"""Build the BabyYarros evaluation booth: voice A/B + beat->paragraph + delta_cb.
Reads the eval jsonls and the voice_distance summary, emits a self-contained
index.html for the Booth. Three panels:
A VOICE — each opening line, the three arms' continuations side by side, so the
operator can SEE whether the adapter pulls arbitrary prose toward Yarros.
B BEAT -> PARAGRAPH — the Skaldsong question: does the Instruct arm still take
direction (on-beat / in-band / ran-on) after training on raw Yarros text.
C delta_cb — the seat-free relative measure, with its A-vs-A noise floor.
"""
from __future__ import annotations
import html, json, re, sys
from pathlib import Path
D = Path(sys.argv[1]) # yarros-eval dir
DIST = Path(sys.argv[2]) if len(sys.argv) > 2 else None # distance stdout captured to a file
OUT = Path(sys.argv[3]) if len(sys.argv) > 3 else (D / "index.html")
def rows(f):
p = D / f
return [json.loads(l) for l in p.read_text(encoding="utf-8").splitlines()] if p.exists() else []
ARMS = [("base-unadapted", "Base · no adapter (control)"),
("base-125-tuned", "Base · Yarros LoRA (ckpt-125)"),
("instruct-tuned", "Instruct · Yarros LoRA")]
voice = {}
for key, _ in ARMS:
for r in rows(f"voice.{key}.jsonl"):
voice.setdefault((r["id"], r["seed"]), {})[key] = r
prompts = {}
for key, _ in ARMS:
for r in rows(f"voice.{key}.jsonl"):
prompts[r["id"]] = (r["tier"], r["prompt"])
def wc(t): return len(t.split())
def beat_flags(r):
kh, kws = r.get("keyword_hits", 0), r.get("beat_keywords", [])
ratio = kh / max(len(kws), 1)
on_beat = kh >= 1 and ratio >= 0.34 # at least a third of the beat's content words rendered
return on_beat, f"{kh}/{len(kws)}", r.get("in_band"), r.get("ran_on"), r.get("words", 0)
beats = rows("beats.instruct.jsonl")
esc = lambda s: html.escape(s or "")
parts = ["""BabyYarros — voice & beats
BabyYarros — does the voice transfer, can it do beats?
Qwen3-4B, one epoch on the leak-gated Yarros corpus. Base LoRA = ckpt-125 (its held-out minimum). Generated on gx10, same harness per arm. Not the frozen adjudication — the voice A/B and beat test the operator asked to see.
"""]
# Panel A — voice
parts.append('A · Voice — arbitrary opening line, three arms continue it
')
order = ["a1","a2","a3","b1","b2","b3","c1","c2","c3"]
seedpick = 1234
for pid in order:
if pid not in prompts: continue
tier, ptext = prompts[pid]
parts.append(f'{esc(ptext)} · {tier}
')
cell = voice.get((pid, seedpick), {})
for key, label in ARMS:
r = cell.get(key)
body = esc(r["continuation"].strip())[:1400] if r else "
—"
w = wc(r["continuation"]) if r else 0
parts.append(f'
{esc(label)}
{body}
{w} words
')
parts.append('
B · Beat → paragraph (Instruct, chat template) — the Skaldsong question
')
parts.append('Can the Instruct arm still take direction after training on raw Yarros continuation text? Each beat expanded to one paragraph in Yarros\' voice.
')
if beats:
parts.append('| beat | seed | on-beat (kw) | in-band 90–140 | ran-on | words |
|---|
')
for r in beats:
ob, kw, ib, ro, w = beat_flags(r)
yn = lambda v,good: (f'{"yes" if v else "no"}' if v==good else f'{"yes" if v else "no"}') if v is not None else '—'
parts.append(f'| {esc(r.get("beat",r.get("id","")))[:64]} | '
f'{r.get("seed","")} | '
f'{("yes" if ob else "no")} {kw} | '
f'{yn(ib,True)} | {yn(ro,False)} | {w} |
')
parts.append('
')
# show the actual paragraphs
for r in beats[:6]:
para = esc(r.get("paragraph", r.get("text","")).strip())[:1400]
parts.append(f'{esc(r.get("beat",""))}
')
else:
parts.append('beats file not present
')
# Panel C — delta_cb
parts.append('C · delta_cb — did the adapter move the voice toward held-out Yarros?
')
if DIST and DIST.exists():
parts.append(f'{esc(DIST.read_text())}')
else:
parts.append('distance summary not present
')
OUT.write_text("\n".join(parts), encoding="utf-8")
print(f"wrote {OUT} ({OUT.stat().st_size} bytes)")