# Attribution pilot — round1-diarized

Lane **diarized** · sample `video:ObviousRises-rumble/v6z1o2g` · 1 video(s) · model `qwen2.5:7b` @ numCtx 8192 (maxCues 600) · 2026-08-08T05:32:17.770Z

Outcomes: attributed 1

## Diarized lane — the claim under test is ONE call per video

| video | calls | clusters offered | clusters named | confidences |
| --- | ---: | ---: | ---: | --- |
| ObviousRises-rumble/v6z1o2g | 1 | 9 | 9 | 0.90, 0.50, 0.80, 0.50, 0.70, 0.30, 0.50, 0.80, 0.70 |

**Calls per video: 1.00** (1 call(s) over 1 video(s)). The claim holds iff this is 1.00.

Warnings by code: none

## Cost

Measured over the 1 video(s) this run actually attributed (1/1 chunk(s) ok, 1 call(s), 1 with engine timing). Sample density **4.70 chunks/audio-hour** — the corpus census reads 2.46.

| quantity | value |
| --- | ---: |
| s/chunk, wall (video wall ÷ chunks) | 13.4 |
| s/chunk, per-call wall | 13.4 |
| s/chunk, engine | 13.4 |
| s/chunk, engine excl. model load | 8.3 |
| mean model-load s/call | 5.10 |
| decode tokens/s | 44.4 |
| digest chapters baseline, s/chunk engine | 11.2 |

## Box

Start: `{"loadavg":[1.83,1.7,1.7],"freeMemGb":10.42,"totalMemGb":15.53}`

End: `{"loadavg":[1.56,1.65,1.68],"freeMemGb":9.63,"totalMemGb":15.53}`

## Units

- The unit of text-only work is the **chunk** (one model call). Seconds-per-
  audio-hour is not a unit here: chunk density varies 4× across this corpus, and
  pricing in it is the error behind a retracted throughput headline. This report
  does not print one.
- The unit of diarized work is **calls per video**.
- Wall and engine are different quantities and are never substituted for each
  other. Wall is the realistic ceiling on this shared box; engine excl. load is
  the floor.
- Every rate carries its denominator. At n ≈ 8 videos a bare percentage would be
  a lie of precision.