Pith.

Every reviewed paper

Each paper is listed with what Pith's machine review of it concluded.

499,253

papers reviewed

live · read 16 Nov 2026, 07:05 UTC

Narrow the list

Page 29. Ordered by the date each paper was submitted, newest first.

  1. The paper:

    Vector-Space Projection and Unified Complex-Valued Acceleration for Scaling Matrix-Based Brain-Inspired Representations

    Computer Science · arXiv:2611.16363

    William Youngwoo Chung, Hyunwoo Oh, Calvin Yeung and 3 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Does not hold up as stated. The flattening math is correct but definitional; the binding unit as described computes FHRR-style element-wise complex multiplication, not GHRR's matrix binding, so the central claim that the ASIC preserves non-commutative …

    3 major objections, the first at §3.1, Fig. 3; Eq. (3) · 6 minor

  2. The paper:

    On the h-polynomials of cyclotomic standard graded Cohen-Macaulay rings

    Mathematics · arXiv:2611.16362

    Akihiro Higashitani, Takumi Yanagida

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. The 8k classification is real and the Theorem 1.2 reduction is reusable, but the only-if half hangs on a finite search the paper describes rather than ships; treat it as conditional until the computation is reproducible.

    4 major objections, the first at Appendix A, Lemma A.1(i) · 16 minor

  3. The paper:

    MutAtlas: A PDB-Wide Energy-Guided Atlas of Protein Mutation Effects

    Computer Science · arXiv:2611.16361

    Ruihan Guo, Chaoran Cheng, Zhanghan Ni and 3 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. A solid resource paper with a real method contribution, but the headline performance claim is weaker than advertised because of missing error bars and a validation procedure that effectively tunes λ on the test set.

    4 major objections, the first at Table 1, §6.2 · 9 minor

  4. The paper:

    Removability Criteria for Separately Harmonic and Subharmonic Functions

    Mathematics · arXiv:2611.16360

    Mansour Kalantar

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: minor revision.

    Clean, narrow result: if the second singular projection is polar, separate harmonic+subharmonic implies joint subharmonic. The proof is mostly standard potential theory; the one gap (Green vs Newtonian energy in Thm 3.6) is real but fillable. …

    This review says the paper's mathematics is wrong. Pith did not check that against the paper's source.

  5. The paper:

    IsharaBART: An efficient BART-Based Framework for Low-Resource Bangla Sign Language Translation

    Computer Science · arXiv:2611.16359

    Aonmoy Das, Ananna Dev Aishi, Md. Fazlul Kader

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    A useful small-model recipe for Bangla Sign Language gloss–sentence translation, with an evaluation-integrity question that needs answering before the headline numbers are trusted.

    the referee pass did not run

  6. The paper:

    Optimal Sample Complexity for Genus-Two Zeta Functions from Noisy Random Euler Products

    Mathematics · arXiv:2611.16358

    Taro Hayashi, Ryoichi Suzuki

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.

    Matching minimax bounds for recovering genus-two zeta numerators from noisy scalar observations; clean, honest, and technically sound.

    3 major objections, the first at §5.1, Lemma 5.2 and §6 · 9 minor

  7. The paper:

    DIAGNO: Diagonal Spherical Neural Operators for Heterogeneous Earth Dynamics Modeling

    Computer Science · arXiv:2611.16356

    Herui Li, Bin Lu, Haonan Qi and 4 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. DIAGNO is a solid, well-executed paper that introduces a genuinely novel architectural idea for spherical neural operators and backs it with thorough experiments. The missing error bars are a real reporting gap, but the central claim holds up.

    This review says the paper's mathematics is wrong. Pith did not check that against the paper's source.

  8. The paper:

    Optimal Seat Movement Strategies Among Modular Bus Units

    Computer Science · arXiv:2611.16357

    Shiyue Wang, Yuhao Liu, Zhibin Chen and 2 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. A technically solid, niche contribution that formulates and optimally solves a previously unoptimized subproblem in modular transit. The BSDP algorithm is a genuine advance for this specific problem, but the …

    5 major objections, the first at §6.5, Eq. (66) and surrounding text · 10 minor

  9. The paper:

    Energy gaps for critical Dirac equations on spheres

    Mathematics · arXiv:2611.16355

    Tian Xu

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. The two-dimensional energy classification is a clean, self-contained result; the higher-dimensional gap theorem is honest about its dependence on unquantified constants from prior work.

    4 major objections, the first at §4.3, Proposition 4.9 · 10 minor

  10. The paper:

    Postcritically Finite Unicritical Polynomials over CM Fields

    Mathematics · arXiv:2611.16354

    Kaoru Sano

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    A clean, complete classification of PCF unicritical parameters over CM fields; the proof is rigorous and the result is a natural extension of prior work.

    the referee pass did not run

  11. The paper:

    Weighted summability criteria for stability and instability of discrete dynamics with general growth rates

    Mathematics · arXiv:2611.16352

    Ariana G\u{a}in\u{a}, Cristian L\u{a}zureanu, Nicolae Lupa

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up. Solid extension of Datko criteria to general growth rates; the paper is clean and honest about its scope, but the main idea (time rescaling) is borrowed and the results are incremental.

    8 minor

  12. The paper:

    HyBridge: Bridge-Guided Self-Supervised Hyperbolic Hypergraph Representation Learning

    Computer Science · arXiv:2611.16351

    So-Bin Jung, David Yoon Suk, Sang-Wook Kim

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · of version 1 of the paper; version 2 is newer · what was read was not recorded

    Holds up, with conditions. HyBridge is a solid, well-executed hypergraph representation learning paper with a clear novel idea (hypergraph-specific bridge scores), but the K=ground-truth-classes issue is a real soft spot that needs addressing before I'd fully trust the SOTA claims.

    4 major objections, the first at Section IV-B, Table VI · 6 minor

  13. The paper:

    Convolution on quantum tori I: Sharp Young inequalities and endpoint Sobolev embeddings

    Mathematics · arXiv:2611.16350

    Fedor Sukochev, Ramazan Tastankul, Kanat Tulenov and 1 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Solid paper: new convolution on quantum tori, sharp Young inequalities, and two open embeddings resolved. The stress-test concern about L1-boundedness of a Fourier projection is overstated—the map is a finite combination of conditional expectations, each L1-contractive. …

    the referee pass did not run

  14. The paper:

    An optical-frequency-comb-enabled unified infrastructure for quantum networks

    Physics · arXiv:2611.16349

    Yiting Lin, Zishuo Ren, Yunkun Zhao and 10 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Solid integration demo of timing, classical comms, and CV-QKD on a single comb carrier; the engineering is careful and the numbers are credible, but the reciprocity assumption for two-way time …

    the referee pass did not run

  15. The paper:

    Families of (Pluri)subharmonic Functions and Separate Subharmonicity

    Mathematics · arXiv:2611.16348

    Mansour Kalantar

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Solid potential theory paper that resolves a natural question about singular sets of envelopes; the counterexample in R^N for N≥3 is the real gem.

    the referee pass did not run

  16. Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: agrees with the reader. Referee: major revision.

    Solid ATLAS SMEFT combination across nine top+X processes; the methodology comparison is the real novelty, and the paper is honest about its LO EFT parameterisation limitation.

    4 major objections, the first at §3.1, Eq. (3) · 8 minor

  17. The paper:

    MotionSkill: From Bipedal Motion Video to Control across Embodiments

    Computer Science · arXiv:2611.16346

    Philip Niu, Xiaofeng Han, Sylvie Pan and 1 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. Competent integration paper with honest numbers, but the 98% headline measures reference tracking from near-reference starts, not cross-embodiment transfer, and the paper never says so.

    6 major objections, the first at IV-B, Table II · 9 minor

  18. The paper:

    DRAMA: Dissecting Attention Redundancy for Accelerating Multimodal Diffusion Large Language Models

    Computer Science · arXiv:2611.16345

    Yi-Hsin Hung, Fangfu Liu, Shao-Yuan Lo and 1 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. Measured speedup is real and repeatable; the quality-preservation claim is weaker than the abstract suggests, but the paper is still a solid systems contribution.

    5 major objections, the first at Section 3.3.2, Table 10 · 7 minor

  19. The paper:

    Strong Well-Posedness and Path-by-Path Uniqueness for Fractional SDEs with Integrable Drifts

    Mathematics · arXiv:2611.16344

    Oleg Butkovsky, Khoa L\^e, Toyomu Matsuda

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: agrees with the reader. Referee: major revision.

    Strong well-posedness for fractional SDEs with integrable drifts under conditions that recover the Krylov–Röckner threshold as H→1/2; the proof is technically deep and the main results are solid, but condition (2.3d) is a genuine restriction whose necessity is not demonstrated.

    4 major objections, the first at §2.1, condition (2.3d) · 9 minor

  20. The paper:

    Grothendieck groups and Auslander–Reiten relations in extended module categories

    Mathematics · arXiv:2611.16343

    Yajie Xiang, Xiao Zhuang

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.

    Solid paper, main result is new and the proof is clean. The stress-test concern about the bounded negative extension sequence is a real gap in the verification for C_m(A), but it looks fixable. The paper deserves a serious referee.

    6 major objections, the first at Section 4.2, after Lemma 4.5 · 8 minor

  21. The paper:

    HARMONY: an efficient and accurate deep learning framework for prediction of experimental vibrational spectra

    Physics · arXiv:2611.16342

    Xinyu Lu, Bowen Li, Yi Rong and 8 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up. HARMONY is a solid, well-engineered framework that delivers on its claims; the metadata generalization concern is real but the paper acknowledges it and the evidence is stronger than the stress-test suggests.

    4 major objections, the first at Section 2.3, Fig. 3D · 8 minor

  22. The paper:

    SUMNO: Spatially Unrolled Multigrid Neural Operator for Fluid Flow Surrogates

    Physics · arXiv:2611.16341

    Yingqi Hu, Nan Deng, Changxiao Shao and 1 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    A genuine multigrid-to-network design with an elegant per-axis periodic attention mask; the architecture deserves review, but the headline 30% margins rest on single-run numbers and no released code.

    the referee pass did not run

  23. The paper:

    The Bolza Surface Does Not Locally Minimize the Diameter Function

    Mathematics · arXiv:2611.16340

    Ryo Matsuda, Keita Yamazaki

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.

    A clean, self-contained criterion for non-minimality of the diameter function, applied to the Bolza surface; the load-bearing geometric claim in Lemma 4.2 is not independently verifiable from the cited source.

    This review says the paper's mathematics is wrong. Pith did not check that against the paper's source.

  24. The paper:

    Hand in Silhouette: Synthetic-to-Real Multi-View Hand Reconstruction via Binary Masks

    Computer Science · arXiv:2611.16339

    Leiyao Cui, Lecheng Ruan, Zihang Zhao

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.

    SilHand is a solid, well-executed paper that makes a real contribution to multi-view hand reconstruction by using binary masks to sidestep the synthetic-to-real appearance gap. …

    4 major objections, the first at §4.2, Table 1 · 6 minor

  25. The paper:

    Total edge irregularity strength of cubic graphs

    Mathematics · arXiv:2611.16338

    Aleams Barra, Suhadi Wido Saputro, Hajime Tanaka

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.

    The paper claims to prove the Ivančo-Jendrol' conjecture for all cubic graphs via a constructive labeling algorithm. The proof has a gap in the swap step that the authors do not address.

    3 major objections, the first at Section 3, after equation [b56] · 5 minor

  26. The paper:

    Memory-Efficient Parallel Policy Learning for Collapse-Reactive Retreat via Hybrid Terrain Modeling

    Computer Science · arXiv:2611.16337

    Yuki Kadokawa, Ritsuki Matsunaga, Yuqi Yang and 2 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. Clever hybrid terrain model for parallel RL on collapsible ground; real-robot validation is thin but the simulation results are solid.

    4 major objections, the first at Section V-K, Fig. 15 · 6 minor

  27. The paper:

    Visibility graphs of irregularly sampled two-dimensional fields via Voronoi tessellations

    Mathematics · arXiv:2611.16336

    Francisco J. Mu\~noz, Juan Carlos Nu\~no

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    A clean extension of visibility graphs to irregularly sampled 2D fields, with honest mean-field predictions and a clear null model. The main result is plausible but the numerical evidence for the scale-free tail is still provisional.

    the referee pass did not run

  28. The paper:

    From More to Better: Causal Inference and Digital Experimentation in the Age of AI

    Computer Science · arXiv:2611.16335

    Winston Chou, M{\aa}rten Schultzberg, Lo-Hua Yuan and 18 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    No verdict was given on this paper.

    4 major objections, the first at §1 Introduction, footnote 1, and Appendix Table 1 · 6 minor

  29. The paper:

    Collective information backflow from a local population record: Identifiability and learning

    Physics · arXiv:2611.16334

    Yifan Shi, Pengju Chen, Duan Wang and 2 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    A careful, honest model study whose real contribution is the separation between ideal identifiability and finite-shot estimability of a backflow diagnostic from a population record.

    the referee pass did not run

  30. The paper:

    When Elements Fail: Weighted Fault-Tolerant Matroid Bases

    Computer Science · arXiv:2611.16333

    Madhumita Kundu, Soumi Nandi, Saket Saurabh

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Resolves two open questions from Bentert et al. with clean new constructions; the polynomial-certificate compression is the real technical meat, and it holds up on close reading.

    the referee pass did not run

  31. The paper:

    Estimates of the Schwarz constant for monogenic functions in ℝ3

    Mathematics · arXiv:2611.16332

    Hung Manh Nguyen (University of Transport, Communications, Hanoi and 1 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. Solid bounds on an open extremal constant in monogenic function theory, with a clean primal-dual reduction; minor typos but no load-bearing flaws.

    6 minor

  32. The paper:

    Statistical correlations between turbulent structures and dissipation proxies in near-Earth space: the MMS 2023-2024 unbiased magnetosheath campaign

    Physics · arXiv:2611.16331

    Le Viet Anh Doan, Luca Sorriso-Valvo, Pierre Raynal and 12 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. Systematic multi-proxy comparison on an unbiased MMS dataset — the central clustering result is real but the shuffle test is weaker than claimed.

    3 major objections, the first at Appendix B, Figure 7 · 8 minor

  33. The paper:

    Snoopie: A Multi-GPU Communication Profiler and Visualizer

    Computer Science · arXiv:2611.16330

    Mohammad Kefah Taha Issa, Muhammad Aditya Sasongko, Ilyas Turimbetov and 3 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.

    4 major objections, the first at §4.4, §5.5 · 22 minor

  34. The paper:

    Information Thermodynamics in Closed Quantum Many-Body Dynamics

    Physics · arXiv:2611.16329

    Yusuke O. Nakai, Shoki Sugimoto, Ryusuke Hamazaki

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up. Clean theorem, honest scope: work from MITE matches the canonical ensemble under outcome-local feedback, and the GHZ example marks the boundary; the soft spot is motivation for the locality conditions, not the proof.

    4 major objections, the first at §3, Eq. (6) and Supplemental Material §S1 · 12 minor

  35. The paper:

    Counting circles in Kleinian circle packings

    Mathematics · arXiv:2611.16328

    Samuel C. Edwards

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up, with conditions. Skeptic: does not hold up. Referee: major revision.

    Sharp circle count for all bounded Kleinian packings, reaching the Lax-Phillips error exponent. The proof is coherent and the main advance is real. …

    4 major objections, the first at §3, Lemma 3.13 · 13 minor

  36. The paper:

    Designing Information in a Forest: Algorithmic Aspects

    Computer Science · arXiv:2611.16327

    Konstantin Zabarnyi

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · of version 1 of the paper; version 2 is newer · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: agrees with the reader. Referee: major revision.

    Solid algorithmic paper with a load-bearing but unverified lifting step in Theorem 10.

    This review says the paper's mathematics is wrong. Pith did not check that against the paper's source.

  37. The paper:

    Tracing dependency networks explains how origins shape downstream vulnerability

    Physics · arXiv:2611.16326

    Ruiwu Niu, Muhammad Azhar, Micha\"el Antonie van Wyk and 1 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up, with conditions. Skeptic: does not hold up. Referee: major revision.

    Proposition 1 is a definitional identity, but the paper's real contribution is the systematic analysis of how sampling and root multiplicity affect edge importance—a useful framework, not a discovery.

    4 major objections, the first at Proposition 1 (Eq. 3) · 6 minor

  38. The paper:

    Optimal staircase structure for bacterial adaptation in antibiotic landscapes

    Physics · arXiv:2611.16325

    Kento Matsukawa, Shin-ichi Sasa, Namiko Mitarai

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. Solid theoretical extension of the staircase model with a clear trade-off and scaling law; the simulation validation is narrower than the claims warrant.

    4 major objections, the first at §IV D 1, Fig. 4 · 10 minor

  39. The paper:

    Galaxy Clustering Topology in Observations and Cosmological Simulations

    Physics · arXiv:2611.16324

    Fuyu Dong, Changbom Park

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up. Solid, careful topology comparison that confirms modern simulations broadly reproduce SDSS genus statistics, with HR4 MBP slightly ahead of hydro simulations. …

    3 major objections, the first at §4.1, Figure 2, Table 1 · 7 minor

  40. The paper:

    Does Deep Knowledge Tracing Learn Semantic Relations Between Knowledge Components?

    Computer Science · arXiv:2611.16323

    Kia Karbasi, Mahdi Saiedi, Kevin Hong and 1 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: minor revision.

    A careful negative result: DKT's learned KC relations are not primarily semantic, but the central comparison is weakened by unquantified stability of the DKT relation graph itself.

    2 major objections, the first at §3.4, §5.1 · 4 minor

  41. Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Does not hold up as stated. The paper's central empirical claim is contradicted by its own Table IV, and the theoretical analysis is generic and unverified. The bidirectional Mamba idea is not new. This is not ready for peer review.

    This review says the paper's mathematics is wrong. Pith did not check that against the paper's source.

  42. The paper:

    From Large Language Models to Efficient System One Models via Adaptive Computation

    Computer Science · arXiv:2611.16321

    Minh-Anh Nguyen

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. Solid analysis of where decisions form inside a fine-tuned LLM, plus a practical method that exploits it; the main caveat is that everything rests on one 4B backbone.

    4 major objections, the first at Section 3.1, Table 1, Figure 2 · 8 minor

  43. The paper:

    3D radiative transfer of K-series lines of He-like ions with SKIRT

    Physics · arXiv:2611.16320

    N. Sameshima, A. Lauwers, B. Vander Meulen and 5 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. Solid incremental extension of SKIRT to He-like K-series lines, verified against multiple benchmarks; the paper is honest about its limits and deserves a serious referee.

    3 major objections, the first at §2.3, Eq. (1)-(2) · 8 minor

  44. The paper:

    Global-in-time dynamics of the pressureless Euler/incompressible non-Newtonian equations

    Mathematics · arXiv:2611.16319

    Jinwook Jung, Subin Kim

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. Solid extension of pressureless Euler theory to non-Newtonian fluids; the bootstrap closure has a genuine gap in the density estimate constant, but the main ideas are sound and the paper is worth engaging with.

    This review says the paper's mathematics is wrong. Pith did not check that against the paper's source.

  45. The paper:

    Benchmarking AI risk behaviors

    Computer Science · arXiv:2611.16318

    Luhan Mikaelson, Robert Adragna, Emmett Brosowsky and 1 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · of version 1 of the paper; version 2 is newer · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.

    Systematic benchmark of LLM risk behaviors with solid descriptive findings; the causal claim about EV maximization is correlational and the paper's own limitations undercut it.

    4 major objections, the first at §5.2.1, §7.3, Appendix G · 10 minor

  46. The paper:

    Wanda-Guided Sparse Perturbations for Efficient Zeroth-Order Optimization

    Computer Science · arXiv:2611.16317

    Ziqing Wen, Xiaohui Song, Jiahuan Wang and 4 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. WIS-MeZO is a sensible incremental combination of Wanda and MeZO; the empirical work is solid but the theoretical justification has a gap that the authors acknowledge but do not resolve.

    3 major objections, the first at Section 5.2, Figure 2, Appendix C · 4 minor

  47. The paper:

    Laser cooling of Th−: Revised bound-state structure and a more efficient cooling scheme

    Physics · arXiv:2611.16316

    Shaowei Tian, Chaofan Shi, Ran Si and 2 more

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.

    Thorough ab initio revision of Th⁻ bound states; the new cooling scheme is plausible but the 'one repump' claim rests on a single tiny branching fraction that is not stress-tested.

    3 major objections, the first at Table I / SM Table I · 4 minor

  48. The paper:

    Shared Item-Level Error Limits the Aggregation of Small Language Models in Fermi Estimation

    Computer Science · arXiv:2611.16315

    Carolina Fortuna, Blaz Bertalanic

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    Holds up, with conditions. The paper convincingly shows that on continuous estimation tasks, the 1/sqrt(N) averaging argument fails because item-level error dominates, but the headline rho=0.906 may be slightly inflated by run/prompt variation not controlled in the ANOVA.

    This review says the paper's mathematics is wrong. Pith did not check that against the paper's source.

    4 major objections, the first at §3.1, Eq. (1)–(2); §4.1; Table D.2 · 7 minor

  49. The paper:

    Rigidity of compact quasi-Einstein manifolds with boundary and low-dimensional focal sets

    Mathematics · arXiv:2611.16314

    Matheus Andrade Ribeiro de Moura Hor\'acio

    Pith says

    Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded

    The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.

    This review says the paper's mathematics is wrong. Pith did not check that against the paper's source.