{"cases":[{"case_id":"accepted-control","expected_skills":[{"name":"evidence-review","status":"matched"}],"gate":"accepted","goal":"Inspect the accepted-control review condition.","has_rejection":false,"results":[{"accepted":true,"error":null,"evaluator":"goal-control","explanation":"Authored passing control.","label":null,"revision":"authored-1","span_id":null,"status":"assessed","trace_id":null,"value":1},{"accepted":true,"error":null,"evaluator":"Builtin.SkillInstructionFollowing","explanation":"Authored passing control.","label":null,"revision":"synthetic-scale-1","span_id":"0000000000000001","status":"assessed","trace_id":"00000000000000000000000000000001","value":1}],"session_id":"session-0","skill_calls":[{"identity":"matched","name":"evidence-review","receipt":{"bundle_sha256":"cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc","content_sha256":"eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee","declared_tools":null,"load_id":"synthetic-0","loaded_at":"2026-09-15T00:00:00Z","name":"evidence-review","permissions_enforced":false,"provider":"dsh-skills-anywhere","provider_version":"0.12.0","schema":"skills-anywhere-load-1","skill_sha256":"dddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd"},"span_id":"0000000000000001","trace_id":"00000000000000000000000000000001"}],"skill_observation_complete":true,"span_count":1,"trace_ids":["00000000000000000000000000000001"]},{"case_id":"assessed-zero","expected_skills":[{"name":"evidence-review","status":"matched"}],"gate":"rejected","goal":"Inspect the assessed-zero review condition.","has_rejection":true,"results":[{"accepted":false,"error":null,"evaluator":"goal-control","explanation":"Valid zero: the authored output lacks evidence.","label":null,"revision":"authored-1","span_id":null,"status":"assessed","trace_id":null,"value":0},{"accepted":true,"error":null,"evaluator":"Builtin.SkillInstructionFollowing","explanation":"Authored passing control.","label":null,"revision":"synthetic-scale-1","span_id":"0000000000000002","status":"assessed","trace_id":"00000000000000000000000000000002","value":1}],"session_id":"session-1","skill_calls":[{"identity":"matched","name":"evidence-review","receipt":{"bundle_sha256":"cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc","content_sha256":"eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee","declared_tools":null,"load_id":"synthetic-1","loaded_at":"2026-09-15T00:00:00Z","name":"evidence-review","permissions_enforced":false,"provider":"dsh-skills-anywhere","provider_version":"0.12.0","schema":"skills-anywhere-load-1","skill_sha256":"dddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd"},"span_id":"0000000000000002","trace_id":"00000000000000000000000000000002"}],"skill_observation_complete":true,"span_count":1,"trace_ids":["00000000000000000000000000000002"]},{"case_id":"skipped-judge","expected_skills":[],"gate":"incomplete","goal":"Inspect the skipped-judge review condition.","has_rejection":false,"results":[{"accepted":null,"error":"Authored example of unavailable context.","evaluator":"goal-control","explanation":"Authored passing control.","label":null,"revision":"authored-1","span_id":null,"status":"skipped","trace_id":null,"value":null},{"accepted":null,"error":null,"evaluator":"Builtin.SkillInstructionFollowing","explanation":"No annotated skill calls; coverage is caller-declared.","label":null,"revision":"synthetic-scale-1","span_id":null,"status":"not_applicable","trace_id":null,"value":null}],"session_id":"session-2","skill_calls":[],"skill_observation_complete":true,"span_count":1,"trace_ids":["00000000000000000000000000000003"]},{"case_id":"missing-result","expected_skills":[],"gate":"incomplete","goal":"Inspect the missing-result review condition.","has_rejection":false,"results":[{"accepted":null,"error":null,"evaluator":"goal-control","explanation":"No result for this declared target.","label":null,"revision":"authored-1","span_id":null,"status":"missing","trace_id":null,"value":null},{"accepted":null,"error":null,"evaluator":"Builtin.SkillInstructionFollowing","explanation":"No annotated skill calls; coverage is caller-declared.","label":null,"revision":"synthetic-scale-1","span_id":null,"status":"not_applicable","trace_id":null,"value":null}],"session_id":"session-3","skill_calls":[],"skill_observation_complete":true,"span_count":1,"trace_ids":["00000000000000000000000000000004"]},{"case_id":"missed-skill","expected_skills":[{"name":"evidence-review","status":"not_called"}],"gate":"rejected","goal":"Inspect the missed-skill review condition.","has_rejection":true,"results":[{"accepted":true,"error":null,"evaluator":"goal-control","explanation":"Authored passing control.","label":null,"revision":"authored-1","span_id":null,"status":"assessed","trace_id":null,"value":1},{"accepted":null,"error":null,"evaluator":"Builtin.SkillInstructionFollowing","explanation":"No annotated skill calls; coverage is caller-declared.","label":null,"revision":"synthetic-scale-1","span_id":null,"status":"not_applicable","trace_id":null,"value":null}],"session_id":"session-4","skill_calls":[],"skill_observation_complete":true,"span_count":1,"trace_ids":["00000000000000000000000000000005"]}],"comparison":{"baseline_source_sha256":"a62386dddd44ee95ab68869ee043f9fd30c2cbd2b924088467d8d0729648cf1c","cases":[{"baseline":"accepted","case_id":"accepted-control","current":"accepted","regressed":false},{"baseline":"accepted","case_id":"assessed-zero","current":"rejected","regressed":true},{"baseline":"accepted","case_id":"skipped-judge","current":"incomplete","regressed":true},{"baseline":"accepted","case_id":"missing-result","current":"incomplete","regressed":true},{"baseline":"accepted","case_id":"missed-skill","current":"rejected","regressed":true}],"configuration_changes":{"prompt_sha256":{"baseline":"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa","current":"ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff"}},"interpretation":"Paired descriptive comparison; no causal or statistical gain claim."},"configuration":{"model":"synthetic-control","model_parameters":{},"prompt_sha256":"ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff","skills":{"evidence-review":"cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc"},"tools_sha256":"bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"},"dataset":{"cases":[{"expected_skills":["evidence-review"],"goal":"Inspect the accepted-control review condition.","id":"accepted-control"},{"expected_skills":["evidence-review"],"goal":"Inspect the assessed-zero review condition.","id":"assessed-zero"},{"expected_skills":[],"goal":"Inspect the skipped-judge review condition.","id":"skipped-judge"},{"expected_skills":[],"goal":"Inspect the missing-result review condition.","id":"missing-result"},{"expected_skills":["evidence-review"],"goal":"Inspect the missed-skill review condition.","id":"missed-skill"}],"id":"trace-review-controls","version":"1"},"dataset_sha256":"af06543f58bb31780df1d63b6423ca3239720cff8aa2ba826d458b33116db7ab","evaluators":[{"id":"goal-control","level":"session","rating":{"kind":"numeric","max":1,"min":0,"pass_at_least":1},"revision":"authored-1"},{"id":"Builtin.SkillInstructionFollowing","level":"skill","rating":{"kind":"numeric","max":1,"min":0,"pass_at_least":1},"revision":"synthetic-scale-1"}],"provenance":{"description":"Five authored controls for import and review behavior. Placeholder hashes, simulated spans and judgments; no AWS or model run.","kind":"synthetic"},"run_id":"synthetic-current","schema_version":"evalarc.trace-review.v1","scope":"Imported evaluator judgments and caller-declared trace coverage. Identity and consistency checks do not authenticate the producer, rerun a judge, enforce permissions or independently verify task completion.","source_bytes":9126,"source_sha256":"7c16410530ff7c2e4b8553ddfa264eb624006e0236d0d4f12e1823905ff0202e","summary":{"accepted":1,"incomplete":2,"rejected":2}}
