Cell Segmentation

Outline each cell body in a fluorescence image, then score the predicted boundaries against a human annotation.

Segmentation comparison

Microscopy field512 × 383 px
Cultured neural cells with green cytoplasm surrounding bright red nucleiOriginalSegmented

Drag the divider to compare the original image with the predicted contours. Select a cell to inspect its outline.

Task & tools

Cultured Neurons

Loading task description…

Where to draw

Follow the outer edge of the cell body. Include clearly attached cytoplasm, keep touching cells separate and stop at the image boundary for partially visible cells.

Available tools

One supplied image and its instructions. No model-side tools, code execution, browsing, external models or additional data. The harness saves the final JSON response as answer.json.

Unmodified solver input. Select the image to inspect its original pixels.
Agent Context
instruction.mdDownload
Open Agent Context to read the files.

Protocol

  1. Find the cell body

    Look for a visible body around the nuclear signal. Trace neighboring bodies separately where they touch.

  2. Walk the boundary

    Record the ordered vertices of each outline. Use the original 512 × 383 pixel grid, with x increasing to the right and y increasing downward. At the image edge, trace the visible portion.

  3. Submit the rings

    Group each cell’s rings into one JSON entry. The verifier closes the rings, fills their interiors and matches the predicted objects to the human annotation.

Rubric

Continuous segmentation score

Loading the score definition…

Try an overlap

Move the predicted square across an example reference square. The overlap divided by the combined area determines whether this pair matches.

ReferencePrediction

No binary pass threshold was declared for this delivery. Empty or malformed submissions score zero. Reported scores measure segmentation agreement on this image; they do not establish biological health or performance across a dataset.

Runs & evidence

Observed model results

Loading scored-attempt counts…

Selected case: continuous model scores
Model / effortMeanSample SDRangeScored / attempted

Three scored calls per model on the Cultured Neurons image. Range and sample SD describe these calls; they are not confidence intervals. No aggregate dataset leaderboard is claimed.

Individual attempts & settings

Historical traces are excluded. Each row identifies its native result and request checksum in the downloadable record. Full raw traces and configurations remain in the reviewer delivery.

TrialModelScore / outcomeRequested output limitObserved input / output tokens

Download scores, run settings & source hashes

QC & findings

The original delivery’s six-question QC is shown below. These question labels are distinct from the repository’s Step 5 and Step 6A/6B release workflow.

Delivery checkRecorded statusEvidence and scope
Q1B · Benchmark evidenceMissing evidenceObserved cohort analysis exists. A linked M4 contamination assessment is missing. Exploratory binary sensitivity was chosen after the runs and is not the primary score.
Q2 · Scientific groundingPassReal microscopy, human annotation provenance and workflow attestation. No measured expert performance baseline on this exact image.
Q3 · Runnable scoringPassSaved-answer scorer replay and nine targeted scoring probes. This verifies saved-output scoring, not deterministic model generation.
Q4B · Criteria-based rubricNot applicableContinuous segmentation metrics; no criteria-based rubric or M12/M13 ratio.
Q5 · Training retentionNot applicableBenchmark only; no training or retention experiment.
Q6 · ArchitecturePass · exploratory scopeSaved Harbor 0.24.0 / Modal runs, host-side Bedrock requests, no model-side tools or automatic retry; observed concurrency up to three. No buyer-load reliability qualification.

This package establishes completed exploratory delivery. Full Step 5 approval, Step 6A/6B qualification and contamination clearance are not established by this evidence.

Sources & limits

Original reviewer delivery · GitHub access required

Artifacts are dated October 27, 2026; the release was published November 12, 2026. Reference masks, reference answers and gold-derived overlays are kept outside this website. The overlay shows model predictions from the six delivered answers. The results record identifies each answer file and its checksum.