← Back to all development cases
This case was judged by an anonymized AI reviewer and has not been independently reviewed by people; inspect the draft, cards, and both outputs to assess it.
AutocompleteWith cards better256 / 280 · beu-515b4c40c9abae95

Long-time continuum limits for twisted Schr\"{o}dinger lattices

Mathematics · 2609.34081v1

FLOWING EVIDENCE BENCHMARK

How do we compare writing with and without cards?

At the same writing position, the same model produces one first result with cards and one without. All 280 pairs enter the overall anonymized review, which assesses whether a decision not to continue fits the draft.

Overall: 138 with-card wins, 26 ties, 107 no-card wins, 5 pairs where neither was usable, and 4 inconclusive judgments. Both sides wrote text in 218 pairs; 48 had a deliberate stop and 14 included an invalid output.

SAME DRAFT · WITH OR WITHOUT CARDS

01 · FIXED WRITING POSITION

MANUSCRIPT

Same writing position ▌

Matched autocomplete at the same draft position

02 · TWO MATCHED VERSIONS

SHARED BY BOTH

Draft, writing task, and generation model

A · With cards

Relevant literature cards supplied

B · Without cards

No literature cards supplied

Generation model

Same model and version

A → first output

B → first output

Anonymized AI judge

First outputs are anonymized as X and Y

Continuation review: accuracy, fit to the writing task and usability
Returns: X preferred / tie / Y preferred / both unusable

Review again with the answer order swapped

HOW DOES BLIND JUDGING WORK?

① Anonymize both outputs
The AI judge sees the same draft and both first outputs without knowing which received cards.

② Compare and swap order
The judge applies task-specific criteria in X/Y and then Y/X order.

③ Review disagreements
A third pass resolves disagreements. Incomplete reviews remain in the denominator.

How are positions and cards selected?

We selected 40 writing positions in each of seven fields, for 280 comparisons. The position and relevant literature cards were set before each comparison, so both versions began from the same draft.

The main result retains every frozen position, including places where cards might not add a useful next move. This avoids selecting cases based on their outputs, but 49% describes the whole cohort, not a win rate where evidence clearly had an opportunity to help. This cohort did not record that opportunity label for each position before generation, so those two groups cannot yet be separated reliably.

CARD USE · 140/280

Reported card use in continuations with text

The model reports whether a card affected its continuation. In 140 of 280 tests it produced continuation text and reported card use. The previous count of 150 included 10 cases without continuation text and has been corrected.

COMPARISON · 70 / 7 / 30

Which written version was better?

Of the 107 reported-use cases where both versions produced text, the blinded AI judge preferred the with-card version 70 times, found 7 about the same, and preferred the without-card version 30 times.

How are the two table percentages calculated?

ADOPTION COVERAGE

140reported use with text
÷
280all positions
=
50%

WITH-CARD VERSION PREFERRED

70with cards better
÷
107comparable tests
=
65%

The percentages use different groups: 50% counts continuations with text reporting card use among all 280 tests; 65% covers the 107 such cases with text on both sides. The generating model reports card use, while an anonymized AI judge compares writing quality.

Card use is self-reported by the generator. The anonymized AI judge sees the draft and source snippets, so source-aware preference remains possible; there was no independent human review. The overall result describes these 280 frozen positions, not a win probability for any writing task.

Manuscript writing position

Text excerpt · not a PDF page

Research manuscript · excerpt

Long-time continuum limits for twisted Schr\"{o}dinger lattices

Introduction / related work

ave also been observed experimentally [35]. Although (1) is conjugate to the cubic NLS by (6), this time-dependent translation has no direct analogue for (2). Consequently, our analysis must address this nonautonomous lattice dynamics. Our proof combines Birkhoff coordinates and modified energies to control the propagation and size of the consistency error in the nonlinear comparison. We exploit the complete integrability of cubic NLS through its Birkhoff representation as coordinatewise rotations [ 19, 24], using their action-dependent frequencies and the regularity of the coordinate maps to derive linear bounds of the tangent flow. A related Birkhoff argument for Strang splitting appears in [18]. Since the lattice approximation does not preserve this integrable structure, we use modified energies to control its Sobolev growth. In [ 12], modified energies based on higher time derivatives yield polynomial discrete Sobolev bounds for an exponential-in-time continuum-limit estimate, motivating our optimized error bounds. To accommodate fractional Sobolev regularities, we adapt the Fourier-side modified-energy construction of [ 5] to obtain polynomial orbit bounds uniformly in h. This

↓ Next paragraph was generated here

The highlighted text is near the writing position. This is a layout of the evaluation input, not a PDF screenshot.

A matched comparison at the same writing positionOverall AI review: With cards better

Both arms use the same model, task and manuscript context. Only the retrieved passages differ. The first recorded output from each arm is shown below.

Read overall AI review rationale

A = without cards · B = with cards

Both outputs complete the sentence grammatically and maintain the academic tone. However, Output B is significantly better in terms of argumentative fit and scope. The draft is building a technical argument about comparing discrete and continuum flows, with the preceding sentence discussing 'polynomial orbit bounds uniformly in h.' Output B directly connects this to the paper's core goal: 'the discrete and continuum flows to be compared over the long times required here.' This echoes the earlier mention of 'exponential-in-time continuum-limit estimate' and ties the modified-energy construction back to the overarching proof strategy. Output A, while not wrong, makes a more generic claim about 'low-regularity regime where classical energy estimates fail' that is somewhat redundant—the draft has already established the need for fractional Sobolev regularities and modified energies. Output B's 'uniform-in-h control' precisely matches the 'uniformly in h' in the penultimate clause, creating tighter coherence. Output B also better motivates why this particular construction matters for the paper's specific theorem, not just as a general technique.

Evidence

Same model and position · retrieved passages supplied · first output

Preferred by blind review

uniform-in-h control is what allows the discrete and continuum flows to be compared over the long times required here.

Passages supplied to the Evidence version

Card 1 · Bounds on the growth of high discrete Sobolev norms for the cubic discrete nonlinear Schr{\"o}dinger equations on $h\mathbb{Z}$

We consider the discrete nonlinear Schr{\"o}dinger equations on a one dimensional lattice of mesh h, with a cubic focusing or defocusing nonlinearity. We prove a polynomial bound on the growth of the discrete Sobolev norms, uniformly with respect to the stepsize of the grid. This bound is based on a…

Read full passage excerpt

We consider the discrete nonlinear Schr{\"o}dinger equations on a one dimensional lattice of mesh h, with a cubic focusing or defocusing nonlinearity. We prove a polynomial bound on the growth of the discrete Sobolev norms, uniformly with respect to the stepsize of the grid. This bound is based on a construction of higher modified energies.

Card 2 · Mobile Localization in nonlinear Schrodinger lattices

Using continuation methods from the integrable Ablowitz-Ladik lattice, we have studied the structure of numerically exact mobile discrete breathers in the standard Discrete Nonlinear Schrodinger equation. We show that, away from that integrable limit, the mobile pulse is dressed by a background of r…

Read full passage excerpt

Using continuation methods from the integrable Ablowitz-Ladik lattice, we have studied the structure of numerically exact mobile discrete breathers in the standard Discrete Nonlinear Schrodinger equation. We show that, away from that integrable limit, the mobile pulse is dressed by a background of resonant plane waves with wavevectors given by a certain selection rule. This background is seen to be essential for supporting mobile localization in the absence of integrability. We show how the variations of the localized pulse energy during its motion are balanced by the interaction with this background, allowing the localization mobility along the lattice.

Card 3 · Discrete Nonlinear Schrodinger Equations Free of the Peierls-Nabarro Potential

We derive a class of discrete nonlinear Schr{ö}dinger (DNLS) equations for general polynomial nonlinearity whose stationary solutions can be found from a reduced two-point algebraic problem. It is demonstrated that the derived class of discretizations contains subclasses conserving classical norm or…

Read full passage excerpt

We derive a class of discrete nonlinear Schr{ö}dinger (DNLS) equations for general polynomial nonlinearity whose stationary solutions can be found from a reduced two-point algebraic problem. It is demonstrated that the derived class of discretizations contains subclasses conserving classical norm or a modified norm and classical momentum. These equations are interesting from the physical standpoint since they support stationary discrete solitons free of the Peierls-Nabarro potential. As a consequence, even in highly-discrete regimes, solitons are not trapped by the lattice and they can be accelerated by even weak external fields. Focusing on the cubic nonlinearity we then consider a small perturbation around stationary soliton solutions and, solving corresponding eigenvalue problem, we (i) demonstrate that solitons are stable; (ii) show that they have two additional zero-frequency modes responsible for their effective translational invariance; (iii) derive semi-analytical solutions for …

Card 4 · Statistical mechanics of general discrete nonlinear Schr{ö}dinger models: Localization transition and its relevance for Klein-Gordon lattices

We extend earlier work [Phys.Rev.Lett. 84, 3740 (2000)] on the statistical mechanics of the cubic one-dimensional discrete nonlinear Schrodinger (DNLS) equation to a more general class of models, including higher dimensionalities and nonlinearities of arbitrary degree. These extensions are physicall…

Read full passage excerpt

We extend earlier work [Phys.Rev.Lett. 84, 3740 (2000)] on the statistical mechanics of the cubic one-dimensional discrete nonlinear Schrodinger (DNLS) equation to a more general class of models, including higher dimensionalities and nonlinearities of arbitrary degree. These extensions are physically motivated by the desire to describe situations with an excitation threshold for creation of localized excitations, as well as by recent work suggesting non-cubic DNLS models to describe Bose-Einstein condensates in deep optical lattices, taking into account the effective condensate dimensionality. Considering ensembles of initial conditions with given values of the two conserved quantities, norm and Hamiltonian, we calculate analytically the boundary of the 'normal' Gibbsian regime corresponding to infinite temperature, and perform numerical simulations to illuminate the nature of the localization dynamics outside this regime for various cases. Furthermore, we show quantitatively how this …

Card 5 · Dynamical Barrier for the Formation of Solitary Waves in Discrete Lattices

We consider the problem of the existence of a dynamical barrier of ``mass'' that needs to be excited on a lattice site to lead to the formation and subsequent persistence of localized modes for a nonlinear Schrodinger lattice. We contrast the existence of a dynamical barrier with its absence in the…

Read full passage excerpt

We consider the problem of the existence of a dynamical barrier of ``mass'' that needs to be excited on a lattice site to lead to the formation and subsequent persistence of localized modes for a nonlinear Schrodinger lattice. We contrast the existence of a dynamical barrier with its absence in the static theory of localized modes in one spatial dimension. We suggest an energetic criterion that provides a sufficient, but not necessary, condition on the amplitude of a single-site initial condition required to form a solitary wave. We show that this effect is not one-dimensional by considering its two-dimensional analog. The existence of a sufficient condition for the excitation of localized modes in the non-integrable, discrete, nonlinear Schrodinger equation is compared to the dynamics of excitations in the integrable, both discrete and continuum, version of the nonlinear Schrodinger equation.

Model-reported card use

Card 1 · fact

Affected output: uniform-in-h control

Model explanation: The row supplies the precise uniform-in-stepsize bound that the sentence uses to characterize the modified-energy construction, rather than a generic claim of stability.

No Evidence

Same model and position · no retrieved passages · first output

Not preferred in this comparison

last ingredient is essential for handling the low-regularity regime where classical energy estimates fail.

Earlier card-use comparison

The earlier diagnostic compared only cases with reported card use and text on both sides; its scope differs from the overall AI review above.

The blinded model review preferred the Evidence version. Its original rationale appears below.

Read the original model judgment

Output A provides a coherent continuation grounded in the draft's argument. The draft discusses obtaining 'polynomial orbit bounds uniformly in h' through Fourier-side modified-energy construction. Output A's 'uniform-in-h control' directly references this, and 'allows the discrete and continuum flows to be compared over the long times required here' logically follows from the paper's goal of long-time error estimates for lattice approximations. Output B introduces 'the low-regularity regime where classical energy estimates fail' — this is an unsupported claim. The draft mentions 'fractional Sobolev regularities' but does not state that 'classical energy estimates fail' in this regime, nor does it frame this as a 'low-regularity regime' requiring special handling due to failure of classical methods. The draft simply states they 'adapt the Fourier-side modified-energy construction' to accommodate fractional Sobolev regularities, without any claim about classical energy estimates failing. This adds an unsupported mechanism/purpose.

The passages are input material; their presence does not mean an output used them or that they support every claim. Draft and source passages are excerpted; no simulated scores or PDF appear here.