordable, reproducible evaluation ' | |
| 'for academic and model-development use</span>' | |
| '<span><b>160</b> scenes in the <strong>Full Benchmark</strong>: comprehensive evaluation ' | |
| 'for leaderboard and final reporting</span>')) | |
| # leaderboard: the Research Track | |
| lb = one(soup.find(id="leaderboard"), "leaderboard") | |
| one(lb.find(class_="section-desc"), "leaderboard desc").string = \ | |
| "Research Track · 20 representative scenes · 14 coding-agent configurations." | |
| lb.find(class_="section-desc").insert_after(frag( | |
| '<p class="tracks-why">Text-to-scene generation with frontier models is a long-horizon agentic task with substantial ' | |
| 'inference cost and runtime, which makes repeated full-scale evaluation difficult for many research groups. The ' | |
| 'Research Track supports affordable, reproducible experimentation; the Full Benchmark provides the more comprehensive ' | |
| 'evaluation for final model comparison and leaderboard reporting.</p>')) | |
| h3 = one(lb.select_one(".bar-heading h3"), "bar heading") | |
| one(h3.find("span", class_="q"), "bar qualifier").string = "Research Track" | |
| side = [s for s in lb.select(".bar-heading > span")] | |
| assert len(side) == 1, side | |
| side[0].string = "20 scenes · score out of 100" | |
| svg = one(lb.find(id="bars-t2s"), "bar svg") | |
| svg["aria-label"] = "Research Track scores for the 14 Code4Scene configurations" | |
| one(lb.find(class_="figure-subtitle"), "pareto subtitle").string = \ | |
| "Quality against the cost of one case · Research Track, 20 scenes" | |
| note = one(lb.find(class_="board-note"), "board note") | |
| t = note.get_text() | |
| assert t.startswith("20 public cases."), t | |
| note.string = "Research Track, 20 scenes." + t[len("20 public cases."):] | |
| # cache key for the stylesheet (one new rule) | |
| for link in soup.find_all("link", href=re.compile(r"^assets/buildingbench\.css")): | |
| link["href"] = f"assets/buildingbench.css?v={V}" | |
| p.write_text(str(soup)) | |
| left = re.findall(r"(?i)20 public|original 20|paper evaluation|129 public|full benchmark target", p.read_text()) | |
| assert not left, left | |
| css = ROOT / "assets/buildingbench.css"; s = css.read_text() | |
| rule = ".tracks-why{max-width:860px;margin:8px 0 0;font-size:13px;line-height:1.65;color:var(--text-muted);text-align:left}" | |
| if ".tracks-why{" not in s: | |
| css.write_text(s.rstrip("\n") + "\n/* evaluation tracks (scripts/tracks.py) */\n" + rule + | |
| "\n@media(max-width:650px){.tracks-why{font-size:11px}}\n") | |
| print("index.html: tracks strip, Research Track leaderboard") | |
| if __name__ == "__main__": | |
| main() | |