{"id":"150a548d-fee1-48e4-aad0-7928de4c3e77","arxiv_id":"2611.16806","paper_version":1,"verdict":"CONDITIONAL","confidence":"HIGH","novelty_score":7.0,"correctness_risk":"medium","formal_verification":"none","parameter_count":3,"one_line_summary":"FlatSeek uses backward data generation and LLM fine-tuning to discover symbolic flat outputs for nonlinear systems, achieving higher success rates than traditional methods.","lead":"FlatSeek fine-tunes a language model to propose symbolic flat outputs for nonlinear control systems by training on system-output pairs generated backward from known flat parametrizations. The method solves 74 of 83 literature systems and 171 of 200 synthetic systems, outperforming traditional symbolic methods and untuned models.","discovery_kind":"new_method","skeptic_critique":{"model":"deepseek/deepseek-v4-flash","headline":"Synthetic test systems are generated by the same backward construction as training data, so the 171/200 hit rate may reflect pattern matching rather than genuine flat-output discovery.","rationale":"The reader's weakest_assumption focuses on the backward construction's weight functions and domain conditions, which is related but not identical to my concern. The reader notes that the diversity of training data depends on manual choices, which is part of the template bias issue. However, the reader does not explicitly flag that the synthetic test set shares the same construction template as the training set, which is the core of my concern. The reader's verdict is CONDITIONAL, and I also recommend CONDITIONAL, but for a different reason: the reader emphasizes reproducibility (code/data release, error bars), while I emphasize the structural bias in the synthetic evaluation. Both are valid concerns, but mine is more directly about the validity of the central claim. I agree with the reader that the paper is well-motivated and technically sound, but the synthetic benchmark's construction bias is a load-bearing issue that the reader did not fully articulate. Therefore agreement_with_reader is 'partial'. The verdict should remain CONDITIONAL because the concern can be addressed by additional experiments (out-of-template test set) without requiring a fundamental rewrite. If the authors provide such evidence, the verdict could move to ACCEPT; if the concern is confirmed, the claim would need to be substantially qualified.","tokens_in":11652,"tokens_out":724,"duration_ms":7948,"concrete_test":"Generate a new synthetic test set using a different backward construction variant: e.g., allow the first chain to be weighted (a_{1,k} not identically 1) or use non-shear coordinate transformations (e.g., polynomial diffeomorphisms with cross terms). If FlatSeek's hit rate drops significantly (e.g., below 100/200) on this out-of-template test set while the strongest traditional baseline holds steady, then the original synthetic benchmark overstates the method's generality.","verdict_should_be":"CONDITIONAL","load_bearing_attack":"The paper's central claim is that FlatSeek discovers flat outputs for unseen dynamics. The synthetic benchmark (200 systems) is held out from the training corpus, but both training and test sets are generated by the same backward construction (Section III). The construction imposes a specific structural template: weighted derivative chains with the first chain unweighted, terminal weights set to one, and diversification only via shears and symbol renaming. The LLM could therefore learn to recognize the template's signature (e.g., the pattern of multiplicative couplings in the dynamics) rather than learning the general concept of flatness. The literature benchmark (83 systems) is more independent, but the paper does not report how many of the 74 solved literature systems share structural features with the training data (e.g., similar chain lengths or weight patterns). If the model's success on synthetic systems is largely template recognition, then its performance on genuinely novel dynamics—those that do not fit the backward construction's template—may be much lower. The paper acknowledges this indirectly in the conclusion ('Future work will extend the search to systems for which existing methods have not yet produced a flat-output candidate'), but does not quantify the template bias. This concern is load-bearing because the main evidence for the method's generality is the synthetic benchmark, and if that benchmark is structurally biased, the claimed improvement over baselines may not transfer to real-world systems outside the template.","agreement_with_reader":"partial"},"referee_report":{"model":"deepseek/deepseek-v4-flash","summary":"The paper proposes FlatSeek, a framework that combines backward data generation with fine-tuned LLMs to discover symbolic flat outputs for nonlinear control systems. The key idea is to generate training data by starting from a known flat output and reconstruction maps, then deriving compatible dynamics (backward construction). The LLM is fine-tuned on these pairs and at inference proposes candidates that are verified by a symbolic verifier. The method is evaluated on a literature benchmark (83 systems) and a synthetic benchmark (200 systems), outperforming traditional symbolic methods and untuned LLMs. The paper also reports discovery of alternative flat outputs not previously reported.","tokens_in":12056,"tokens_out":1707,"duration_ms":14205,"significance":"If the results hold, this work provides a practical approach to a long-standing open problem in nonlinear control: finding flat outputs for general nonlinear systems. The backward data generation technique is a clever way to create supervised training data where none existed. The combination of LLM generation with symbolic verification is a sensible division of labor. The empirical results are strong, with FlatSeek solving 74/83 literature systems and 171/200 synthetic systems, compared to 58/83 and 127/200 for the best traditional method. The discovery of alternative flat outputs not in the literature is a concrete demonstration of the method's utility. The paper is well-structured and the technical details are clearly presented.","major_comments":[{"comment":"The backward construction assumes that the first chain is unweighted (a_{1,k} ≡ 1) and that terminal weights are set to one. This imposes a structural template on the generated systems: the first output component's derivative appears directly as a state or input coordinate. While this is a valid construction, it biases the training data toward systems where y1 has a simple relationship to the dynamics. The paper does not discuss how this template might limit the diversity of flat-output structures the LLM learns to recognize. Since the synthetic test systems are generated by the same construction, the high hit rate on that benchmark (171/200) may partly reflect pattern matching to this template rather than general flat-output discovery. The literature benchmark is more independent, but the paper does not analyze how many of the 74 solved literature systems share structural features with the training template (e.g., similar chain lengths or weight patterns). This concern is acknowledged indirectly in the conclusion ('Future work will extend the search to systems for which existing methods have not yet produced a flat-output candidate'), but the potential template bias is not quantified or discussed as a limitation.","section":"Section III-A, Step 1","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"The verifier is described as checking 'a finite-order Jacobian-rank test for recoverability of the state and input from the output derivatives; candidates with differentially dependent components are rejected.' However, the paper does not specify the order up to which derivatives are considered, nor does it discuss the possibility of false negatives (rejecting a valid flat output because the required derivative order exceeds the verifier's truncation) or false positives (accepting a candidate that passes the finite-order test but fails at higher order). Since the verifier is the final arbiter of success, its reliability is load-bearing. The paper should provide more details on the verifier's implementation, including the maximum derivative order checked, the rank condition tolerance, and any validation of the verifier against known flat outputs.","section":"Section V-A, Evaluation protocol","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"The comparison with traditional methods is informative, but the paper does not report the computational cost (e.g., wall-clock time, GPU hours) for FlatSeek versus the traditional methods. The traditional methods are given a 120-second limit per system, while FlatSeek uses an LLM with candidate generation and verification. Without cost information, it is difficult to assess the practical trade-off. Additionally, the paper should report the number of candidates that passed the verifier per system (not just whether at least one passed), to give a sense of the verifier's selectivity.","section":"Table I and Section V-B","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"The training corpus contains 12,375 base pairs, augmented to 37,125 rows. The paper states that the 200 synthetic test systems are 'structurally disjoint' from the training set, but does not define what constitutes a structural fingerprint or how disjointness is ensured. Given that both training and test sets are generated by the same backward construction, it is important to clarify the criteria for structural disjointness to rule out data leakage. The paper should provide a more precise description of how the test set was constructed and verified to be distinct from the training set.","section":"Section V-A, Training data","authors_acknowledge":null,"authors_acknowledge_p":null}],"minor_comments":[{"comment":"The abstract states 'FlatSeek outperforms both the traditional symbolic methods and the untuned reference models in flat-output discovery success.' This is accurate, but it would be helpful to include the numerical results (74/83 and 171/200) in the abstract for immediate impact.","section":"Abstract","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"The definition of differential flatness uses r and q for derivative orders in the output map and reconstruction maps, respectively. However, in the backward construction (Section III), q is defined as max_i ℓ_i, which is the maximum chain length. The relationship between the general definition's q and the construction's q should be clarified.","section":"Section II-A, Definition 1","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"The notation D_y g is defined as the total time derivative for functions of y and its derivatives. However, the definition uses y^{(j+1)} without specifying that these are time derivatives. It might be clearer to write d/dt or use an overdot to avoid confusion with spatial derivatives.","section":"Section III-A, Equation (5)","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"The shear transformation T_S(z) = z + e_j S(z_{-j}) is defined, but the notation z_{-j} is not explicitly defined. It is clear from context that it means the vector with the j-th component removed, but a brief definition would improve readability.","section":"Section III-B, Equation (15)","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"The saddle–Jacobi baseline is described as enumerating m-element subsets of state and input coordinates and screening them using an order bound and a truncated determinant. This is a reasonable baseline, but the paper should cite the specific reference for this method (Kaminski and Ollivier, 2024) more explicitly in the baseline description.","section":"Section V-A, Baselines","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"The candidate budget ablation shows hit rates for K from 1 to 200. The figure labels are clear, but the y-axis label 'Hit rate (%)' is slightly misleading because the bars show absolute counts (e.g., 41, 89) rather than percentages. The text clarifies this, but the axis label should be consistent with the data shown.","section":"Figure 5","authors_acknowledge":null,"authors_acknowledge_p":null},{"comment":"The conclusion mentions 'Future work will extend the search to systems for which existing methods have not yet produced a flat-output candidate.' This is a natural direction, but the paper could also discuss potential improvements to the backward construction to cover a wider class of systems (e.g., allowing weighted first chains or more general coordinate transformations).","section":"Section VI","authors_acknowledge":null,"authors_acknowledge_p":null}],"recommendation":"major_revision"},"author_rebuttal":null,"desk_editor":null,"pith_extraction":null,"created_at":"2026-11-13T12:35:43.475967+00:00","model_set":{"reader":"deepseek/deepseek-v4-flash"},"pipeline_version":"pith-pipeline@v1.4.1-daily-deepseek-or-medium","input_kind":null,"input_chars":null,"input_total_chars":null,"passes_missing":null,"published_standing":null,"published_confidence":null,"objection_audit":null,"run_record":null,"basis":{"kind":"not_recorded","source":null,"chars_given":null,"chars_total":null},"receipt":null,"falsifier":null,"supporting_citations":[],"lane_accuracy":{"status":"not yet measured","lane":{"model":"deepseek/deepseek-v4-flash","input_kind":null},"url":"https://pith.science/accuracy"},"review_version":1}