evalarc / trace-workbench /input.json
glayguo's picture
Publish verified EvalArc f90fb4305f1e (part 2)
3a160ad verified
Raw History Blame Contribute Delete
9.13 kB
{
"schema_version": "evalarc.trace-input.v1",
"run_id": "synthetic-current",
"provenance": {
"kind": "synthetic",
"description": "Five authored controls for import and review behavior. Placeholder hashes, simulated spans and judgments; no AWS or model run."
},
"dataset": {
"id": "trace-review-controls",
"version": "1",
"cases": [
{
"id": "accepted-control",
"goal": "Inspect the accepted-control review condition.",
"expected_skills": [
"evidence-review"
]
},
{
"id": "assessed-zero",
"goal": "Inspect the assessed-zero review condition.",
"expected_skills": [
"evidence-review"
]
},
{
"id": "skipped-judge",
"goal": "Inspect the skipped-judge review condition.",
"expected_skills": []
},
{
"id": "missing-result",
"goal": "Inspect the missing-result review condition.",
"expected_skills": []
},
{
"id": "missed-skill",
"goal": "Inspect the missed-skill review condition.",
"expected_skills": [
"evidence-review"
]
}
]
},
"configuration": {
"model": "synthetic-control",
"model_parameters": {},
"prompt_sha256": "ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff",
"tools_sha256": "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
"skills": {
"evidence-review": "cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc"
}
},
"evaluators": [
{
"id": "goal-control",
"revision": "authored-1",
"level": "session",
"rating": {
"kind": "numeric",
"min": 0,
"max": 1,
"pass_at_least": 1
}
},
{
"id": "Builtin.SkillInstructionFollowing",
"revision": "synthetic-scale-1",
"level": "skill",
"rating": {
"kind": "numeric",
"min": 0,
"max": 1,
"pass_at_least": 1
}
}
],
"cases": [
{
"case_id": "accepted-control",
"session_id": "session-0",
"trace_ids": [
"00000000000000000000000000000001"
],
"skill_observation_complete": true,
"spans": [
{
"traceId": "00000000000000000000000000000001",
"spanId": "0000000000000001",
"name": "authored-control",
"attributes": {
"session.id": "session-0"
}
}
],
"skill_calls": [
{
"name": "evidence-review",
"trace_id": "00000000000000000000000000000001",
"span_id": "0000000000000001",
"receipt": {
"schema": "skills-anywhere-load-1",
"load_id": "synthetic-0",
"loaded_at": "2026-09-15T00:00:00Z",
"provider": "dsh-skills-anywhere",
"provider_version": "0.12.0",
"name": "evidence-review",
"skill_sha256": "dddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd",
"content_sha256": "eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee",
"bundle_sha256": "cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
"declared_tools": null,
"permissions_enforced": false
}
}
],
"evaluation_response": {
"evaluationResults": [
{
"evaluatorId": "goal-control",
"evaluatorName": "goal-control",
"evaluatorArn": "synthetic-control",
"context": {
"spanContext": {
"sessionId": "session-0"
}
},
"value": 1,
"explanation": "Authored passing control."
},
{
"evaluatorId": "Builtin.SkillInstructionFollowing",
"evaluatorName": "Builtin.SkillInstructionFollowing",
"evaluatorArn": "synthetic-control",
"context": {
"spanContext": {
"sessionId": "session-0",
"traceId": "00000000000000000000000000000001",
"spanId": "0000000000000001"
}
},
"value": 1,
"explanation": "Authored passing control."
}
]
}
},
{
"case_id": "assessed-zero",
"session_id": "session-1",
"trace_ids": [
"00000000000000000000000000000002"
],
"skill_observation_complete": true,
"spans": [
{
"traceId": "00000000000000000000000000000002",
"spanId": "0000000000000002",
"name": "authored-control",
"attributes": {
"session.id": "session-1"
}
}
],
"skill_calls": [
{
"name": "evidence-review",
"trace_id": "00000000000000000000000000000002",
"span_id": "0000000000000002",
"receipt": {
"schema": "skills-anywhere-load-1",
"load_id": "synthetic-1",
"loaded_at": "2026-09-15T00:00:00Z",
"provider": "dsh-skills-anywhere",
"provider_version": "0.12.0",
"name": "evidence-review",
"skill_sha256": "dddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd",
"content_sha256": "eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee",
"bundle_sha256": "cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
"declared_tools": null,
"permissions_enforced": false
}
}
],
"evaluation_response": {
"evaluationResults": [
{
"evaluatorId": "goal-control",
"evaluatorName": "goal-control",
"evaluatorArn": "synthetic-control",
"context": {
"spanContext": {
"sessionId": "session-1"
}
},
"value": 0,
"explanation": "Valid zero: the authored output lacks evidence."
},
{
"evaluatorId": "Builtin.SkillInstructionFollowing",
"evaluatorName": "Builtin.SkillInstructionFollowing",
"evaluatorArn": "synthetic-control",
"context": {
"spanContext": {
"sessionId": "session-1",
"traceId": "00000000000000000000000000000002",
"spanId": "0000000000000002"
}
},
"value": 1,
"explanation": "Authored passing control."
}
]
}
},
{
"case_id": "skipped-judge",
"session_id": "session-2",
"trace_ids": [
"00000000000000000000000000000003"
],
"skill_observation_complete": true,
"spans": [
{
"traceId": "00000000000000000000000000000003",
"spanId": "0000000000000003",
"name": "authored-control",
"attributes": {
"session.id": "session-2"
}
}
],
"skill_calls": [],
"evaluation_response": {
"evaluationResults": [
{
"evaluatorId": "goal-control",
"evaluatorName": "goal-control",
"evaluatorArn": "synthetic-control",
"context": {
"spanContext": {
"sessionId": "session-2"
}
},
"explanation": "Authored passing control.",
"errorCode": "Skipped",
"errorMessage": "Authored example of unavailable context."
}
]
}
},
{
"case_id": "missing-result",
"session_id": "session-3",
"trace_ids": [
"00000000000000000000000000000004"
],
"skill_observation_complete": true,
"spans": [
{
"traceId": "00000000000000000000000000000004",
"spanId": "0000000000000004",
"name": "authored-control",
"attributes": {
"session.id": "session-3"
}
}
],
"skill_calls": [],
"evaluation_response": {
"evaluationResults": []
}
},
{
"case_id": "missed-skill",
"session_id": "session-4",
"trace_ids": [
"00000000000000000000000000000005"
],
"skill_observation_complete": true,
"spans": [
{
"traceId": "00000000000000000000000000000005",
"spanId": "0000000000000005",
"name": "authored-control",
"attributes": {
"session.id": "session-4"
}
}
],
"skill_calls": [],
"evaluation_response": {
"evaluationResults": [
{
"evaluatorId": "goal-control",
"evaluatorName": "goal-control",
"evaluatorArn": "synthetic-control",
"context": {
"spanContext": {
"sessionId": "session-4"
}
},
"value": 1,
"explanation": "Authored passing control."
}
]
}
}
]
}