Braintrust JSONDiff Inaccurate 100%

cli_output.txt

sharecal:eval: > NODE_ENV=production pnpx braintrust eval "./evals/json-repro.eval.ts"
sharecal:eval:
sharecal:eval: .../Library/pnpm/store/v3/tmp/dlx-5175   | Progress: resolved 1, reused 0, downloaded 0, added 0
sharecal:eval: .../Library/pnpm/store/v3/tmp/dlx-5175   | Progress: resolved 56, reused 27, downloaded 0, added 0
sharecal:eval: .../Library/pnpm/store/v3/tmp/dlx-5175   | Progress: resolved 84, reused 62, downloaded 0, added 0
sharecal:eval: .../Library/pnpm/store/v3/tmp/dlx-5175   | +106 +++++++++++
sharecal:eval: .../Library/pnpm/store/v3/tmp/dlx-5175   | Progress: resolved 127, reused 106, downloaded 0, added 0
sharecal:eval: .../Library/pnpm/store/v3/tmp/dlx-5175   | Progress: resolved 127, reused 106, downloaded 0, added 106, done
sharecal:eval: Processing 1 evaluators...
sharecal:eval: Experiment main-1726691757 is running at https://www.braintrust.dev/app/sharecal/p/JSONDiff%20repro/experiments/main-1726691757
sharecal:eval:  ░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ | JSONDiff repro                           |   1% | 1/100 datapoints
sharecal:eval:
sharecal:eval:
sharecal:eval: =========================SUMMARY=========================
sharecal:eval: main-1726691757 compared to main-1726691587:
sharecal:eval: 100.00% 'JSONDiff' score	(0 improvements, 0 regressions)
sharecal:eval:
sharecal:eval: 0.00s 'duration'	(0 improvements, 0 regressions)
sharecal:eval:
sharecal:eval: See results for main-1726691757 at https://www.braintrust.dev/app/sharecal/p/JSONDiff%20repro/experiments/main-1726691757

 Tasks:    6 successful, 6 total
Cached:    4 cached, 6 total
  Time:    19.055s

json-repro.eval.ts

import { Eval } from "braintrust";
import { JSONDiff } from "autoevals";

const testFn = () => {
  return [
    {
      start: new Date("2023-08-01T14:00:00.000Z"),
      end: new Date("2023-08-01T15:00:00.000Z"),
    },
  ];
};

Eval<any, any>("JSONDiff repro", {
  data: () => {
    return [
      {
        input: {
          rawText: "test1",
        },
        expected: [
          {
            start: new Date("2023-08-03T14:00:00.000Z"),
            end: new Date("2023-08-03T15:00:00.000Z"),
          },
        ],
      },
    ];
  },
  task: async (input) => testFn(),
  scores: [JSONDiff],
});