Exact selected lineage
HeyDonto Labs; responsible contact Reza Nehzati, Ph.D. (profile).
The private N3 backbone is the uniform FP32 mean of S1001, S1003 and S1004 at step17535, serialized in BF16. Its combined named-shard digest is a78c72786e43b779ab886d583d9a7da3fb6ed07e026b681cc8a7270b216acf8e. Its 18 files are retained byte-for-byte, including its private config and processor metadata.
The selected main continuation is original-n3-main-lr2e5-step000900: learning rate 2e-5, seed908, gradient accumulation8. The selected prefix contains 7,200 draws and 4,130 unique rows from the eligible 7,207-row continuation training population. Its adapter is 0240d87b…, rank16/alpha32, 15,335,424 parameter elements. Serving retains one FP32 default LoRA on the BF16 N3 backbone, unmerged. Later producer steps and exposures are not attributed to this checkpoint.
The selected temporal continuation is original-temporal-lr5e6-step000600: learning rate 5e-6, seed908, gradient accumulation8. The selected prefix contains 4,800 draws and 2,912 unique rows from the eligible 4,680-row population. The 87fc446a… checkpoint contains the complete updated adapter initialized from a47; a47 must not be applied as a second adapter. The serving configuration is the exact normalized 0ff6dad4… file, while producer config d621c666… remains separately identified. The frozen temporal loader applies it once to public Qwen revision0c351, then merges at initialization.
The inherited N3 source corpus 4b1ee90b… contains 46,758 rows: 33,581 organizer rows, 4,621 paraphrases, 5,217 count rows, 2,317 convention rows and 1,022 adopted human-review rows. The continuation corpus 66362830… is separate. Official-only new continuation does not erase inherited clinical/development exposure. Historical temporal smoke/full populations and the owner-reported human-labeler/eligibility interpretation remain separate disclosures; no new organizer eligibility decision is asserted.
The private annotation packet ee69dafa… retains the known 13,177 derived rows across four JSONL files. It excludes all 33,581 organizer rows and video pixels; row locators and review statements do not establish complete signature custody or redistribution permission. ANNOTATION_SCOPE.json lists exact counts and hashes. Its intended private organizer venue is a preserved owner decision; actual access and delivery receipts must be recorded independently.
The six inherited prior files remain byte-identical. cholec_priors_v38.json arose from zero-shot OWLv2 detections on 613 frames from 10 CholecTrack20 videos; it is not a new optimizer-training corpus. The remaining duration, quadrant, stem and mode tables retain their organizer-training provenance. No v40 prior or obsolete neural checkpoint is included.
The original forward candidate changed the frame sampler (cd146570…). The later R3 compatibility derivative additionally fixes image-owned SEGMENT routing in cap_fmt_inferrer.py and records exactly attributed pre-generation deferrals in its bootstrap; the original timestamps, sampler/model behavior and all other 51 serving files remain unchanged. Public Qwen, private N3, both selected adapters, all six priors, prompts, precision, frame limits and generation settings are unchanged. TRAINING_RESOURCES.json preserves selected-save timing/peak scopes and producer identities; MODEL_IDENTITY.json preserves every selected file identity.
The known derived packet contains all 13,177 listed extensions: 4,621 paraphrases, 5,217 count remints, 2,317 convention remints and 1,022 adoption rows. Exclusion of the 33,581 organizer rows is intentional, not evidence that those rows must be republished. The unresolved items are the separate private annotation URL/access/delivery receipts and complete signature provenance.
R4 serving compatibility update
R4 local runtime, archive and import checks completed; official platform qualification remains unproven. The exact archive is e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00 (35,613,293,722 bytes), immutable generation 1789092734891901. The build manifest is ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0 and configuration 3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4. Full compressed/raw archive verification covers all 26 ordered DiffIDs; actual same-generation classic Docker import reports config 3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4 and no imported manifest digest. The agreed eight cases completed 9 application invocations and 1593 answer executions across 533 unique qIDs. Healthy20 and loose/ZIP500 matched saved content; reverse20 matched the same-image ordinary20, and both ZIP quotas matched the same-image loose500. Canonical repeated calls retained the exact disclosed deferrals. The mixed recovery case blanked only its declared failed questions and preserved later healthy outputs. These are bounded runtime/interface/content checks; no new semantic grade or official final result is claimed.
R4 retains the image-owned literal SEGMENT task and the original request clocks. It stages only the selected ZIP member for each startup probe or answer, verifies that member through CRC/EOF and SHA-256, closes decoder handles, and removes the lease before continuing. Loose input remains a direct read. Model initialization is still eager. An attributed ordinary per-question exception produces empty content for that qID with measured latency and failure telemetry; successful answers are preserved and later questions continue. Unsafe or ambiguous archives, source mutation, cleanup integrity, required model initialization, environment and fixed-track failures remain fatal. The inherited precise pre-generation rules deferrals remain separately disclosed as degraded coverage. The four changed image files are the bootstrap, contract, probe entrypoint and new ZIP helper; all 51 unchanged inherited serving source files, including cap_fmt, all 50 model/prior assets, prompts, model arithmetic and generation settings remain unchanged.
The full retained ZIP500 was qualified locally at the stated 4 GiB and 16 GiB tmpfs profiles, alongside loose500, healthy20, reversed20, default and persistent canonical calls, and controlled recovery. These fixtures do not establish the platform scratch quota, all possible input sizes, continuous resource peaks, cold-cache requirements, general order invariance, new semantic scores, independent-holdout performance or official platform success. Canonical deferrals and deliberately failed recovery rows are reduced scientific coverage. The prior R3 4 GiB eager-ZIP failure is a conditional local capacity reproduction, not proof of the organizer failure cause. Earlier images and failed attempts remain historical.