Skip to content
← Back to explorer

CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles

Swapnil Parekh · Feb 28, 2026 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Feb 28, 2026, 7:44 AM

Recent

Extraction refreshed

Mar 7, 2026, 4:25 PM

Fresh

Extraction source

Runtime deterministic fallback

Confidence 0.35

Abstract

Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot" explanations with no principled notion of uncertainty. We reframe circuit discovery as an uncertainty-quantification problem over these analytic degrees of freedom. Our method, CIRCUS, constructs an ensemble of attribution graphs by pruning a single raw attribution run under multiple configurations, assigns each edge a stability score (the fraction of configurations that retain it), and extracts a strict-consensus circuit consisting only of edges that appear in all views. This produces a threshold-robust "core" circuit while explicitly surfacing contingent alternatives and enabling rejection of low-agreement structure. CIRCUS requires no retraining and adds negligible overhead, since it aggregates structure across already-computed pruned graphs. On Gemma-2-2B and Llama-3.2-1B, strict consensus circuits are ~40x smaller than the union of all configurations while retaining comparable influence-flow explanatory power, and they outperform a same-edge-budget baseline (union pruned to match the consensus size). We further validate causal relevance with activation patching, where consensus-identified nodes consistently beat matched non-consensus controls (p=0.0004). Overall, CIRCUS provides a practical, uncertainty-aware framework for reporting trustworthy, auditable mechanistic circuits with an explicit core/contingent/noise decomposition.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.35 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Runtime deterministic fallback missing

No explicit feedback protocol extracted.

Evidence snippet: Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot" explanations with no principled notion of uncertainty.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Runtime deterministic fallback evidenced

Includes extracted eval setup.

Evidence snippet: Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot" explanations with no principled notion of uncertainty.

Quality Controls

missing

Not reported

Confidence: Low Source: Runtime deterministic fallback missing

No explicit QC controls found.

Evidence snippet: Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot" explanations with no principled notion of uncertainty.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Runtime deterministic fallback missing

No benchmark anchors detected.

Evidence snippet: Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot" explanations with no principled notion of uncertainty.

Reported Metrics

partial

Relevance

Confidence: Low Source: Runtime deterministic fallback evidenced

Useful for evaluation criteria comparison.

Evidence snippet: We further validate causal relevance with activation patching, where consensus-identified nodes consistently beat matched non-consensus controls (p=0.0004).

Rater Population

missing

Unknown

Confidence: Low Source: Runtime deterministic fallback missing

Rater source not explicitly reported.

Evidence snippet: Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot" explanations with no principled notion of uncertainty.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: General
  • Extraction source: Runtime deterministic fallback

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.35
  • Flags: low_signal, possible_false_positive, runtime_fallback_extraction

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

relevance

Research Brief

Deterministic synthesis

Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot" explanations with no principled notion of uncertainty. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 7, 2026, 4:25 PM · Grounded in abstract + metadata only

Key Takeaways

  • Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot"…
  • We reframe circuit discovery as an uncertainty-quantification problem over these analytic degrees of freedom.
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (relevance).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot" explanations with no principled notion of uncertainty.
  • We reframe circuit discovery as an uncertainty-quantification problem over these analytic degrees of freedom.
  • Our method, CIRCUS, constructs an ensemble of attribution graphs by pruning a single raw attribution run under multiple configurations, assigns each edge a stability score (the fraction of configurations that retain it), and extracts a…

Why It Matters For Eval

  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: relevance

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote