IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs

We introduce ISOSCI, a benchmark of isomorphic cross-domain science problem pairs that separates reasoning ability from domain knowledge retrieval in LLM evaluation. Each pair shares identical logical structure but requires different domain-specific knowledge, enabling controlled attribution of reasoning-mode gains. Across five model pairs spanning four model families, we find that 91.3% of reasoning-mode gains are knowledge-dependent rather than structure-invariant (63/69 gains; Wilson 95% CI [82.3%, 96.0%]), directly challenging the assumption that chain-of-thought reasoning improves short-horizon procedural scientific problem-solving. Reasoning toggles on highly capable models provide less than 5 percentage points accuracy gain across all domains, and a reasoning-specialized model (o3-mini) that outperforms its standard counterpart on GPQA Diamond (+19.2 percentage points) underperforms on ISOSCI (-24.7 percentage points), showing that benchmark choice determines conclusions about reasoning utility. We release ISOSCI at https://huggingface.co/datasets/isosci/isosci

GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis

Prototype-based medical image classifiers present three clinical limitations: they treat findings as independent, silently amplify unsafe physician feedback, and require full retraining whenever a new finding is needed. We present GRAPE (Graph-Augmented Prototype Explanations), a unified architecture that addresses all three challenges. First, a Graph Attention Task Head models anatomical concept co-occurrence, boosting macro-F1 by +13.8,pp over the prototype baseline on TBX11K. Second, a Concept-Mismatch Safety Check - the first such mechanism in prototype-based medical classifiers - warns when the model's dominant finding inside a doctor-drawn region conflicts with the claimed label, catching 85% of erroneous annotations versus 51% for MC-Dropout with no extra inference cost. Third, Open-Vocabulary Prototype Anchoring aligns visual prototypes to clinical text, allowing a new finding to be added from a single labeled image without modifying any other component. On NIH ChestX-ray14, one Effusion example recovers full-supervision localization accuracy; on TBX11K, prototype maps achieve 2.6x better lesion localization than end-to-end baselines. All three capabilities add only +1~ms latency at interactive batch size. The project page is https://github.com/KurbanIntelligenceLab/GRAPE.

A Cost-Aware, Paired Protocol for Auditing Dynamic Tool Synthesis in Agentic Video Question Answering

Agentic Video Question Answering (VideoQA) systems invoke tools during inference, but their tool libraries are fixed, so recurring procedures are rebuilt from primitives on every question. Synthesizing composite tools could remove this overhead, but whether such expansion helps is hard to assess: final-answer accuracy, the standard metric, ignores inference effort, so it cannot reveal how a system shifts cost. We propose a cost-aware, paired protocol for auditing tool-augmented video agents. The protocol pairs two complete systems on the same input for each question and reports their net difference across accuracy and cost jointly. For each question, it sorts the paired outcome into one of six groups defined by joint correctness and by the change in visible tool calls, separating accuracy-preserving efficiency gains from harmful regressions. Significance is reported with McNemar's test and paired bootstrap confidence intervals. We instantiate the protocol on Dynamic-SAGE, an agentic VideoQA framework that synthesizes, validates, and persistently registers executable composite tools for reuse on unseen questions, and evaluate it against the SAGE baseline on SAGE-Bench. The audit reveals a multi-axis profile that a scalar accuracy comparison would miss: Dynamic-SAGE improves accuracy by 7.5 points (p < 0.001) and reduces reasoning turns and visible tool calls by roughly 28%, while shifting rather than reducing inference cost, as token usage rises 34% and cost 26%. Gains are largest on visual and open-ended questions and neutral on verbal and multimodal ones, and residual failures concentrate on hard, open-ended questions where the pipeline does the most work. By measuring accuracy and cost jointly, the protocol shows where the pipeline-level difference is reliable and where it is not. The code is available at https://github.com/KurbanIntelligenceLab/Dynamic-SAGE.

Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit

AI-generated video detection benchmarks such as GenVidBench and AIGVDBench are the de facto leaderboards, yet most evaluation protocols leave uncontrolled confounds that can inflate reported generalization. As an existence proof, a three-feature clip-length classifier reaches a leave-one-generator-out (LOGO) AUC of 0.998 on GenVidBench under unaudited evaluation, while measuring nothing about motion. A 20-paper survey finds none applying all six standard controls that would catch this, so we combine them into an audited protocol and apply it to six representative feature sources (three published detectors and three repurposed signal sources), re-running it cross-dataset on AIGVDBench. The audit both debunks and certifies: the trivial classifier collapses to near chance (0.529), a CLIP baseline is caught carrying dataset identity, and the 2025 forensic detector WaveRep clears the floor at out-of-distribution LOGO AUC 0.996 with chance-level real-vs-real coherence. At a deployable FPR of 0.1%, multiple high-AUC methods fall to single-digit recall and the leaderboard order changes, so we recommend an audited tuple (AUC, above-floor margin, operating-point recall, and calibration) over a single number. As a white-box positive control, we add TemporalSpec (codec motion vectors); via cross-substrate feature fusion (XSFF), a second substrate adds genuine complementarity that survives the audit. We release VidAudit, to our knowledge the largest unified and audited detector collection for this task, providing 14 detectors behind one plugin API, a leaderboard, and Croissant metadata, available at https://github.com/KurbanIntelligenceLab/vidaudit. Together, the protocol and toolkit move evaluation from leaderboard rank toward whether a result measures what it claims.

STEMGym: Benchmarking Sequential Decision-Making under Dose Budgets in Autonomous Electron Microscopy

A central premise of autonomous scientific imaging is that smarter navigation, whether Bayesian, RL-based, or otherwise adaptive, is the principal lever for sample-efficient acquisition. We present evidence to the contrary in scanning transmission electron microscopy (STEM), an atomic-resolution imaging modality whose every measurement deposits damaging electron dose. We introduce STEMGym, an open-source Gymnasium benchmark of 15 physics-simulated STEM worlds spanning five materials, three difficulty levels, and four characterisation tasks, scored by the Dose-Efficiency Curve area (DEC-AUC), a single scalar capturing the information-vs-dose Pareto frontier. Across 33 agent configurations under realistic dose budgets, the dominant determinant of dose efficiency is the analyst (perception) pipeline, not the navigator: pairing a trained CNN analyst with naïve raster scanning raises DEC-AUC by 5.5x over a CNN-free raster baseline (0.287 vs.\ 0.052), while substituting Bayesian or adaptive finite-state-machine navigation for raster yields no statistically significant further gain. Production-tier vision-language models further underperform task-specific CNNs by {\sim}13x on crystallographic defect analysis. By decoupling perception, navigation, and planning under a unified dose budget, STEMGym reframes where ML effort should be invested in autonomous electron microscopy and provides the measurement infrastructure to test it.

Geometric Algebra Meets Cartesian Tensors: Higher-Order Equivariance for Interatomic Potentials

$\mathrm{Cl}(3,0)$ interatomic potentials, despite their algebraic elegance, predict force magnitudes accurately but force directions poorly. Across ten rMD17 molecules, every $L \leq 1$ baseline in our twelve-model study attains aggregate force-cosine similarity below $0.25$. The cause is structural. The geometric product of two vectors in $\mathbb{R}^3$ realises only the $L=0$ and $L=1$ components of its irreducible representation content, leaving the symmetric-traceless rank-2 component absent from the per-edge bilinear that drives each message-passing layer. We address this with CliffordSTF, which couples the Clifford multivector to closed-form symmetric-traceless tensor tracks at ranks two and three through bilinear cross-track contractions, using a single learned bilinear and no Clebsch--Gordan tables, Wigner-$D$ matrices, or e3nn calls. On rMD17, CliffordSTF raises aggregate force-cosine similarity from $0.055$ (base Clifford) to $0.551$, an order-of-magnitude relative directional gain, alongside improved magnitude accuracy (force MAE $15.8\%$ lower; energy MAE $10.9\%$ lower). It outperforms all CG-free or body-ordered baselines in our study (all $\leq 0.17$). On catalysis benchmarks, CliffordSTF achieves the best out-of-distribution S2EF energy MAE on OC22 in our experiments, and the best in-distribution energy MAE among $L \geq 2$ methods on OC22 IS2RE. An eleven-variant ablation shows the two tracks are complementary: neither alone matches the combined model.

Intrinsic 4D Gaussian Segmentation from Scene Cues

Dynamic 4D Gaussian Splatting reconstructs deforming scenes with high fidelity and is increasingly adopted as a representation for dynamic 3D scenes. Putting such a scene to use, for editing, manipulation or motion analysis, first requires segmenting it: grouping the Gaussian primitives into coherent objects. Current pipelines obtain this grouping by importing 2D masks from foundation models such as SAM and lifting or distilling them into the Gaussian representation. In dynamic scenes these masks must be generated across many frames and views, which is costly, and the resulting segmentation can depend strongly on the quality and consistency of those external masks. We ask how much object-level structure can instead be recovered from the Gaussians themselves, and propose Intrinsic-GS, a training-free, mask-free method that builds a sparse affinity graph over Gaussian primitives from appearance, orientation, scale, deformation-trajectory and non-learned rendered-boundary cues. The graph is partitioned with Leiden community detection, requiring no foundation model and no learned feature field. On the standard 4D Gaussian segmentation benchmarks, Neu3D and HyperNeRF, Intrinsic-GS recovers substantial object structure without mask supervision, reaching 0.746 mIoU on Neu3D and 0.575 on HyperNeRF; on Neu3D, a geometry-only variant reaches 0.902 mIoU, matching SAM-supervised TRASE. On HyperNeRF, Intrinsic-GS runs 12.5x faster than the mask-generation and feature-rendering stages used by mask-supervised pipelines. These results suggest that much of the segmentation signal is already encoded in the Gaussians themselves, offering a fast, mask-free direction for 3D and 4D Gaussian segmentation that may also point toward more generalizable, robust segmentation in settings where external masks are unreliable or expensive.

Topical Phase Transitions in Artificial Intelligence Research: Large-Scale Evidence and an Early-Warning Signature for Emerging Topics

Do research topics in artificial intelligence grow gradually, or do they advance through abrupt, detectable jumps? Analyzing 80,814 accepted main-track papers from five premier AI conferences (ACL, CVPR, ICLR, ICML, NeurIPS) spanning 2017 to 2025, we show major AI topics advance through topical phase transitions: remaining marginal for years, then surging across venues within one to three years. Large language models became the dominant cross-venue topic by 2025, diffusion models rose with comparable abruptness, and language-model methods crossed into computer vision via vision-language models, whereas reinforcement learning compounded smoothly, distinguishing genuine phase transitions from ordinary growth. This structure is our primary contribution: a large-scale, cross-venue characterization of how AI research reorganizes. We then ask whether a transition leaves a detectable footprint before it peaks. We define an early-warning signature, four publication-dynamics criteria frozen on 2017-2021 data, and evaluate it out of sample on 2023-2025 transitions, obtaining a precision of 27% and recall of 63% against a 13.5% base rate. Applied to 2025 data, the signature flags reasoning and test-time compute, agentic AI, multimodal LLMs, retrieval-augmented generation, and world models as topics to monitor over 2026-2028. The source code is also publicly available on GitHub at https://github.com/KurbanIntelligenceLab/ai-phase-transitions.

Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation

Evaluation language is typically treated as a fixed English default in agentic code benchmarks, yet we show that changing the judge's language can invert backbone rankings. We localize the Agent-as-a-Judge prompt stack to five typologically diverse languages (English, Arabic, Turkish, Chinese, Hindi) and evaluate 55 DevAI development tasks across three developer-agent frameworks and six judge backbones, totaling 4950 judge runs. The central finding is that backbone and language interact: GPT-4o achieves the highest satisfaction in English (44.72\%), while Gemini leads in Arabic (51.72\%, $p<0.001$ vs.\ GPT-4o) and Hindi (53.22\%). No single backbone dominates across all languages, and inter-backbone agreement on individual requirement judgments is modest (Fleiss' $κ\leq 0.231$). A controlled ablation further shows that localizing judge-side instructions, not just benchmark content, can be decisive: Hindi satisfaction drops from 42.8\% to 23.2\% under partial localization. These results indicate that language should be treated as an explicit evaluation variable in agentic benchmarks. Full requirement-level judgments and runtime statistics are released for reproducibility.

IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video

Unsupervised physical parameter estimation from video lacks a common benchmark: existing methods evaluate on non-overlapping synthetic data, the sole real-world dataset is restricted to single-body systems, and no established protocol addresses governing-equation identification. This work introduces IRIS, a high-fidelity benchmark comprising 220 real-world videos captured at 4K resolution and 60\,fps, spanning both single- and multi-body dynamics with independently measured ground-truth parameters and uncertainty estimates. Each dynamical system is recorded under controlled laboratory conditions and paired with its governing equations, enabling principled evaluation. A standardized evaluation protocol is defined encompassing parameter accuracy, identifiability, extrapolation, robustness, and governing-equation selection. Multiple baselines are evaluated, including a multi-step physics loss formulation and four complementary equation-identification strategies (VLM temporal reasoning, describe-then-classify prompting, CNN-based classification, and path-based labelling), establishing reference performance across all IRIS scenarios and exposing systematic failure modes that motivate future research. The dataset, annotations, evaluation toolkit, and all baseline implementations are publicly released.