arXiv:2606. 01632v1 Announce Type: cross Abstract: Estimating the economic contribution of a single patent inside a product that embodies tens of thousands of patents is a long-standing unsolved problem in intellectual property economics.
arXiv:2606. 09556v1 Announce Type: new Abstract: AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prompting, or reasoning scaffolds.
BLANC (Blank Landscape Analysis through NPMI Conditioning) is a three‑phase pipeline that uses multi‑view neural topic modeling across application/use, novelty, and inventive step, computes Normalized Pointwise Mutual Information (NPMI) to measure cross‑dimensional cluster association, and introduces a conditional detection step that flags combinations whose NPMI drops when the corpus is filtered by a keyword. The drop is quantified by a new metric, ΔNPMI, which identifies combinations that are established globally but unexplored locally. BLANC was evaluated on two USPTO corpora—machine learning/AI and glass compositions—by artificially depleting known technology combinations; it recovered 34.1% and 27.3% of the depleted pairs, respectively, while random removals rarely recovered the target, and it successfully identified a fluorine surface‑treatment × warpage‑suppression candidate in a proprietary float‑glass case.
The paper evaluates unsupervised embedding geometries for patent claim classification, comparing hyperbolic and Euclidean Variational Autoencoders trained on 45,000 US patents. Hyperbolic embeddings retrieve cross-category prior art 52% more often than Euclidean embeddings (18.76% vs. 12.34% of top‑10 results across 3,000 queries). The study also links classification breadth and patents per subgroup to model performance, offering a practical signal for when the method is most useful.
arXiv:2608.21924v1 Announce Type: new Abstract: Patent litigation imposes substantial costs on firms and distorts R&D incentives, making early risk identification a practically important task. While...
The paper introduces CreativePreferences, a large dataset of 2.8 million texts labeled by 317 million human preference judgments across seven creative domains, and explores how preference components that are tacit, articulable, and verifiable differ. By modeling these labels with executable programs, rubric banks, and densely trained models, the authors identify robust articulability and verifiability gaps—especially in domains like peer review and creative writing—and propose a novel measurement approach to estimate these gaps. The study demonstrates that fully articulated models can diverge from human preferences and that articulating preferences may shift them away from tacit dimensions, offering recommendations on task prompting and learning strategies. "whyItMatters":"The findings highlight that current AI preference modeling may miss crucial tacit aspects, potentially leading to misaligned or suboptimal outcomes in creative and evaluative tasks."
arXiv:2609.14170v2 Announce Type: replace-cross Abstract: Distributed multiple testing asks $N$ sites, each holding p-values for its own hypotheses, to control the false discovery rate (FDR) of the d...
arXiv:2605. 07663v2 Announce Type: replace-cross Abstract: Data valuation methods allocate payments and audit training data's contribution to machine-learning pipelines; however, they often assume passive contributors.
arXiv:2609.15219v1 Announce Type: new Abstract: Founders face two linked decisions: whether to pursue an idea before founding, and which operating actions and capital partners fit afterward. We prese...
The paper investigates higher-dimensional confidence sequences for monitoring multiple data streams. It introduces three extensions of one-dimensional betting-based CSs—a weighted Bonferroni region, a max‑wealth form, and a portfolio region—highlighting that the portfolio is tighter but computationally challenging. To make it practical, the authors propose tractable outer approximations (bounding box, π‑ellipsoid, and their intersection) that preserve validity and outperform existing methods in experiments, enabling applications such as multi‑metric A/B testing and model comparison.
QuadraSHAP is a method for computing ε-exact Shapley values in product games, where coalition values factor across players. It replaces the exponential coalition sum with a one-dimensional polynomial integral, using Gauss–Legendre quadrature to achieve exact values when ε = 0 and provides a computable error bound for ε > 0. The approach supports weighted sums of product games, enabling baseline and empirical interventional attribution for models such as log-link regression, Cox models, odds-scale classifiers, product-kernel machines, and tree-based models, and achieves logarithmic parallel time with efficient GPU evaluation even for hundreds of thousands of features.
The Data Differentiator Framework (DDF) is a composite scoring method that evaluates candidate data assets by combining a mutual‑information redundancy penalty, a cost‑normalized marginal utility score from an ablation study, and explicit governance inputs such as trust and strategic weights. It is executed through the Strategic Data Sourcing Agent Ecosystem (SDSAE), which bypasses costly model retraining for assets that fail governance or redundancy checks. In a credit‑card fraud benchmark, only the genuinely differentiated asset passed the significance gate and received an acquisition recommendation, while a fully redundant asset scored lowest.
arXiv:2603. 03672v2 Announce Type: replace Abstract: The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space.