Run #782
done
rubric v1
session 79220225
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 · 100% confidentWork is the right way up Orientation is upright at 0 degreesAll frames (1-8) are oriented upright (0 degrees).
-
Your view
-
seen · 95% confidentWriting is legible at video size Handwriting is clearly legible against the dark backgroundHandwritten trigonometric formulas in Frames 2 to 8 are written with reasonable size and contrast.
-
Your view
-
seenThe work fills the frame Not applicable to a board session
-
seenNothing distracting in shot Not applicable to a board session
-
seen · 95% confidentThe student's problem is established Student's revision request is captured on the screenFrame 1 shows the student's text prompt: 'mujhe trigonometry fanction ka all formula revision karana hai'.
-
Your view
-
seen · 90% confidentWork proceeds in followable steps Board is systematically organized and cleared by formula topicsFrames 2-3 cover Pythagorean identities, Frame 4 covers cot/cosec identities, Frame 5 covers compound angle formulas, Frame 6 covers tan addition formulas, and Frames 7-8 cover product-to-sum formulas.
-
Your view
-
seen · 85% confidentIt reaches an answer Session ends mid-formula on the last lineIn Frame 8, the tutor stops writing halfway through the formula for '2 cos A cos B = cos(A+B) - cos(A...'.
-
Your view
-
measuredSomething was actually written board went from 4.71% to a peak of 4.71% covered (+0.00 points), ending at 3.83%Effectively nothing was written.
-
Your view
-
heard · 90% confidentThe concept is named before the working Tutor explicitly states the topic being revisedIn the transcript, the topic is confirmed: 'I have to revise the formula of the Trignometry function.' and tutor proceeds with trigonometric identities.
-
Your view
-
heard · 85% confidentExplained rather than jumped to the answer Tutor sets expectations before listing formulasTutor establishes the revision plan at the start: 'So, I am writing here. Do you understand? First of all, you should remember this.' before writing in Frame 2.
-
Your view
-
heard · 90% confidentSolved step by step, not in one leap Formulas and their rearranged forms are derived stage-by-stageFrames 2, 3, 4, 5, and 8 show formulas appearing sequentially along with rearranged variations.
-
Your view
-
heard · 95% confidentThe session opens properly Tutor greets the student and clarifies the requestTranscript opens with 'Hello son, Rajkishore. Good morning, welcome to the Filo... Son, what did you tell me? I have to revise the formula of the Trignometry function.'
-
Your view
-
measuredNo long dead air 1 gaps over 6.0s, 6s total (2% of the session), longest 6sSilence 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 Not applicable to a board sessionNot 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.
-
measuredExposure is usable Not applicable to a board sessionNot 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.
-
heardUnderstanding of the concept is checked Tutor actively quizzes the student on formula values and transformationsTutor asks: 'Sine Sper X plus Cos Sper X. Tell me, what is its value?' and 'If I tell you, Cossack square x equal to how much?', prompting active student recall.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