Evidence workspace

See what the video supports—and what still needs asking

Inspect speech and on-screen text alongside timecoded visual observations, attention, motion, and hand landmarks. Missing expert judgment is not inferred.

Speech ledger · Missing analysis is not inferred

07

Speech + on-screen text

00

Direct visual observations

587

Visual annotations + derived cues

12

Real model artifacts

00

Interview probes

Titans of CNC · 0:59 · 0b61f470ae71

Original source · Human review pending

Timecoded source evidence

7
Evidence 01
So there's going to be three components that make up our RID spindle. There's going to be the main shaft, the mounting arbor, which gets threaded directly into the main shaft, and then once it's all the way threaded in, we mount our wheel. Today we're going to be using a TeraLit RAA 100 grit pink wheel. So in order to mount this wheel, the first thing I did was I scuffed up the face with a file,

spoken statement · segments 0, 1, 2, 3 · human review pending

Evidence 02
wheel. So in order to mount this wheel, the first thing I did was I scuffed up the face with a file, that way it gives the epoxy a good bonding surface. Then I'm going to spray it with a little bit of

spoken statement · segments 3, 4 · human review pending

Evidence 03
alcohol. So once that's clean I'm going to go ahead and start mixing my epoxy. I'm going to start with the resin then I'm going to add some hardener and I'm going to use a coffee stir stick.

spoken statement · segments 5, 6 · human review pending

Evidence 04
First thing I'm going to do is I'm going to coat the face of my arbor. Now all I have to do now is

spoken statement · segments 7 · human review pending

Evidence 05
mount my wheel to my arbor. So it's just going to drop down give it a nice little spin put some

spoken statement · segments 8 · human review pending

Evidence 06
epoxy in the center of the wheel. Very important to keep this wheel clean and have a good bond because this wheel is going to be spinning anywhere between 20,000 and 30,000 rpm. So that

spoken statement · segments 9, 10 · human review pending

Evidence 07
Looks good.

spoken statement · segments 11 · human review pending

02 · MULTIMODAL EVIDENCE

Visual evidence and machine observations

This separates literal video observations, authored attention, OpenCV-derived motion, and artifacts from models that actually ran. None of these alone establishes expert intent, rationale, quality, or safety.

Inspect overlays in Vision Lab
0Direct visual observations
587Visual annotations + derived cues
12Real model artifacts

Observations and model outputs support what is visible. What it means must be checked with a practitioner or separately cited existing knowledge.

01

Direct observations from the video

Literal descriptions of visible objects, orientation, possible contact, and movement only.

No direct visual observation has yet been admitted to this source bundle. The annotations and derived cues below remain visible, but they do not silently become expert knowledge.

02

Timecoded visual annotations and derived cues

Attention points, motion trails, hand landmarks, and related candidates. Play any card at its source moment.

03

Artifacts from visual models that actually ran

hand poseMediaPipe Hand Landmarker

Google · mediapipe-0.10.35:fbc2a30080c3

hand-clip-01.json
segmentationSAM 2.1 Hiera Tiny

Meta · facebookresearch/sam2@2b90b9f5ceec907a1c18123530e92e794ad901a4

keyframes.jsoncomponent-arbor-mask.pngcomponent-wheel-mask.pngepoxy-component-black-cap-mask.pngepoxy-component-red-cap-mask.pngmixing-hand-mask.pngmixing-tray-mask.png
segmentationSAM 2.1 Hiera Tiny video predictor

Meta · facebookresearch/sam2@2b90b9f5ceec907a1c18123530e92e794ad901a4

11000-14500-6fps.json13000-14500-6fps.json29500-30750-6fps.json29500-33000-6fps.json

Continue with this source

One source, five connected views

Switching views preserves the same source hash across instruction, analysis, skill structure, evidence, and human review.