What Output-Equivalence Oracles Miss: An Empirical Study of Equivalence-Invisible Bug Fixes in Quantum Transpilers (Qiskit, tket, Cirq)

• URL: http://arxiv.org/abs/2609.13839v1
• Date: Sat, 12 Sep 2026 09:49:43 GMT
• Title: What Output-Equivalence Oracles Miss: An Empirical Study of Equivalence-Invisible Bug Fixes in Quantum Transpilers (Qiskit, tket, Cirq)
• Abstract summary: Quantum compilers are judged correct by an output-equivalence.<n>We measure how often this happens in real merged compiler fixes.<n>A conservative floor remains even restricted to the one unconditionally equivalence-invisible channel.
• Score: 0.25489046505746704
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantum compilers are judged correct by an output-equivalence oracle: the compiled circuit must compute the same unitary as the original, modulo global phase and a qubit-layout permutation. This oracle, by construction, checks only that semantic map, not the circuit's own layout, permutation, or phase records: a defect there, or in a fixed-seed run's determinism, can pass unseen though the record is public. We measure how often this happens in real merged compiler fixes: a systematically identified corpus of Qiskit transpiler bug-fixes, classified by an independently dual-coded, source-validated manifestation taxonomy. Nineteen of 68 fixes (28%, 95% Wilson CI 19-40%) repair faults that this equivalence screen does not catch, even one augmented with compilation-validity, circuit-quality, and performance checks. A secondary wider-window robustness sample produced a nearly identical fraction (29/104, 27.9%, CI 20-37%). A conservative floor remains even restricted to the one unconditionally equivalence-invisible channel (a corrupted layout or permutation record): 10 of 68 fixes (15%, CI 8-25%) beneath the 28% headline. The gap is not Qiskit-specific: it replicates in tket (7 of 21, 33%), with Cirq smaller but consistent. We detected no systematic differences on five inexpensive PR-level characteristics (19 vs 49, underpowered to rule out a modest true difference). This class dominates the invisible set, concentrating at representation-boundary crossings. We release the corpus, codebook, and coding artifacts. Here we only measure it.

Related papers

• When LLM Decompilers Recompile More and Preserve Less [35.2873296518414]
  We show that a function may and pass every shipped test yet diverge on other legitimate inputs.<n>We propose De-Diverge, a behavioral comparison oracle not relying on fixed or hand-crafted tests.
  arXiv  Detail & Related papers  (2026-09-04T17:16:18Z)
• Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution [0.0]
  We train transformers on a synthetic language where recency and rarity are exactly coextensive.<n>We separate them with a minimal causal edit that inverts one cue while holding the truth, token count and answer position fixed.
  arXiv  Detail & Related papers  (2026-08-25T12:09:19Z)
• When Graph-JEPA Learns the Wrong Thing: Diagnosing and Repairing Category-Conditional Collapse [3.0255780640228984]
  Joint-embedding predictive architectures are selected almost universally by linear probing and effective rank.<n>We report a case where both read healthily while the representation carries zero usable instance information.<n>A Graph-JEPA predicts one masked aspect from a subgraph's remaining aspects, attaining linear-probe accuracy 0.871 and effective rank 18-47.<n>We release a harness with a reducibility audit and target gate.
  arXiv  Detail & Related papers  (2026-08-20T19:22:49Z)
• Similarity Gates Approve Reversals: A Validity Audit of Embedding-Cosine Thresholds in Agent Systems [0.0]
  Agent frameworks ship quality gates that compare text blocks by embedding-cosine similarity and decide at a fixed cutoff.<n>Deduplication filters, semantic caches, drift guards, and answer grader gates deploy to answer the question: "Does this text still mean the same thing?"<n>We audit this gate class as a measurement instrument.
  arXiv  Detail & Related papers  (2026-08-10T20:36:40Z)
• Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair [36.56438114281786]
  We study the gap between finding a correct patch and retaining, verifying, and submitting it.<n>We derive an evidence-bound typed loop contract and instantiate its mechanically enforceable subset in a reference implementation.
  arXiv  Detail & Related papers  (2026-07-27T16:05:23Z)
• Forgetting Is Not a Fix: Path Dependence in Sequential Engram Editing [35.76482964927589]
  We test the hypothesis that concept-specific memory traces become linear objects that can be extracted once and combined arithmetically.<n>We run that test on the authors' own reference implementation, at their reported best edit strength.<n>For unlearning-as-compliance: erasure certified today does not certify the artifact after its next edit.
  arXiv  Detail & Related papers  (2026-07-06T23:45:06Z)
• Context-Verified, Error-Budget-Aware Decomposition Selection for Toffoli Networks [0.0]
  We present the first compiler pass that selects a per-Toffoli decomposition to minimize a two-qubit-infidelity error budget.<n>Our verifier flags 66 library rewrites of a deployed open as non-equivalent without a context check, and count-greedy substitution silently corrupts 6 of 12 benchmark circuits.
  arXiv  Detail & Related papers  (2026-06-30T15:11:28Z)
• Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence [56.25095230687242]
  Coding agents often over-trust their own local validation routines and declare success on artifacts that satisfy surface checks.<n>This problem is especially acute in conversion, where prior evaluation is outcome-driven.<n>Across blind conversion attempts, the best system reaches 26.7--28.9% overall pass rate despite Spec pass rates up to 91.1%.<n>This suggests that failures stem more from contract-misaligned self-validation than from limited budget or backbone strength.
  arXiv  Detail & Related papers  (2026-05-27T19:57:15Z)
• What Are We Actually Decoding? Source Attribution for Non-Invasive Brain-to-Language Retrieval [42.66754319854329]
  We recast stimulus-locked MEG-to-audio retrieval as an auditing framework.<n>We use structural shortcuts, window-level stimulus-locked evidence, and cross-window contextual aggregation.<n>These results suggest that brain-to-language performance should be source-attributed, not merely reported.
  arXiv  Detail & Related papers  (2026-05-23T11:23:39Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels [41.03500441875287]
  LLM-based Triton kernel generation has attracted significant interest, yet a fundamental empirical question remains unanswered.<n>We present KernelBenchX, a benchmark designed to answer this question through category-aware evaluation of correctness and hardware efficiency.
  arXiv  Detail & Related papers  (2026-05-06T14:18:36Z)
• The Rotation Gap Is Not An Error: Ternary Structure in IBM Quantum Hardware [0.0]
  Quantum error correction assumes that all syndrome activations represent errors requiring correction.<n>We present evidence from 756 QEC runs across three IBM Eagle r3 processors that this assumption is wrong.<n> Hardware exhibits sub-Poissonian syndrome statistics, indicating that a fraction of syndrome events are not random noise but structured cooperative transitions.
  arXiv  Detail & Related papers  (2026-04-13T18:54:39Z)
• QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation [39.32132630606808]
  We introduce QuanBench+, a unified benchmark spanning Qiskit, PennyLane, and Cirq.<n>We evaluate models with executable functional tests, report Pass@1 and Pass@5, and use KL-divergence-based acceptance for probabilistic outputs.<n>Across frameworks, the strongest one-shot scores reach 59.5% in Qiskit, 54.8% in Cirq, and 42.9% in PennyLane.
  arXiv  Detail & Related papers  (2026-03-25T20:51:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.