- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper studies the separation between learning finite computational structure and executing it reliably over long sequences. It introduces a small orthogonal transport component for recurrent models trained on group state-tracking tasks. The authors recover finite algebraic structure from learned operators, quantify the error accumulated during continuous execution, and investigate its causal role through a controlled intervention. They then compile the recovered structure into discrete execution and exhaustively verify exported executors and readouts against the task specification. Extensions examine product groups, distractors, and noninvertible reset operations. The all-length guarantee applies to the exported finite machine; results for the neural network remain empirical.
Critical strengths
- The paper provides a coherent and quantitatively supported account connecting learned algebraic structure to execution failure. Recovering the correct group structure across all twenty core models, predicting continuous-state deviation across 120 checkpoint–length combinations, and directly manipulating the operator defect together provide useful evidence beyond observing poor length generalization. Although the causal intervention concerns one checkpoint, it meaningfully strengthens the proposed explanation.
- The connection from approximate learned operators to checked discrete execution is compelling. The core experiments demonstrate substantial improvements in length generalization, and codebook execution eliminates observed errors across approximately 84 million evaluated positions in million-token sequences. The separate exhaustive verification establishes correctness of the exported executors and readouts at every length. The paper carefully distinguishes this guarantee from the neural decoder’s empirical performance and reports informative failures outside the core setting.
Critical weaknesses
- The incremental capability of the proposed extraction machinery over existing geometric extraction methods remains insufficiently established. Prior work already demonstrates that correct automata can be extracted from recurrent networks with poor long-sequence performance, including Wang et al. (2018). The distinctive contribution therefore rests substantially on the operator-level analysis and compilation procedure. The adapted WL* comparison and earlier clustering results do not fully isolate this contribution under matched access, checkpoints, and readout construction. In particular, the expanded black-box search contains the correct structure in all three cases, and the observed advantage concerns candidate selection and query budget.
- The conditions governing successful recovery remain unclear beyond the core group tasks. With auxiliary supervision, recovery succeeds in 7/10 product-group runs and 6/15 distractor runs, while the twelve-state partial-reset task yields no certificates across 33 runs. The successful reset/set experiments are encouraging, but these failures suggest that transition structure and the learned representation matter substantially beyond state count.
Questions for authors
- On the same checkpoints, with comparable access and a common readout and verification procedure, what advantage does operator-based extraction provide over established hidden-state clustering approaches?
- Can the unsuccessful product-group and partial-reset experiments distinguish incomplete learned structure from limitations of the extraction procedure? What observable properties predict successful recovery?
Reminder to reviwers to read author's responses
Dear Reviewers,
Thank you for your efforts in providing thorough reviews.
As the discussion period is underway, I would like to kindly remind you to read the authors' responses to your reviews and provide follow-up comments where appropriate or leave a comment. In particular, please consider whether the responses address your questions and concerns, and update your assessment if the clarifications or additional information affect your initial evaluation.
Your engagement in this discussion is important for ensuring a fair and thorough review process.
Thank you again for your time and contributions!
Best regards, Area Chair