The Inference Report

Retrieval over corpora that mix several domains often returns relevant but wrong-domain evidence that ranking metrics miss and that conformal risk control bounds only marginally, under-covering the worst domains. This work introduces C3R, a drop-in control layer that, from an inferred domain posterior and no query-time label, certifies a per-domain contamination budget where feasible and otherwise abstains rather than silently violating; on the hardest domains it guarantees a reduction, not a tight bound. The core is a two-split scheme built on risk-controlling prediction sets, whose finite-sample transfer bound crosses from the inferred to the true domain with fully estimable slack, supports heterogeneous budgets, and inverts for deployment. Population validity rests on this bound and a controlled simulation; across a thousand resampled calibrations the certificate never violates (a stability result) while marginal control violates the most-contaminated domain in every draw, and soft demotion retains more recall than the strongest calibrated cascade at equal certified contamination. The method replicates across open testbeds including an independent one from public federal regulations, and an LLM-judged downstream probe indicates wrong-authority grounding rises with contamination and falls under control. The layer is frozen-stack and reranker-agnostic.

Wildfire detection from satellite imagery is a semantic image segmentation problem that has proven to be difficult due to challenges such as class imbalance, feature complexity, and atmospheric interference. In this paper, we build on the foundational U-Net image segmentation model to develop a quantum-hybrid solution in hopes of more effectively modeling the high-dimensional spectral feature space of the Sen2Fire dataset. We inject a variational quantum circuit in the bottleneck portion of U-Net, specifically the QuFeX and QB-Net ansatzes. We test a classical Feature Pyramid Network (FPN) for further comparative analysis of the model, and we also explore classical improvements to the U-Net model and its training process, including a compression of parameters, alternative loss functions, and uniform mixing of input data. Our primary finding is that under matched conditions, both QB-Net (with an $F_1$ score of 31.18) and QuFeX ($F_1 = 30.79$) outperformed the classical U-Net baseline results ($F_1 = 28.71$). Additionally, the classical FPN achieved a comparable score of 31.13. A crucial finding was that data mixing removed a significant domain shift between the geographically-separated train and test sets, which boosted the classical FPN $F_1$ score to 39.76. We validate the architecture's robustness and generalizability to the wildfire detection problem via cross-dataset transfer on the California Burned Areas (CaBuAr) dataset. Overall, we find that quantum machine learning has potential to provide an advantage in the problem of wildfire image segmentation, and further experiments will continue to validate and expand upon this finding.

Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes. State-of-the-art algorithms such as PPO, RLOO, and GRPO inherit their rollout topology from RLHF: for each prompt, N independent trajectories are sampled from the initial state, and an advantage is computed by subtracting a group baseline. This design ignores a defining property of agent sandboxes. They are deterministic, snapshottable, and resumable from any intermediate state. We argue that this property enables a fundamentally different rollout topology: rather than N independent trees of depth T, one can construct a single tree of N leaves whose siblings share prefixes, and therefore share variance. We instantiate this idea as Branching Policy Optimization (BPO), a sandbox-native RL algorithm that (i) adaptively snapshots the sandbox at high-entropy decision points along a backbone trajectory, (ii) forks K alternative actions per branch point and rolls out each to termination, and (iii) computes per-step advantages from sibling returns rather than from independent prompts. We prove this estimator is unbiased and has strictly lower variance than the trajectory-level baseline, with the reduction equal to the prefix-explained portion of return variance. On WebShop, ALFWorld, and SWE-bench Verified with Qwen2.5-7B and Llama-3.1-8B backbones, BPO improves success by 3.6--6.1 absolute points over GRPO and RLOO at matched compute, halves gradient-norm variance, and matches the best baseline using 38% fewer policy updates.

Financial sentiment extraction has largely relied on news text and supervised extraction against return labels alone, leaving 10-K filings -- and volatility, the target risk disclosure is arguably best suited to informing -- comparatively unexplored. We extend a supervised lexicon-learning approach to 10-K filings and their Item 1A risk-factor sections, training sentiment scores against both return and volatility labels at three levels of aggregation: sector, portfolio, and individual firm. Across 1,383 filings from 94 Nasdaq-100 technology constituents (2006--2023), we evaluate the resulting twelve sentiment metrics on classification accuracy, correlation with realised market outcomes, and qualitative lexical content. Full-filing text produces more accurate sentiment at the sector and portfolio level for both targets, but this reverses at the individual-firm level, where the narrower Item 1A section performs better -- an effect we attribute to the interaction between document volume and the amount of independent training signal available at each level of aggregation. A Loughran-McDonald dictionary baseline is consistently, strongly negatively correlated with price at every level tested, underscoring the value of a supervised approach for regulatory disclosure text. These findings, and the design choices they motivate, establish the sentiment-generation methodology underlying a subsequent, larger-scale, multi-source system.

Reliable, low-latency uplink connectivity is a key requirement for C-V2X networks in dense urban environments, where fast channel variations and blockages often degrade direct vehicle-to-infrastructure links. Multi-hop relaying can restore coverage, but relay-link activation under radio, capacity, and routing constraints results in an NP-hard optimisation problem, typically solved via Mixed-Integer Linear Programming (MILP), whose runtime scales poorly with graph size. This paper introduces an edge-aware Learning-to-Optimise framework for real-time relay selection. Each V2X snapshot is modelled as a directed graph: node features encode vehicle state and traffic demand, while edge features capture radio-link capacity. An offline MILP oracle generates optimal relay configurations that supervise a Graph Isomorphism Network with Edge Features (GINE), enabling edge-level relay activation through a single forward pass, with tightly bounded inference latency. To bridge learning and exact optimisation, we also propose a hybrid GINE-Pruned MILP (GP-MILP) strategy in which GINE predictions prune the MILP search space. Experiments on a large-scale dataset generated via an OSM-SUMO-GEMV$^2$ pipeline show that GINE closely matches MILP decisions at the link level (accuracy 0.9589), F1-score (0.9544) on validation) and yields consistent end-to-end connectivity gains over a 1-hop MILP baseline (up to 9.2% with four RSUs and 12% with two RSUs). Inference latency remains tightly bounded, with all evaluated instances completing within 5~ms. Moreover, GP-MILP preserves MILP-equivalent solutions (same objective value) while achieving solver runtimes below 30~ms for more than 98%) of the graph instances, making MILP-grade optimisation compatible with stringent NR-V2X latency budgets.

World models are widely used in offline reinforcement learning (RL) to improve sample efficiency and generate experience beyond a fixed dataset. However, they are vulnerable to model exploitation where data coverage is thin. Prior work addresses this either by collecting more expert demonstrations, which is often expensive, unsafe, or unavailable, or by conservative algorithms that avoid uncertain regions, which limits generalization. We propose instead to repair exploitation directly using human preferences over imagined rollouts, leveraging the strong intuitive physics that allows humans to easily spot egregious dynamics hallucinations. We formalize this as Dynamics Learning from Human Feedback (DLHF), a Bradley-Terry preference loss over trajectory log-likelihoods under a learned dynamics model. Unfortunately, naive DLHF is sample inefficient, so we introduce RENEW, which uses epistemic uncertainty to focus finetuning where the model is most exploitable. We evaluate on several Jumanji and classic control environments and find that while naive DLHF requires an outsize preference budget, RENEW makes the framework practical by improving sample efficiency, limiting catastrophic forgetting, and reducing exploitation in pretrained world models. Taken together, our results provide initial evidence that preferences can supervise world model dynamics directly, offering a new approach to addressing exploitation in offline model-based RL.