iiRecord
Agentic AI Atlas · Should EvalRun be merged with Run?
open-question:benchmark-run-primitivea5c.ai
II.
OpenQuestion JSON

open-question:benchmark-run-primitive

Structured · live

Should EvalRun be merged with Run? json

Inspect the normalized record payload exactly as the atlas UI reads it.

File · catalog-meta/open-questions/benchmark-run-primitive.yamlCluster · catalog-meta
Record JSON
{
  "id": "open-question:benchmark-run-primitive",
  "_kind": "OpenQuestion",
  "_file": "catalog-meta/open-questions/benchmark-run-primitive.yaml",
  "_cluster": "catalog-meta",
  "attributes": {
    "displayName": "Should EvalRun be merged with Run?",
    "description": "Whether benchmark eval runs share enough lifecycle semantics with\nruntime Runs to unify them into a single primitive in v2.\n",
    "owner": "@a5c-ai/catalog-stewards",
    "affectedEntities": [
      "eval-run:swe-bench.claude-code@1.x.2025-04-29",
      "run:01kqex-example-run-001"
    ],
    "status": "open",
    "raisedAt": "2026-04-28T00:00:00Z"
  },
  "outgoingEdges": [],
  "incomingEdges": [
    {
      "from": "gap:expertise-level-collapse",
      "to": "open-question:benchmark-run-primitive",
      "kind": "raised_question",
      "attributes": {}
    }
  ]
}