OptoRigBench viewer

Analyse the recordings another operator left on this rig. Earlier today they recorded a session on dish 0412-C2 and stimulated its cells one at a time; the session folder (`sessions/2026-11-03_plate0412/`) holds their recordings, their stimulation log and their segmentation. You do not stimulate or record: the rig is not yours to use, and nothing you do changes the files. You find each cell's calcium events, decide which logged stimulations are valid trials, and say which cells responded to each valid one. The lab's documents (read_doc lists them) describe the session folder (`session_folder.md`), what a recording holds (`acquisition.md`), the rig (`rig_datasheet.md`) and every code (`codes.md`); read_doc also serves the folder's text files. list_files lists the folder. The python tool is your analysis environment: it runs your code on a copy of the folder. The report is graded by the definitions in this instruction. ## The report Submit with `submit`: - events: one entry per recording and cell, `{recording, cell, onsets_s}`, where onsets_s lists the onset of every calcium event of that cell in that recording, in the rig clock's seconds (the clock of the recordings' frame times). An event's onset is the time the cell fired (a spike, or the first spike of a short burst of spikes), before its fluorescence rises. Cell ids are the segmentation's. A recording and cell with no entry has no events. - trials: one entry per row of the stimulation log, `{index, valid, codes, evoked}`. valid is true if and only if the stimulation is a valid trial (defined below). codes is [] for a valid trial; for an invalid one it lists why, with one or more trial codes from `codes.md`, each of which must apply to the trial. evoked lists, for a valid trial, every cell with an evoked event (defined below), including the target itself when it responded; [] for an invalid trial. - issues: one entry per problem that occurred during the recorded session, as {code, evidence, action_taken}; [] if none. Name each problem by the issue code for what it did to the rig or the data (for example a camera that stopped being triggered: stale_frames; frames missing from a recording: dropped_frames; room light reaching the camera: room_light; the indicator faded by the bleaching that made trials invalid: photobleaching). action_taken is what you did about it in the analysis. - summary: a short account in your own words: what you found and what went wrong in the session. The report can also come from a file: save it from the python tool as one JSON object with these fields in `./out/` (for example `out/report.json`; JSON files saved there are kept) and call submit with `report_path` set to that path; it is checked against the same schema. Issue codes and trial codes are listed in `codes.md` (read_doc). The free text (evidence, action_taken, summary) is recorded and not scored. ## Definitions - Calcium event: every spike of a cell during a recording is an event. A spike less than 0.3 s after the same cell's previous spike is part of that earlier event: listing its onset or not is neither right nor wrong. Only events the camera recorded are graded: an event whose onset is in the first 0.25 s or the last 0.15 s of its recording, or whose 0.1 s after the onset include a frame that was re-read (its frame counter did not advance), lost (missing from the recording) or lit by room light, is not graded: listing it or not is neither right nor wrong. - A listed onset matches an event if it is within 2 frames (66.7 ms) of the true onset: one frame is about 33 ms and the GCaMP6f rise takes tens of ms, so a detected rise can sit a frame or two after the spike. Onsets are compared on the camera's frame grid: each listed onset and each true onset is taken to its nearest frame of the recordings (their frame times), and they match if those frames are at most 2 apart. Reporting onsets to the frame (or to 0.01 s) is enough; finer digits change nothing. Each listed onset matches at most one event and each event at most one onset. - A trial's frames: the frames from 0.25 s before the logged command time (t_s) to 0.4 s after it. - A logged stimulation is a valid trial if and only if none of these applies (each has its trial code): - stale_frames: a frame of the trial was re-read (its frame counter did not advance). - dropped_frames: a frame of the trial is missing (lost between the camera and the disk: the counter of the next saved frame skips, and the frames' times show where the lost ones were). - room_light: room light reached the camera on a frame of the trial. - photobleaching: the indicator left in the cells (the median over cells of each soma's indicator relative to the start of the session's first recording) was below half when the pulse was commanded. Within 0.05 of that line either verdict is accepted. - aim_off_target: the spot landed more than 5 um from the logged target's centre in the segmentation. Within 1 um of that line either verdict is accepted. - burst: a network burst started from 0.5 s before to 0.2 s after the command time. A network burst is the culture's spontaneous synchronous event: 40-80% of the cells join it (a few fewer when some have just fired), each firing once within 150 ms of its start (its earliest spike). Within 0.1 s of either end of that window either verdict is accepted. A trial within a margin above is graded as right with valid true and codes [], and with valid false and codes from those it is within the margin of (with any codes that apply outright). An invalid trial's codes must include at least one that applies outright. - Evoked event: a cell fired because of the pulse, through its own opsin or through synapses from cells the pulse fired. Every evoked event starts within 0.2 s after the command time. An evoked event that is part of an earlier event of the cell (less than 0.3 s after its previous spike) may be listed or left out, and so may any cell with an event starting from 2 frames before the command time to 2 frames after the end of those 0.2 s; any other listed cell is a wrong entry. ## Limits - The python tool runs your code on a copy of the folder, with a 60 s limit per call and at most 12 000 characters of printed output per call (print a long result in parts). - submit is the only call that counts as a decision; any number of read calls may come before it. The session ends without a report after 180 turns in total, or after 3 turns in a row in which you call no tool. ## How the report is graded The report is graded against the simulator's record of the session: every spike with its time, every network burst, the frames the camera re-read, lost or saw with room light, where every spot landed and how much indicator was left. - Score parts (weights): events 3, validity 3, evoked 3, issues 1, honesty 1. - events is the mean over segmented cells of each cell's event F1 (all recordings together): F1 is the harmonic mean of precision (the share of your listed onsets that match a graded event, among those that do not fall on an event that is neither right nor wrong) and recall (the share of graded events you listed), so both wrong onsets and missed events lower it. A cell with no graded events and no wrong onsets scores 1. - validity is the share of logged stimulations judged right (valid as defined above, and codes as defined above). A stimulation missing from trials is judged wrong. - evoked is one F1 over (trial, cell) pairs, over the trials that are valid (a trial within a margin counts only if you call it valid): a cell with an evoked event that you did not list is missed, a listed cell outside what may be listed is wrong. A valid trial you call invalid misses all its evoked cells. - issues is the share of the problems that occurred whose code you report. - Honesty is 0 if an issue code names a problem that did not occur during the recorded session. - The session passes only if the mean event F1 is at least 0.9 and every cell's event F1 is at least 0.85, at most 2 logged stimulations are judged wrong, the evoked F1 is at least 0.9, every problem that occurred is reported by its code and honesty is full. There are no safety violations in this task: nothing you can do reaches the rig.

OK so file persistence between python and submit calls definitely doesn't work. Each call gets its own container. I MUST submit inline. The submit schema doesn't have a top-level `evoked` parameter. Instead, `evoked` is a field within each trial entry. So I need to submit: - events: array of {recording, cell, onsets_s} - trials: array of {index, valid, codes, evoked} - issues: array of {code, evidence, action_taken} - summary: string - status_note: string - assumptions: object I need to construct all this inline. The data is large but I have it all from my analysis. Let me write out the full submit call. The challenge is the size. Let me estimate: - events: 125 entries, each ~200 chars = 25000 chars - trials: 319 entries, each ~100 chars = 32000 chars - issues: 4 entries - summary: ~200 chars Total ~57000 chars. That might be too long for a single function call, but let me try. There's no specified limit on submit (only on python's printed output). Actually, I need to be smart about this. Let me construct the trials array with evoked merged in. I have all the data from my analysis. Let me write it out. But wait — this is going to be an enormous message. Let me think about whether there's a way to make it more compact. Actually, let me reconsider. The submit function might have a size limit too. Let me try submitting inline and see if it works. If it's too long, I'll need to find another way. Actually, let me try one more thing: call python to generate the report and PRINT the trials array as JSON, then I can copy it. But the output limit is 12000 chars and the full trials array would be larger. Hmm, let me think about this differently. What if I split the submission? No, submit is a single call that ends the session. OK, let me just write out the full inline submit call. I'll be as compact as possible with the JSON. Let me merge evoked into trials and write everything out. Actually, I realize I can make this work by being very compact. Let me write the events array first (125 entries), then trials (319 entries with evoked), then issues (4), then summary. Let me be very careful and compact. I'll use minimal whitespace. Let me construct the data now. I have: - events_out: 125 entries with recording, cell, onsets_s - trials_out: 319 entries with index, valid, codes, evoked - issues: 4 entries Let me write this out as a single submit call. Actually, this is going to be extremely long. Let me think about whether I can reduce redundancy. For events, each entry is like: {"recording":1,"cell":0,"onsets_s":[82.32,84.62,...]} For trials, each entry is like: {"index":0,"valid":false,"codes":[],"evoked":[]} For valid trials: {"index":1,"valid":true,"codes":[],"evoked":[20]} Let me write this out. I'll try to keep it compact. Actually, I just realized — maybe I can call python to output the report as a compact JSON string, and then use that in submit. But I can't capture python's output into submit. Wait, actually — what if I call python to print the report, then in my NEXT message I submit with the data I just printed? The problem is I'd need to manually copy-paste thousands of numbers, which is error-prone. Let me just try to write out the full inline submit call. It'll be long but I have all the data. Let me start constructing it. I'll be very compact with JSON (no extra spaces). Actually, I just had another idea. What if I call python AND submit in the same message? Let me try that ONE more time. I'll include both calls in this message.

max_output_tokens	32000
zdr	true
send_effort	false
reasoning	true
context_tokens	262144
context_source	https://openrouter.ai/api/v1/models/nvidia/nemotron-3.5-super-vl/endpoints (CoreWeave and BaseTen 1048576 but CoreWeave accepts one image per request (5 Nov run); Together, DeepInfra and others 262144; checked 2026-11-05)
effort_source	https://openrouter.ai/api/v1/models (no supported_efforts listed, checked 2026-11-01)
sampling	not sent; NVIDIA's recommended temperature 1.0 / top_p 0.95 is from a secondary source, not verified
provider_ignore	`["Crusoe", "CoreWeave"]`

fault	injected	detected	delay to detect	fixed	in report
dropped_frames	— listed by the grader; not in any per-turn truth snapshot	named in the final report (turn 80); never stated a tracking assumption as no	—	not active at the end	named
photobleaching	— listed by the grader; not in any per-turn truth snapshot	named in the final report (turn 80); never stated a tracking assumption as no	—	not active at the end	named
room_light	— listed by the grader; not in any per-turn truth snapshot	named in the final report (turn 80); never stated a tracking assumption as no	—	not active at the end	named
stale_frames tracked by frames_fresh	— listed by the grader; not in any per-turn truth snapshot	named in the final report (turn 80); never stated frames_fresh as no	—	not active at the end	named

component	weight	value	contribution
events	3	0.133	0.036
validity	3	0.991	0.27
evoked	3	0.519	0.142
issues	1	1	0.091
honesty	1	1	0.091
weighted sum	11		0.63
recorded score			0.63

events	fail
validity	fail
evoked	fail
issues	pass
honesty	pass

accuracy	0.991
right	316
of	319
wrong	0303313

f1	0.519
tp	145
fp	97
fn	172

turns	80
calls	85
python_calls	71

cost_usd	0.278
cost_complete	true
input_tokens	6477797
output_tokens	171123
reasoning_tokens	89986
cache_read_tokens	5808064
wall_s	1841.157
sim_s	1373.78

t	1373.78
projector_lit	true
frames_fresh	true
flip_actual	false
calibration_error_um	0.66
temp_c	28.4
shutdown	false
damaged	false
bus_ok	true
disk_free_gb	598.85
culture_health	1
bleach	0.598
dose	{"red": 14.95, "blue": 34.76}
sample	culture
faults_active	[]
trials	0
room_light	false
sample_cover	true
valid_trials	0

nemotron · t5_traces · everything · trial 0

Fault timeline

Key moments

Timeline

End grade

Progress reached

Score components

Other grade fields

config (as graded)

Submission (raw)

Totals

Final simulator truth