MétaCan
Menu
Back to cohort

ScenarioBench: Trace-Grounded Compliance Evaluation for Text-to-SQL and RAG

2025· article· W7125586192 on OpenAlexaff
Zahra Atf

Bibliographic record

Venuenot available
Typearticle
Language
FieldDecision Sciences
TopicScientific Computing and Data Management
Canadian institutionsOntario Tech University
Fundersnot available
KeywordsCorrectnessBenchmark (surveying)Artifact (error)Code (set theory)Matching (statistics)Aggregate (composite)WitnessCore (optical fiber)Compliance (psychology)

Abstract

fetched live from OpenAlex

ScenarioBench is a policy-grounded, trace-aware benchmark for evaluating Text-to-SQL and retrieval-augmented generation in compliance settings. Each YAML scenario ships with a no-peek gold-standard package-expected decision, minimal witness trace, governing clause set, and canonical SQL-enabling end-to-end scoring of both what a system decides and why it decides so. Systems must justify outputs with clause IDs retrieved from the same policy canon, making explanations falsifiable and audit-ready. The evaluator reports core signals-decision/trace quality, retrieval and SQL correctness (by result-set equivalence), latency, and a hallucination rate. A normalized Scenario Difficulty Index (SDI) and its budgeted variant (SDI-R) aggregate these while pricing retrieval difficulty and time. Unlike Spider/BIRD or KILT/RAG-style setups, ScenarioBench enforces clause-ID grounding under a strict nopeek rule. On a seed synthetic suite (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$N=16$</tex>), accuracy saturates (Acc <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$=\mathbf{M}-\mathbf{F} 1=1.000)$</tex>, and a single budgeted reflection closes trace gaps (TrC & Coverage <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$0.541 \rightarrow 1.000$</tex>) with zero hallucination at <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\sim+1 \text{ms}$</tex>-showing that marginal gains come from why-quality under explicit time budgets. Artifact & Code (v0.1.0): https://github.com/ShabnamAtf/ScenarioBench/releases/tag/v0.1.0

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.020
metaresearch head score (Gemma)0.006
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication, Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.872
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0200.006
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.003
Science and technology studies0.0010.000
Scholarly communication0.0030.001
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.317
GPT teacher head0.486
Teacher spread0.169 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designOther design
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicScientific Computing and Data ManagementFrench-language works237,207