EVALARC / COMPARISON

Compare outcomes.

support-routing · matched task, grader, cases, and runtime

0.9
baseline score
0.9375
current score
+0.0375
score change
1
regressed checks

2 improved checks. 1 current cases still fail. No regression is not the same as full resolution.

Changed outcomes

CaseSeedBefore → afterRegressed checksImproved checks
retry-after-commit17passed → failednotes
retry-before-commit17failed → passedclosure
route-open-ticket17failed → passedclosure

retry-after-commit

Seed 17 · passed → failed

Regressed: notes

Improved: none

retry-before-commit

Seed 17 · failed → passed

Regressed: none

Improved: closure

route-open-ticket

Seed 17 · failed → passed

Regressed: none

Improved: closure

Reproduction record

Grader SHA-256: 2dced2a842369299e6e924db626fedc120071d5731cd9b79202dba7395b90255
Cases SHA-256: b7cd8663c69da9e1715d5c8e1d707514863dcc333fefc57acc3315053ebc85df
Created: 2026-09-14T01:58:21.259930+00:00
Seeds: [17]
Runtime: {"backend": "docker", "image": "python:3.12-slim", "image_id": "sha256:78387bc3881b8273120a12ebe6c1ab22b018ccc2c9adf565ae1ac9b536e184ea", "command": ["{python}", "-I", "-B", "main.py"], "response_timeout_seconds": 10.0, "session_output_limit_bytes": 1048576, "python": "3.12.3", "platform": "Linux-6.17.0-1020-aws-x86_64-with-glibc2.39"}

Baseline candidate: a34429419d7c794420d43f7873ce5b1474f73821329f414609d5e4d18fc174c3

Current candidate: b89a99819c03e8290096ca268f637c5517d465b3ec5f0b5fe2b21c35509ff202

Comparison JSON · Baseline evidence · Current evidence