# Serving and runtime qualification

The current artifact is the R4 container identified in [IMAGE_IDENTITY.json](IMAGE_IDENTITY.json). HeyDonto Labs confirmed its successful finals submission, with no errors reported, on September 14, 2026. The exact confirmation scope is recorded in [SUBMISSION_STATUS.json](SUBMISSION_STATUS.json).

## Container identity and interface

| Identity | Value |
| --- | --- |
| Archive SHA-256 | `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00` |
| Archive size | 35,613,293,722 bytes |
| Immutable GCS generation | `1789092734891901` |
| Docker image/configuration SHA-256 | `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4` |
| Build OCI manifest SHA-256 | `ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0` |

Archive, configuration and manifest hashes identify different objects. The same-generation archive passed full gzip/CRC/tar verification, all 26 ordered layer DiffID checks and an actual classic Docker import. That import exposed the configuration identity but no imported manifest digest.

The container runs as user `app` from `/app`, with entrypoint `/opt/conda/bin/python -I -S /opt/orena/segment/bootstrap.py` and offline model settings. It reads the SEGMENT request, FO definitions and per-question clips, supplied loose or in ZIP archives, and writes `/output/answer.json`. The container always uses the SEGMENT task. Question times retain the original source-video clock.

## Input handling and recovery

R4 stages one selected ZIP member at a time for a startup probe or answer, verifies it through CRC/EOF and SHA-256, closes decoder handles and removes the staged file before continuing. Loose clips are read directly. Model initialization remains eager.

A recoverable error attributed to one question produces an empty answer for that qID, with elapsed latency and failure telemetry, while successful answers are retained and later questions continue. Unsafe or ambiguous archives, source mutation, cleanup-integrity failures, required model initialization failures, environment violations and fixed-track failures remain fatal.

Existing pre-generation deferrals to rules remain separately recorded. A valid output file can therefore include rule-based or empty answers; it does not establish healthy neural inference for every question.

The four R4 wrapper files are available under [platform_wrapper/](https://huggingface.co/HeyDonto/SURGFIELD-ORena-2026-SEGMENT-FINAL/tree/main/platform_wrapper). The 51 inherited serving source files and all 50 model/prior assets remain unchanged from R3, as do prompts, model arithmetic, frame limits and generation settings.

## Measured local coverage

The H100 qualification matrix completed eight test cases and nine application invocations, producing 1,593 answer executions across 533 unique qIDs:

| Test condition | Observed result |
| --- | --- |
| Ordinary and reversed 20-question inputs | Ordinary outputs matched the saved reference; reversed outputs matched the same image's ordinary outputs. |
| 500 loose clips | All contents matched the saved candidate reference. |
| The same 500 clips in ZIP archives, with 4 GiB and 16 GiB scratch limits | Both runs matched the same image's loose-clip outputs. |
| Default and repeated canonical calls | Outputs retained the three documented pre-generation deferrals. |
| Controlled 23-question recovery fixture | Exactly three intended empty answers; all 20 healthy outputs preserved. |

The independently measured 500-question runtimes were approximately 1,226.6–1,267.1 seconds. [PLATFORM_COMPATIBILITY.json](PLATFORM_COMPATIBILITY.json) and [EVALUATION.json](EVALUATION.json) retain the detailed identities and measurements. Content agreement is distinct from semantic accuracy; repeated questions and deliberate failures are included in these counts.

## Failure history and remaining limits

R3's eager extraction of the retained approximately 21 GB, 500-clip ZIP reproduced an `ENOSPC` failure locally with 4 GiB scratch, before model loading. R4 completed that fixture at the same scratch limit. This establishes a repaired local capacity failure, rather than the cause of the earlier platform submission failure, whose failing-case logs were not captured.

Earlier images also exposed input-alias and canonical-interval admission issues. Their tests and failures remain historical in [EVALUATION.json](EVALUATION.json) and the [immutable prior compatibility report](https://huggingface.co/HeyDonto/SURGFIELD-ORena-2026-SEGMENT-FINAL/blob/24133f8d4a491845db2a19c84c2d182f8b4e4831/PLATFORM_COMPATIBILITY.md). Narrow successful tests did not cover all later failure conditions.

The local matrix does not establish universal input-size limits, general order invariance, continuous resource peaks, cold-cache requirements or the organizer's scratch allocation. Sampled resource maxima, independent elapsed times and self-reported answer latencies are separate measurements. Actual submitted resource settings and terminal platform logs have not been independently recorded here. Successful submission supplies no official answer-quality score; see [EVALUATION.md](EVALUATION.md).