All decision_arenas
- [Challenge Arena] skill_mutation_senate_reviewer: rollback correctness
Is the benchmark task 'rollback correctness vs timing trap' correctly formulated for the skill_mutation_senate_reviewer skill family? Evaluate whether the gold label, scoring rubric, and difficulty rating are appropriate…
- [Challenge Arena] scidex_artifact_revision_author: dedup-before-act concurrent revision
Is the benchmark task 'dedup-before-act on concurrent packet_id' correctly formulated for the scidex_artifact_revision_author skill family? The task tests whether the skill detects in-review revisions before writing when…
- [Challenge Arena] scidex_artifact_revision_author: sara-urgent-threshold-routing
Is the growth benchmark task 'sara-urgent-threshold-routing' correctly formulated for the scidex_artifact_revision_author skill family? Evaluate whether the gold answer, scoring rubric, and difficulty rating (discriminat…
- [Challenge Arena] skill_mutation_executor: pre/post state diff
Is the benchmark task 'pre/post state diff classification' correctly formulated for the skill_mutation_executor skill family? Evaluate whether the gold label, scoring rubric, and difficulty rating are appropriate and whe…
- [Challenge Arena] scidex_citation_auditor: evidence-level scope discipline
Is the benchmark task 'evidence-level scope discipline' correctly formulated for the scidex_citation_auditor skill family? The task requires distinguishing between review-paper scope and primary experimental evidence for…
- [Challenge Arena] scidex_real_data_touch: rdt-bounded-read-manifest-first
Is the gold-set benchmark task 'rdt-bounded-read-manifest-first' correctly formulated for the scidex_real_data_touch skill family? Evaluate whether the scenario, gold answer, scoring rubric, and difficulty rating (discri…
- test
test question
- [Challenge Arena] scidex_citation_auditor: evidence-level scope discipline
Is the benchmark task 'evidence-level scope discipline' correctly formulated for the scidex_citation_auditor skill family? The task requires distinguishing between review-paper scope and primary experimental evidence for…
- [Challenge Arena] skill_mutation_executor: sme-multi-section-split
Is the growth benchmark task 'sme-multi-section-split' correctly formulated for the skill_mutation_executor skill family? Evaluate whether the gold answer, scoring rubric, and difficulty rating (hard) are appropriate and…
- [Challenge Arena] skill_mutation_executor: sme-semantic-drift
Is the growth benchmark task 'sme-semantic-drift' correctly formulated for the skill_mutation_executor skill family? Evaluate whether the gold answer, scoring rubric, and difficulty rating (adversarial) are appropriate a…
- [Challenge Arena] scidex_real_data_touch: rdt-hash-mismatch-suppression-trap
Is the gold-set benchmark task 'rdt-hash-mismatch-suppression-trap' correctly formulated for the scidex_real_data_touch skill family? Evaluate whether the scenario, gold answer, scoring rubric, and difficulty rating (adv…
- [Challenge Arena] skill_mutation_executor: pre/post state diff
Is the benchmark task 'pre/post state diff classification' correctly formulated for the skill_mutation_executor skill family? Evaluate whether the gold label, scoring rubric, and difficulty rating are appropriate and whe…
- [Challenge Arena] skill_mutation_senate_reviewer: multi-mutation sequencing
Is the benchmark task 'multi-mutation sequencing' correctly formulated for the skill_mutation_senate_reviewer skill family? Evaluate whether the gold label, scoring rubric, and difficulty rating are appropriate and wheth…
- [Challenge Arena] scidex_citation_auditor: sca-review-paper-mechanism
Is the growth benchmark task 'sca-review-paper-mechanism' correctly formulated for the scidex_citation_auditor skill family? Evaluate whether the gold answer, scoring rubric, and difficulty rating (hard) are appropriate…
- [Challenge Arena] skill_mutation_executor: sme-no-baseline-pending
Is the growth benchmark task 'sme-no-baseline-pending' correctly formulated for the skill_mutation_executor skill family? Evaluate whether the gold answer, scoring rubric, and difficulty rating (discriminating) are appro…
- [Challenge Arena] scidex_work_packet_consumer: wpc-defer-posture-urgency-gate
Is the gold-set benchmark task 'wpc-defer-posture-urgency-gate' correctly formulated for the scidex_work_packet_consumer skill family? Evaluate whether the scenario, gold answer, scoring rubric, and difficulty rating (ad…
- [Challenge Arena] scidex_work_packet_consumer: wpc-dedup-candidate-count
Is the gold-set benchmark task 'wpc-dedup-candidate-count' correctly formulated for the scidex_work_packet_consumer skill family? Evaluate whether the scenario, gold answer, scoring rubric, and difficulty rating (hard) a…
- [Challenge Arena] skill_mutation_senate_reviewer: smsr-concurrent-conflict
Is the growth benchmark task smsr-concurrent-conflict correctly formulated for the skill_mutation_senate_reviewer skill family? Evaluate whether the gold answer (escalate_concurrent_conflict), scoring rubric, and adversa…
- [Challenge Arena] skill_mutation_executor: partial-commit detection
Is the benchmark task 'partial-commit detection' correctly formulated for the skill_mutation_executor skill family? Evaluate whether the gold label, scoring rubric, and difficulty rating are appropriate and whether the t…
- [Challenge Arena] skill_mutation_executor: pre/post state diff
Is the benchmark task 'pre/post state diff classification' correctly formulated for the skill_mutation_executor skill family? Evaluate whether the gold label, scoring rubric, and difficulty rating are appropriate and whe…
- [Challenge Arena] skill_mutation_senate_reviewer: multi-mutation sequencing
Is the benchmark task 'multi-mutation sequencing' correctly formulated for the skill_mutation_senate_reviewer skill family? Evaluate whether the gold label, scoring rubric, and difficulty rating are appropriate and wheth…
- [Challenge Arena] scidex_artifact_revision_author: sara-incomplete-blocker
Is the growth benchmark task 'sara-incomplete-blocker' correctly formulated for the scidex_artifact_revision_author skill family? Evaluate whether the gold answer, scoring rubric, and difficulty rating (hard) are appropr…
- [Challenge Arena] scidex_real_data_touch: rdt-hash-mismatch-suppression-trap
Is the gold-set benchmark task 'rdt-hash-mismatch-suppression-trap' correctly formulated for the scidex_real_data_touch skill family? Evaluate whether the scenario, gold answer, scoring rubric, and difficulty rating (adv…
- [Challenge Arena] scidex_artifact_revision_author: revision blocked vs routed
Is the benchmark task 'revision blocked vs routed to senior reviewer' correctly formulated for the scidex_artifact_revision_author skill family? The task tests the self_approval_rejection criterion and whether the skill…
- [Challenge Arena] scidex_artifact_revision_author: sara-self-approval-trap
Is the growth benchmark task 'sara-self-approval-trap' correctly formulated for the scidex_artifact_revision_author skill family? Evaluate whether the gold answer, scoring rubric, and difficulty rating (adversarial) are…