Run #784
done
rubric v1
session 79142930
gemini-3.7-flash
2026-09-21 02:21
Review team
no_issue
Product AI
nothing found
teaching Yes · mistakes No · satisfactory Yes
Each verdict takes your own. Yours is stored against the stack's, so “where is it wrong most often” is a question with an answer.
-
seen · 95% confidentWork is the right way up Writing is inverted at 180 degreesIn frames 4 to 7, the written word 'Narration' is oriented upside-down (180 degrees).
-
Your view
-
seen · 95% confidentWriting is legible at video size Camera is overexposed and almost no content is writtenFrames 2 and 3 are completely overexposed/blown out white, frames 4 and 5 are blurry, and only a single word is scribbled in frames 6 and 7.
-
Your view
-
seen · 90% confidentThe work fills the frame Camera is poorly framed and switched to black screenFrames 1, 8, and 9 show a blank black screen, while frames 2 to 7 capture part of the paper along with a bedsheet.
-
Your view
-
seen · 90% confidentNothing distracting in shot Floral bedsheet visible alongside writing sheetA red floral patterned fabric is prominently visible on the right side in frames 2 through 7.
-
Your view
-
seen · 95% confidentThe student's problem is established No question is presented or statedOnly a generic topic label 'Narration' is visible across frames 1, 6, 7, 8, and 9 with no actual problem or question shown.
-
Your view
-
seen · 95% confidentWork proceeds in followable steps No structured steps or explanations shownAcross all frames, only the single word 'Narration' is written in frames 6-7 before returning to a black screen in frames 8-9.
-
Your view
-
seen · 95% confidentIt reaches an answer No working or solution is providedNo content or problem solving is attempted throughout the frames, ending on a blank screen in frames 8 and 9.
-
Your view
-
measuredSomething was actually written Not applicable to a camera session
-
heardThe concept is named before the working Not assessedOnly 62 characters of speech after cleaning (100 were the language-detection artefact) — too little to judge teaching from.
-
Your view
-
heardExplained rather than jumped to the answer Not assessedOnly 62 characters of speech after cleaning (100 were the language-detection artefact) — too little to judge teaching from.
-
Your view
-
heardSolved step by step, not in one leap Not assessedOnly 62 characters of speech after cleaning (100 were the language-detection artefact) — too little to judge teaching from.
-
Your view
-
heardThe session opens properly Not assessedOnly 62 characters of speech after cleaning (100 were the language-detection artefact) — too little to judge teaching from.
-
Your view
-
measuredNo long dead air 0 gaps over 6.0s, 0s total (0% of the session), longest 0sSilence is below -35.0dB — a crude measure on a phone microphone, so treat a low count as weak evidence rather than proof the tutor was talking.
-
Your view
Observations judged, but not counted as the lab objecting
-
measuredThe camera holds still picture moves 40.0 on average between keyframes, 2.7 hard jumps/minConsistent with the camera being handheld — a stand would remove this entirely. A handheld phone measured 35.1. No steady-camera session has been measured yet, so the lower band is a guess.Not counted: Measured over 183 known-bad and 29 known-good camera sessions (2026-09-21): raised on 87% of the bad and 86% of the good, and the motion distributions are the same shape — median frame difference 25 on the bad set, 27 on the good. No threshold on this number separates them, so it is reported and not counted.
-
Your view
-
measuredExposure is usable average brightness 115.6, 9.6% of frame very dark, 13.8% blown outBlown-out share is reported but not judged: the subject is white paper, so a good session measures 11-24% there too.Not counted: Same two sets: it raised 6 of 183 known-bad and 2 of 29 known-good sessions. Both too few to mean anything, and the brightness distributions overlap almost exactly. The earlier reading that it 'fires more on clean sessions' was two sessions out of twenty-nine — noise, not an inverted rule.
-
Your view
-
heardUnderstanding of the concept is checked Not assessedOnly 62 characters of speech after cleaning (100 were the language-detection artefact) — too little to judge teaching from.Not counted: Raised on 87% of known-bad and 80% of known-good sessions. The criterion is honest about why in its own `why`: the transcript has no speaker labels, so a real check and a rhetorical 'ok?' are often indistinguishable, and the bar ends up one almost no session clears. Still judged and shown, because reading it beside a recording is how it gets better.
-
Your view