Stage
Disqualified
12 of 12 stages
Settled in
22h 06m
committed Sep 21, 18:54 UTC
Round score
—
awaiting round
p99 latency
—
ceiling 2000 / 50 ms
Round 6: disqualified · no score
12/12 stages
Intake & gates
6/6Patch hash recorded; awaiting fetch.
{
"hotkey": "5G4AVs54rV7unZdSsPGcnAeWUV9UcqjcSpLP9rxR2g4Dp5HF",
"payment_tx": 2,
"commit_block": 9117867,
"payment_block": 9117864,
"patch_fingerprint": "sha256:3df2e5692b0abb8450491cf2ed0ddcb2d7e4c8cc156bd15fc7e8e6b8e15ea52a",
"patch_reveal_delayed": true
}A worker claimed the submission and started the pipeline.
{
"job_id": 172
}Patch artifact retrieved from object storage.
{
"size": 387768,
"patch_hash": "sha256:a06ebe58d71d8dedb19892cf8fb86d33d88bf1b4dc5b3d3bacabf6b872d229eb"
}Integrity and path constraints checked.
{
"identity": "ok",
"patch_hash": "sha256:a06ebe58d71d8dedb19892cf8fb86d33d88bf1b4dc5b3d3bacabf6b872d229eb"
}Patch applied onto the baseline checkout.
{
"ok": true
}Public API / surface compatibility held.
{
"files": [
"python/sglang/kernels/ops/attention/fla/fused_sigmoid_gating_recurrent.py",
"python/sglang/kernels/ops/attention/fla/gdn_replayssm_deferred_fold.py",
"python/sglang/kernels/ops/attention/fla/gdn_replayssm_spec_decode.py",
"python/sglang/kernels/ops/attention/fla/layernorm_gated.py",
"python/sglang/kernels/ops/mamba/causal_conv1d_triton.py",
"python/sglang/kernels/ops/sampling/sharded_gumbel.py",
"python/sglang/kernels/ops/speculative/__init__.py",
"python/sglang/kernels/ops/speculative/topk1.py",
"python/sglang/srt/arg_groups/attention_hook.py",
"python/sglang/srt/arg_groups/speculative_hook.py",
"python/sglang/srt/distributed/device_communicators/fp8_a2a_all_reduce.py",
"python/sglang/srt/distributed/device_communicators/host_shm_ag_gemm.py",
"python/sglang/srt/distributed/device_communicators/host_shm_all_reduce.py",
"python/sglang/srt/distributed/parallel_state.py",
"python/sglang/srt/entrypoints/openai/serving_completions.py",
"python/sglang/srt/environ.py",
"python/sglang/srt/layers/attention/flashinfer_backend.py",
"python/sglang/srt/layers/attention/hybrid_linear_attn_backend.py",
"python/sglang/srt/layers/attention/linear/gdn_backend.py",
"python/sglang/srt/layers/attention/linear/kernels/gdn_triton.py",
"python/sglang/srt/layers/attention/linear/sn10_extend_graph.py",
"python/sglang/srt/layers/attention/mamba/mamba2_metadata.py",
"python/sglang/srt/layers/communicator.py",
"python/sglang/srt/layers/logits_processor.py",
"python/sglang/srt/layers/quantization/fp8_utils.py",
"python/sglang/srt/layers/quantization/modelopt_quant.py",
"python/sglang/srt/layers/sampler.py",
"python/sglang/srt/layers/sharded_greedy.py",
"python/sglang/srt/layers/sharded_sampling.py",
"python/sglang/srt/layers/sn10_fp8_splitk.py",
"python/sglang/srt/layers/sn10_oproj_allgather.py",
"python/sglang/srt/managers/io_struct.py",
"python/sglang/srt/managers/schedule_batch.py",
"python/sglang/srt/managers/scheduler.py",
"python/sglang/srt/managers/scheduler_components/request_receiver.py",
"python/sglang/srt/managers/tokenizer_manager.py",
"python/sglang/srt/mem_cache/kv_cache_configurator.py",
"python/sglang/srt/mem_cache/mamba_slot_fused.py",
"python/sglang/srt/mem_cache/memory_pool.py",
"python/sglang/srt/mem_cache/unified_memory_pool.py",
"python/sglang/srt/model_executor/cpu_graph_runner.py",
"python/sglang/srt/model_executor/forward_batch_info.py",
"python/sglang/srt/model_executor/model_runner.py",
"python/sglang/srt/model_executor/runner/decode_cuda_graph_runner.py",
"python/sglang/srt/model_executor/runner/prefill_cuda_graph_runner.py",
"python/sglang/srt/models/qwen3_5.py",
"python/sglang/srt/speculative/eagle_draft_cuda_graph_runner.py",
"python/sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py",
"python/sglang/srt/speculative/eagle_info.py",
"python/sglang/srt/speculative/eagle_utils.py",
"python/sglang/srt/speculative/eagle_worker_common.py",
"python/sglang/srt/speculative/eagle_worker_v2.py",
"python/sglang/srt/speculative/sn10_fp8_draft_head.py",
"python/sglang/srt/speculative/spec_utils.py"
]
}Build
3/3Hermetic engine image build in progress.
No structured detail recorded for this step.
Candidate engine image pushed to the registry.
{
"image_ref": "ghcr.io/pareton-ai/pareton-engine@sha256:d92125290d6dc8a79c0033b399b145f259a490bc8fff7ee12afafafd4be2c95e",
"image_digest": "sha256:d92125290d6dc8a79c0033b399b145f259a490bc8fff7ee12afafafd4be2c95e"
}Candidate engine image built and digest pinned.
{
"mock": false,
"build_log": "/var/log/pareton/builds/4f455030-d1c7-4f53-aec2-45604b780bf2/build.log",
"image_ref": "ghcr.io/pareton-ai/pareton-engine@sha256:d92125290d6dc8a79c0033b399b145f259a490bc8fff7ee12afafafd4be2c95e",
"image_tag": "ghcr.io/pareton-ai/pareton-engine:a06ebe58d71d8dedb19892cf8fb86d33d88bf1b4dc5b3d3bacabf6b872d229eb"
}Round
3/3Waiting to be seated in a round.
No structured detail recorded for this step.
Seated in a round; waiting to run or running.
{
"ordinal": 3,
"round_id": "1178de44-5591-4be7-b15a-55a3c03be145"
}The image ran and holds a round score.
{
"kind": "relative-degeneracy-four-prompt-allowance-v1",
"score": 0.6339530154046228,
"ordinal": 3,
"operator": "user-authorized Codex repair",
"round_id": "1178de44-5591-4be7-b15a-55a3c03be145",
"policy_pr": "https://github.com/Pareton-ai/pareton/pull/173",
"policy_commit": "e8959a8",
"previous_reason": "degenerate output (hf-023: distinct 16-gram ratio 0.814 is more than 0.10 below baseline 0.924 over 21924 chars)",
"previous_status": "disqualified",
"relative_degeneracy": {
"failed_prompts": 2,
"failed_request_ids": [
"hf-023",
"hf-024"
],
"max_failed_prompts": 4
},
"source_evidence_sha256": {
"bench_report.json": "bb36ae3399451c481beb8858117ad52fdc488cd06f2b1a93faa175c659d9d16c",
"bench_request.remote.json": "339df806bc1af19c23a38e5891ccc80923af05569aea2c9e4b546679657e4f6c",
"evidence/correctness/baseline.jsonl": "62c625d41fc882e44813b307be679b8f15e96f75d97d8ff4a675c2c881a1fec2",
"evidence/correctness/candidate_0.jsonl": "5b4cb3f3710511ece20afc1b17b2e6520df3e416ac0bc797dfba1e443657971e",
"evidence/correctness/baseline_exclusions.json": "1b762bbc54aa5b4569a5ea4495c93c95a0c480a2d1ce5e35a05e2a7bf13189b8"
}
}Other events
The image ran and produced wrong output.
{
"score": null,
"reason": "degenerate output (hf-023: distinct 16-gram ratio 0.814 is more than 0.10 below baseline 0.924 over 21924 chars)",
"ordinal": 3,
"round_id": "1178de44-5591-4be7-b15a-55a3c03be145"
}The image ran and produced wrong output.
{
"score": null,
"reason": "degenerate output (hf-029: rep 1: longest repeated span ratio 0.341 at or above harness ceiling over 20210 chars)",
"ordinal": 6,
"round_id": "42477d44-c32a-48d4-a844-4059d8e2b661"
}The image ran and produced wrong output.
{
"kind": "repeated-span-four-prompt-allowance-v1",
"score": null,
"ordinal": 6,
"operator": "user-authorized Codex repair",
"round_id": "42477d44-c32a-48d4-a844-4059d8e2b661",
"policy_pr": "https://github.com/Pareton-ai/pareton/pull/175",
"new_reason": "degenerate output (baseline-relative repetition failures exceed allowance of 4 prompts (hf-029: distinct 16-gram ratio 0.537 is more than 0.10 below baseline 0.652 over 20210 chars))",
"new_status": "disqualified",
"policy_commit": "a951858d18c1b9d799c9a416f34b197b397a12e6",
"leader_decision": {
"event": "overtaken",
"prev_score": 0.6214243148870308,
"void_reason": null,
"leader_score": 0.6271758502694322,
"overtake_threshold": 0,
"prev_submission_id": "4f455030-d1c7-4f53-aec2-45604b780bf2",
"leader_submission_id": "a3591f40-bd28-412b-803b-942fda0c6c3a"
},
"previous_reason": "degenerate output (hf-029: rep 1: longest repeated span ratio 0.341 at or above harness ceiling over 20210 chars)",
"previous_status": "disqualified",
"relative_degeneracy": {
"failed_prompts": 5,
"failed_request_ids": [
"hf-020",
"hf-022",
"hf-025",
"hf-027",
"hf-029"
],
"max_failed_prompts": 4
},
"source_evidence_sha256": {
"bench_report.json": "e509a5a049970a2f52b137baeba49db781aa9b410c17588d8976ce2f3eb15e75",
"bench_request.remote.json": "eff51d8f24da6a1c562648e10ac8b457f5b60e464dd209479a350c4af692b155",
"evidence/correctness/baseline.jsonl": "3691dfd98b636b4597b2feb2dfb2642cc909fa3909b82e41890b3ff0dc053ac7",
"evidence/correctness/candidate_0.jsonl": "84fe7768aefe0dad1b7661c0438afb6457a863ff5a5ca5ca3cce92fd4f1c1b58",
"evidence/correctness/candidate_1.jsonl": "1443a2b84106a615ac04e9cbcf8290b7b5676f3f0805b9ca6fc04cd9c0cd417e",
"evidence/correctness/candidate_2.jsonl": "5bdc850fd2f525536c97b72499488738744c5b6ebefbae4fb2093dbabf20fe8a",
"evidence/correctness/candidate_3.jsonl": "005e0040224ffcf4429bc53f7f27d7a1902190bfbbaa1a2a2b5e2da88b2ea760",
"evidence/correctness/candidate_5.jsonl": "76f198ab6393f06c0cbe13d7b80e564c6b4a904e62841736fab0a6e30aa8c3f3",
"evidence/correctness/baseline_exclusions.json": "7ff1521f01e8ee03ce2549a0eaacc82537ba561d8d8a572124d23a33a7a79f0b"
},
"repeated_span_degeneracy": {
"failed_prompts": 1,
"failed_request_ids": [
"hf-029"
],
"max_failed_prompts": 4
}
}