MachSMT: A Machine Learning-based Algorithm Selector for SMT Solvers
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract In this paper, we present MachSMT, an algorithm selection tool for Satisfiability Modulo Theories (SMT) solvers. MachSMT supports the entirety of the SMT-LIB language. It employs machine learning (ML) methods to construct both empirical hardness models (EHMs) and pairwise ranking comparators (PWCs) over state-of-the-art SMT solvers. Given an SMT formula $$\mathcal {I}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>I</mml:mi> </mml:math> as input, MachSMT leverages these learnt models to output a ranking of solvers based on predicted run time on the formula $$\mathcal {I}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>I</mml:mi> </mml:math> . We evaluate MachSMT on the solvers, benchmarks, and data obtained from SMT-COMP 2019 and 2020. We observe MachSMT frequently improves on competition winners, winning $$54$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mn>54</mml:mn> </mml:mrow> </mml:math> divisions outright and up to a $$198.4$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mn>198.4</mml:mn> </mml:mrow> </mml:math> % improvement in PAR-2 score, notably in logics that have broad applications (e.g., BV, LIA, NRA, etc.) in verification, program analysis, and software engineering. The MachSMT tool is designed to be easily tuned and extended to any suitable solver application by users. MachSMT is not a replacement for SMT solvers by any means. Instead, it is a tool that enables users to leverage the collective strength of the diverse set of algorithms implemented as part of these sophisticated solvers.
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.
Full frame distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it