Searcharxiv⌕ Search

arXiv subjects

Amir Rafe

Publications and source records attributed to Amir Rafe.

16 recordsLinked to original sources

SignalAudit-QD: A Reproducible Audit Resource for External Signals in AI-Query Forecasting

SignalAudit-QD is a reproducible audit resource for testing whether a dated public signal adds information beyond query history in a fixed 20-term U.S. AI panel. It aligns two archived Google Trends extractions with eight USPTO AI-patent publication streams and releases origin-indexed predictions, paired losses, provenance, executable tests, and tamper-evident run manifests. Both inputs are retrospective reconstructions obtained after the modeled 2020--2023 origins; the task is therefore a pseudo-origin assay within frozen measurement vintages, not a historical deployment simulation. In the designated one-month comparison, adding a two-component patent block to a level ridge changes macro mean absolute error by +0.0012 Trends points, with conditional 95% moving-block interval [-0.0363,+0.0387]. This establishes neither aggregate benefit nor equivalence. Alternative dimensions, semantic mapping, patent definitions, a second extraction, and a three-month horizon remain unresolved; persistence-anchored and nonlinear hosts instead show model-specific worsening, tiny for the anchored fit. Matched timing controls expose availability assumptions, while a planted-signal assay detects only the largest tested injection. A within-query high-interest alert demonstrates the released interface but not online utility. The contribution is a bounded negative case study and an extensible evidence schema for auditing external-signal claims in temporal information retrieval.

cs.IR↗

Estimating Uncoded Crash Factors with Tabular Foundation and System One Models: Kumo Tabular and Jev

Road safety programs count the coded fields of police crash records, while the officer's narrative, which often records factors the fields omit, is rarely read. A safety office thus cannot tell how much its counts miss or where to review. This study develops and evaluates a system that joins both views of the 5,601,890 Texas crashes from 2017 to 2025 into population estimates with stated validity. An in-context tabular foundation model, Kumo Tabular, reads the coded record of every crash, a calibrated System One model, Jev, reads the narratives of two probability samples, and human judgments recalibrate its probabilities. A multiwave predict-then-debias estimator joins the three tiers, and a second human tier drawn with recorded probabilities checks the estimates by design. For hydroplaning, medical episodes, fatigue, animals, and phone use, the narrative documents more injury crashes than the coded field, 15,074 against 7,340 for phone use, and the human check agrees with all fifteen estimates within its margin. A re-read list ranked by Kumo Tabular finds confirmed discordance 7 to 58 times as often as random reading. At the planning cost of human coding, one further round of human judgments would cut the root mean square relative half-width from 22.0 to 16.2 percent, against 21.2 for reading every narrative. Two calibrated readers of different views, joined by a sampling design, give a safety office counts, a discordance map, a validated re-read list, and a reading budget, with Kumo Tabular reading the table at 15 times the speed of TabPFN 3.5.

stat.AP↗

Benchmarking System One decision models against trained classifiers and language models for automated decision gates

Software that hands branching decisions to a model needs a declared option and a probability it can threshold. Typed decision models, also called System One models, return such probabilities without generating text, while supervised classifiers and generative language models are the established alternatives. One harness sends eight decision-model checkpoints from six families, including the hosted model Jev, and four open generative models from three developers the same semantic requests, and scores trained and zero-shot classifiers on the same workflow, intent, emotion and social-science items. With task labels, a fine-tuned DeBERTa-v3-large has the highest observed accuracy on every labeled benchmark but one. Without labels, no decision model is significantly more accurate than Jev on workflows or intents, but Gemma-4-31B matches it on workflows and exceeds it on CLINC-150 at higher cost and latency. Stated probabilities of generative models become unreadable when replies miss the key format, whereas key likelihoods avoid this but can saturate. A guaranteed 5 percent risk leaves Jev 0.528 of the intent decisions, and an in-scope threshold still accepts 0.310 of out-of-scope requests. On typed-decisions, swapping yes and no flips 50.5 answers per hundred for Jev and at least 16.8 for every generative model tested, against at most 6.5 for four fine-tuned decision checkpoints. Exposure to a benchmark's training data explains the largest lead of an open checkpoint, which vanishes on rater-labeled emotions. An intent-trained first stage escalating to Gemma-4-31B reaches that model's accuracy at about Jev's price. The results yield condition-dependent design rules for automated decision gates.

cs.LG↗

CHOIR: heterogeneity-aware conformal prediction for crash injury severity across driver safety strata

Transportation agencies increasingly predict crash-injury severity with statistical and machine-learning models, but these models do not state how often their output contains the recorded injury level or for which groups of drivers it fails, a gap that matters most for motorcyclists and unrestrained drivers. This study develops and evaluates a certification layer that gives any fitted severity model a finite-sample, distribution-free coverage guarantee within prespecified safety strata. The layer, CHOIR (Conformal Heterogeneity-aware Ordinal Inference with Risk control), combines groupwise and weighted conformal prediction with conformal risk control to return contiguous KABCO intervals, and adds a declared sensitivity analysis for medically assessed injury and bounds on fatal omission. It is evaluated on 4.04 million Texas crashes from 2017-2023, one sampled driver per crash, with seven base models from the ordered logit to a tabular foundation model, and on held-out counties and later years. Under one pooled threshold every model reaches 0.90 coverage overall but covers motorcyclists or unrestrained drivers at 0.868 or lower, and class-balanced gradient boosting covers unrestrained drivers at only 0.374. Calibration within four safety strata places all 28 model-by-stratum estimates between 0.898 and 0.907, at the cost of sets spanning 3.6 to 4.6 of five categories for these groups, and the certified ordered logit is within 0.03 categories of the narrowest model. Injury-model coverage should therefore be certified within safety groups rather than on average, calibration rather than model complexity determines validity, and a statewide threshold should not be applied to small rural counties without local calibration data.

stat.ML↗

Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev)

Crash datasets that carry an investigator narrative hold information the coded fields omit. Coding those narratives at scale has been blocked by three obstacles. Frontier large language models are costly at that scale, their generated text cannot be verified, and no rule says how much output a human must check. This paper formulates narrative coding as gated, typed decisions answered by Jev, a System One model that returns probabilities over analyst-defined options and generates no text. A screen covered 499,500 Texas narratives and 195,857 were coded with a 27-question schema. Cost is governed by schema size rather than narrative length. The probabilities are audited against coded fields and against 2,416 blinded human judgments drawn under a stated sampling design. Two frontier large language models are benchmarked on the same records. Against human labels the typed model attains an F1 of 0.908. One frontier model gains 0.059 and the other is indistinguishable from it. Calibration varies by model rather than by paradigm, so each model must be audited. Recalibration on the same labels reduces calibration error by a factor of 3.3. Agreement with coded fields understates fidelity to the narrative by a median of 0.26 in kappa. A resolution-floor bound covers any model that reports probabilities on a discrete grid. A review budget over flagged records gives the records a human must read per variable and per year. Adding the calibrated variables to the coded fields raises the injury and fatal crashes attributed to nine factors by 10,747 per year.

cs.CL↗

Counting the Uncounted: Population-Level Surveillance of Documented Pregnancy and Fetal Harm in Police Crash Narratives with a System One Model (Jev)

Motor-vehicle crashes are a leading cause of traumatic fetal death in the United States, yet no crash database records pregnancy. Existing estimates come from national investigation samples with wide intervals, trauma registries seeing only the injured, or record linkage in a few states. Police narratives record pregnancy whenever it matters at the scene, and no study has read them at population scale. We read every police crash narrative in Texas from 2017 through 2025, 5,018,079 in total. A regular-expression screen flags 6,840 candidates, which Jev, a calibrated System One decision model, reads under an eight-question schema, returning probabilities and no text. It confirms 5,333 as documenting a pregnant person involved in the crash, with role, stage and post-crash condition. The same model reads 499,306 of the remainder under the presence question, to estimate what the screen missed. Blind human adjudication of a probability-stratified sample gives weighted sensitivity 0.999 and specificity 1.000, from which the Rogan-Gladen estimator and a bootstrap give 5,467 crashes with a documented pregnancy, with a 95% interval of 5,306 to 5,577, including 58 crashes documenting fetal harm. Person-level records give a rate of 1.13 to 1.45 per 1,000 female drivers aged 15 to 49. Measured against a live-birth expectation from vital statistics, narratives document 2.56% to 3.09% of expected pregnant drivers, and documented-case status is most strongly associated with the driver's own recorded injury, at an odds ratio of 21.7.

stat.AP↗

Who Bears the Risk When Generative AI Enters Transport? A Distributional Sociotechnical Audit of Algorithmic Equity, Synthetic-Data Validity, and Public Trust

Generative artificial intelligence is entering transportation through traveler-facing advisories, synthetic crash-record generation, and policy decision support. Existing governance frameworks lack transport-specific statistical tools to measure distributional risks across heterogeneous populations. We develop a Distributional Sociotechnical Audit (DSA) that integrates algorithmic equity, synthetic-data validity, and public-attitude heterogeneity into one empirical pipeline. The audit analyzes 5,760 persona-controlled queries to four LLM families across 12 demographic cues and four transport topics, uses two cross-family judges and a Wasserstein-2 Equity Dispersion Index, tests three FARS crash-record generators with conditional projected maximum mean discrepancy (cpMMD), fits a Bayesian ordered-logit model to Pew American Trends Panel Wave 152 (N = 4,538), and combines the signals into a continuous Sociotechnical Risk Index. Congestion-pricing advice has the highest persona-based dispersion (mean EDI = 1.96; highest direct EDI = 2.20). CART synthetic crash records fail all conditional tests (p < 0.001), while the Gaussian copula has borderline conditional stress (p = 0.105) despite passing marginal checks. Attitudes to AI vary across demographic strata. Distributional audits and continuous risk indices with sensitivity reporting offer a more defensible basis for transport GenAI governance than categorical approval tiers, which show a 75% assignment flip rate under weight perturbation.

cs.CY↗

Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mamba

Structured State Space Models (SSMs) have become a prominent class of sequence models, developed against two long-standing difficulties: the sequential computation and gradient propagation limits of Recurrent Neural Networks (RNNs), and the quadratic time and memory cost of self-attention in Transformers. By combining structured recurrence with state-space representations, SSMs attain linear or near-linear scaling in sequence length and hold a constant-size recurrent state during autoregressive decoding, so that no key-value cache grows with context. This paper is a structured review of the lineage running from the Structured State Space Sequence model (S4), through its diagonal and simplified successors S4D, Diagonal State Spaces (DSS) and S5, to the selective models Mamba and Mamba-2, and on to SSM-attention hybrids. Rather than describing models one at a time, the analysis is organized around cross-cutting design dimensions: input-dependent selectivity, the recurrent and convolutional views and when each is preferable, diagonalization, cache behavior at inference, hardware-aware kernels, and hybridization. Structured state-space duality is treated as a central thread, because it accounts for the equivalence between the recurrent and the attention-like form and for why hybrid designs work. Reported efficiency and accuracy results are presented with their measurement configuration and evidence level, because observed speedups reflect the combined effects of the algorithm, implementation kernel and hardware rather than an intrinsic property of the model alone. SSMs are competitive with Transformers and more efficient in specific long-context regimes, whereas attention retains an advantage on tasks dominated by exact retrieval and associative recall. The review closes with limitations, failure modes, deployment considerations and open problems.

cs.LG↗

Socio-Conformal Calibration in Complex Survey Data: Marginal Validity Is Not Enough for Subgroup Reliability

Machine-learning systems used in survey-based social measurement require uncertainty estimates that are reliable across population subgroups, not merely valid in aggregate. We study ordinal conformal prediction for five-level AI-attitude forecasting on the Pew American Trends Panel (Wave 152; n=4,591; 12 race x education subgroups), comparing standard split conformal, Mondrian (group-specific) conformal, and a regularized Mondrian comparator across 100 respondent-disjoint splits with survey-weighted evaluation. Standard conformal achieves nominal marginal coverage for all four base predictors but leaves weighted subgroup gaps of ~13 percentage points. For the strongest predictor (XGBoost), Mondrian worsens the fairness-efficiency trade-off: weighted set size rises by +0.036 (dz =1.66) while the weighted subgroup gap grows by +0.013 (dz =0.30). A regularized comparator that shrinks group thresholds toward the global quantile mitigates this instability (Delta gap = -0.001, Delta size = +0.012) but does not yield a decisive fairness gain. Failure analysis traces the mechanism to calibration-cell fragmentation interacting with group-specific confidence mismatch. The negative result persists across alternate outcome codings and subgroup granularities, demonstrating that nominal marginal validity is insufficient for subgroup reliability and that naive group-specific calibration is not a dependable fairness remedy in complex survey settings.

stat.ME↗

Heterogeneous Ordinal Structure Learning with Bayesian Nonparametric Complexity Discovery

Public attitudes toward artificial intelligence are heterogeneous, ordinally measured, and poorly captured by any single dependency graph. Existing ordinal structure learners assume a shared directed acyclic graph (DAG) across all respondents; recent heterogeneous ordinal graphical-model approaches focus on subgroup discovery rather than confirmatory cluster-specific DAG estimation; and latent profile analyses discard dependency structure entirely. We introduce a heterogeneous ordinal structure-learning framework combining monotone Gaussian score embedding, Bayesian nonparametric (BNP) complexity discovery via a truncated stick-breaking prior, and confirmatory fixed-K estimation with cluster-specific sparse DAG learning. The key methodological insight is a discovery-to-confirmation workflow: the nonparametric stage calibrates plausible archetype complexity, while inner-validated confirmatory refitting yields stable, interpretable structural estimates. On the 2024 Pew American Trends Panel AI attitudes survey, Wave 152 (W152) survey, (N = 4,788, 8 ordinal items), the confirmatory K*=5 model reduces holdout transformed-score mean squared error (MSE) by 25.8% over a single-graph baseline and by 4.6% over mixture-only clustering. A controlled tiered semi-synthetic benchmark calibrated to W152 structure validates recovery across difficulty regimes and transparently reveals failure modes under stress conditions.

stat.ML↗

Coupled-NeuralHP: Directional Temporal Coupling Between AI Innovation Exposure and Public Response

Artificial intelligence innovation exposure and public response co-evolve, but innovation arrives as irregular event streams while response is observed monthly. We introduce Coupled-NeuralHP, a hybrid event-plus-state model linking eight-domain USPTO AI patent publication streams to a train-only Google Trends response index. Under the cleaned response protocol, the validation-selected one-way real-data variant gives the best held-out innovation count forecasts in the registered comparison set (pseudo-log-likelihood -30.4 vs. -34.7; root mean squared error (RMSE) 471 vs. 532) while matching the stronger multi-lag factor-family baseline on response RMSE (0.295). Ablations show that the real-data response signal is carried mainly by the structured forecast head, whereas the reverse response-to-innovation block is not supported on held-out count prediction. Across 60 semi-synthetic replications with known structure, the broader coupled family recovers innovation-to-response links much better than vector autoregression with exogenous inputs (VARX) (F1 = 0.734 vs. 0.386). A placebo-controlled 2022 split-date analysis finds no robust milestone-specific regime break.

cs.CY↗

Community Driving-Safety Deterioration as a Push Factor for Public Endorsement of AI Driving Capability

Road traffic crashes claim approximately 1.19 million lives annually worldwide, and human error accounts for the vast majority, yet the autonomous vehicle acceptance literature models adoption almost exclusively through technology-centered pull factors such as perceived usefulness and trust. This study examines a moderated mediation model in which perceived community driving-safety concern (PCSC) predicts evaluations of AI versus human driving capability, mediated by Generalized AI Orientation and moderated by personal driving frequency. Weighted structural equation modeling is applied to a nationally representative U.S. probability sample from Pew Research Center's American Trends Panel Wave 152, using Weighted Least Squares Mean and Variance Adjusted (WLSMV)-estimated confirmatory factor analysis on ordinal indicators, bias-corrected bootstrap inference, and seven robustness checks including Imai sensitivity analysis, E-value confounding thresholds, and propensity score matching. Results reveal a dual-pathway mechanism constituting an inconsistent mediation: PCSC exerts a small positive direct effect on AI driving evaluation, consistent with a domain-specific push interpretation, while simultaneously suppressing Generalized AI Orientation, which is itself a strong positive predictor of AI driving evaluation. Conditional indirect effects are negative and statistically significant at low, mean, and high levels of driving frequency. These findings establish a risk-spillover mechanism whereby community driving-safety concern promotes domain-specific AI endorsement yet suppresses domain-general AI enthusiasm, yielding a near-zero net total effect.

cs.CY↗

Latent Profiles of AI Risk Perception and Their Differential Association with Community Driving Safety Concerns: A Person-Centered Analysis

Public attitudes toward artificial intelligence (AI) and driving safety are typically studied in isolation using variable-centered methods that assume population homogeneity, yet risk perception theory predicts that these evaluations covary within individuals as expressions of underlying worldviews. This study identifies latent profiles of AI risk perception among U.S. adults and tests whether these profiles are differentially associated with community driving safety concerns. Latent class analysis was applied to nine AI risk-perception indicators from a nationally representative survey (Pew Research Center American Trends Panel Wave 152, n = 5,255); Bolck-Croon-Hagenaars corrected distal outcome analysis tested class differences on nine driving-safety outcomes, and survey-weighted multinomial logistic regression identified demographic and ideological predictors of class membership. Four classes emerged: Moderate Skeptics (17.5%), Concerned Pragmatists (42.8%), AI Ambivalent (10.6%), and Extreme Alarm (29.1%), with all nine driving-safety outcomes significantly differentiated across classes. Higher AI concern mapped monotonically onto greater perceived driving-hazard severity; the exception, comparative evaluation of AI versus human driving, was driven by trust rather than concern level. The cross-domain covariation provides person-level evidence for the worldview-based risk structuring posited by Cultural Theory of Risk and yields a four-class segmentation framework for AV communication that links AI risk orientation to transportation safety attitudes.

cs.CY↗

Exploring the Determinants of Pedestrian Crash Severity Using an AutoML Approach

This study investigates pedestrian crash severity through Automated Machine Learning (AutoML), offering a streamlined and accessible method for analyzing critical factors. Utilizing a detailed dataset from Utah spanning 2010-2021, the research employs AutoML to assess the effects of various explanatory variables on crash outcomes. The study incorporates SHAP (SHapley Additive exPlanations) to interpret the contributions of individual features in the predictive model, enhancing the understanding of influential factors such as lighting conditions, road type, and weather on pedestrian crash severity. Emphasizing the efficiency and democratization of data-driven methodologies, the paper discusses the benefits of using AutoML in traffic safety analysis. This integration of AutoML with SHAP analysis not only bolsters predictive accuracy but also improves interpretability, offering critical insights into effective pedestrian safety measures. The findings highlight the potential of this approach in advancing the analysis of pedestrian crash severity.

cs.LG↗

Exploring Factors Affecting Pedestrian Crash Severity Using TabNet: A Deep Learning Approach

This study presents the first investigation of pedestrian crash severity using the TabNet model, a novel tabular deep learning method exceptionally suited for analyzing the tabular data inherent in transportation safety research. Through the application of TabNet to a comprehensive dataset from Utah covering the years 2010 to 2022, we uncover intricate factors contributing to pedestrian crash severity. The TabNet model, capitalizing on its compatibility with structured data, demonstrates remarkable predictive accuracy, eclipsing that of traditional models. It identifies critical variables, such as pedestrian age, involvement in left or right turns, lighting conditions, and alcohol consumption, which significantly influence crash outcomes. The utilization of SHapley Additive exPlanations (SHAP) enhances our ability to interpret the TabNet model's predictions, ensuring transparency and understandability in our deep learning approach. The insights derived from our analysis provide a valuable compass for transportation safety engineers and policymakers, enabling the identification of pivotal factors that affect pedestrian crash severity. Such knowledge is instrumental in formulating precise, data-driven interventions aimed at bolstering pedestrian safety across diverse urban and rural settings.

cs.LG↗

Applied hybrid binary mixed logit to investigate pedestrian crossing safety at midblock and unsignalized intersection

Pedestrian's crossing from unsignalized locations at intersections or midblock locations is a risky decision that could lead to fatal accidents. Despite making a decision to accept a safe gap to cross the street is a personal choice, studying this phenomena and its affecting variables are crucial for accident analysis and traffic safety investigations. In this paper we used video taped data to study pedestrian gap acceptance behavior at an unsignalized intersection and a midblock facility in Tehran, Iran. Multi way ANOVA test indicates simultaneous effect of gender and child accompaniment have the highest effect on size of accepted gap and waiting time. In addition, number of rejected gap is mostly affected by the child accompaniment status. Investigation about critical gap shows in general, critical gap was bigger at unsignalized intersection and for women. We defined a latent variable named caution behavior based on some observable indicators and using structural equation modeling it was estimated and used as an input in a binary mixed logit model. This variable identified important in gap acceptance decision. Despite both structural equation and logit models are used in previous gap acceptance studies, but according to our best knowledge this is the first use of the hybrid mixed logit modeling approach in this field and we developed a new methodology to combine psychological and behavioral aspects of pedestrians' gap acceptance studies. Modeling approach shows pedestrian decision regarding acceptance or rejection of a gap to be highly influenced by the size of current gap, caution behavior and waiting time.

physics.soc-ph↗