Sixty-seven recordings through the whole loop - #512
Merged
Conversation
…pend what #507-509 bought The full senktide (29) and TTX (38) cohorts, artifact-excluded, assessed at K = 10% of each recording's ROI population floored at 3, simulated from their own baseline, calibrated and trained on 72 held-out simulated recordings, detected at that calibration with those trained models, and drawn as 24 pages -- twelve detectors x two treatments, four group facets x two streams each. Everything derived from the recordings is in the darkroom, per FOUNDATIONS §5. This handoff is the pointer and carries no such number; the run record beside the artifacts carries all of them. WHAT IS DIFFERENT FROM THE PILOT is most of what mattered. Both of pipeline.md's blockers closed yesterday and this run is the first to spend them: the six ran at a calibration derived from this cohort's own simulated data rather than at shipped operating points, and all six learned models ran from checkpoints in a separate process from training. Two more things the pilot could not do: background heterogeneity was FITTED from the folder rather than inherited -- eighty-four baselines where the pilot had six -- and the input was the producer's artifact-excluded export rather than a folder nobody had scanned. WHAT IT COST TO GET THERE is in #511: the newest export had been on disk six days with no file in this repo naming it, K as a percentage had no floor, derive_spec could only work at one absolute K, and the figure had no group facets and clipped its own fourth column. THE EDGE-OF-GRID ASYMMETRY is filed rather than left in a transcript. `tube` is the best learned model on this cohort and its deployed threshold sits at the top of the searched grid. The coded branch treats that as a refusal in terms -- "an optimum at the edge is not an optimum, it is the search telling you it stopped too early" -- and the learned branch warns and ships. The todo does not assume which side is right: for a probability threshold an edge may mean the model separates cleanly, and there is one measurement that tells the two apart. Nobody has run it. THE FIREFLIES NOTE IS MARKED AS A DRAFT AND MUST NOT BE SENT. It is addressed to another team, which makes it a document deliverable, and it has not been reviewed or released. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The full senktide (29) and TTX (38) cohorts through every step of
pipeline.mdexcept MAHICE, which Tony instructed be skipped.This branch is the record, not the results. Everything derived from the recordings is in the darkroom (FOUNDATIONS §5); the handoff here is the pointer and carries no such number.
What is new about this run
Both of
pipeline.md's blockers closed on 2026-09-08, and this is the first run to spend them:The finding filed here
tubeis the best learned model on this cohort and its deployed threshold sits at the top of the searched grid. The coded branch treats an edge-of-grid optimum as a refusal, in terms — "an optimum at the edge is not an optimum — it is the search telling you it stopped too early" — while the learned branch warns and ships. So the best learned detector here runs at a threshold the other branch would not publish.The todo deliberately does not assume which side is right: for a probability threshold in (0, 1) an edge may mean the model separates cleanly and any high threshold works rather than the search stopped too early, and those want opposite responses. One measurement tells them apart and nobody has run it.
Not reviewed
Neither this handoff nor the darkroom run record is murderboarded — both are working material, the same standing as
pipeline.md. The one artifact addressed to another team,for_fireflies/README.md, is marked as a draft and must not be sent until reviewed and released.🤖 Generated with Claude Code