# Research Papers — 2026-07 · bundle page 144 of 222 > Full-text markdown of papers #7151–7200 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/144 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/143.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/145.md) ### Calibrated Trust, Not Sharper Prediction: An Empirical Test of Uncertainty Fusion Authors: Surya Saka Published: 2026-07-11 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.14617v1 A recurring proposal in legal AI is to improve case-outcome prediction by fusing uncertainty tools (evidence graphs with belief propagation, sequential Bayesian odds updating, Dempster-Shafer combination, and conformal prediction) into one pipeline. We test this on 1,000 real European Court of Human Rights cases from LexGLUE and FairLex, predicting whether the Court found a Convention violation from the case's fact paragraphs. We compare three families across two frontier LLMs (Claude Opus 4.8 and GPT-5.5) as per-fact evidence estimators: (A) the raw LLM, (B) the LLM routed through the fusion pipeline, and (C) a term-frequency baseline through the same pipeline. Across roughly 4,750 tests we find: (1) on discrimination (AUROC around 0.83) the pipeline yields no improvement over either the raw LLM or the baseline; a frontier LLM used directly is the strongest single discriminator. (2) Naively composing an LLM with Bayesian-odds and Dempster-Shafer fusion more than doubles calibration error (ECE from about 0.16 to 0.46) via a prior-mismatch mechanism that replicates across both models. (3) Dempster-Shafer fusion is actively unsafe on long chains, committing confidently to wrong labels at below-chance accuracy; we recommend removing it. (4) The pipeline's genuine value is operational: routed through a conformal selective-prediction layer, the system decides which cases to automate and which to escalate. After removing Dempster-Shafer, recalibrating, and applying class-conditional risk control on the full 1,000-case set, the tuned engine auto-clears at 96.8 percent accuracy with 0.5 percent errors escaping and 96.3 percent caught for review, versus 85.9 / 3.8 / 72.1 for an untuned baseline. The contribution of such pipelines in law is calibrated trust, not sharper prediction. --- ### Request-Level Energy Attribution for Batched LLM Serving Authors: Qi Luo, Kunlin Li, Ziwen Wang, Dongsheng Wang, Yun Chen Published: 2026-07-11 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2608.00026v1 Batched LLM serving improves throughput but complicates energy accounting. GPU power telemetry is aggregate, whereas sustainability reporting, chargeback, and workload analysis often require request-level energy charges. Existing inference-energy benchmarks report model-, phase-, or token-level energy, and recent carbon-accounting work motivates Shapley fairness conceptually. Neither provides measured request-level ground truth, so how far the accounting rules used in practice deviate from a fair allocation has remained unknown. We present JouleShare, an attribution framework with two components. An offline harness establishes this ground truth by replaying request subsets under vLLM with a reproducible protocol, integrating GPU power telemetry, and computing exact Shapley energy for each request. A lightweight calibration model, JCalib, then learns to predict Shapley shares from cheap request features for use at serving time. Across 16 model/workload runs, token-proportional attribution differs from exact Shapley by 0.440 normalized L1 on average under static batching and by 0.458 under continuous batching, a gap that reproduces across three data-center GPUs. JCalib reduces this error to 0.116 under static batching and 0.177 under continuous batching, below even a standalone-measurement baseline that is unavailable online, while preserving exact batch-energy efficiency. Sampled Shapley extends the measured reference to larger group sizes, where the gap persists and a single offline calibration remains the most accurate deployable rule. The results show that token attribution is not a reliable proxy for marginal energy under batched execution, and that measured Shapley ground truth can calibrate low-cost request features toward fairer attribution. --- ### DOSA: A Tree-Guided, Self-Regressive Framework for Long Document Structure Analysis Authors: Bohou Li, Benjamin Sowell, Mehul Shah, Mark Lindblad, Henry Lindeman Published: 2026-07-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22679v1 In visually-rich documents, information is encoded not only in individual page objects such as tables, headers, and text blocks, but also in the structural relations among them, making document structure analysis fundamental to information retrieval and document understanding. However, accurately inferring such relations remains challenging in multi-page documents with long-range dependencies and heterogeneous layouts. To address this, we propose a tree-guided and self-regressive framework, termed DOcument Structure Analyzer (DOSA), for inferring relations among page objects and reconstructing document-level semantic trees. DOSA processes documents chunk-by-chunk, fusing visual, textual, and layout features for each page object and predicting hierarchical and ordering relations. The predicted relations are used to incrementally construct a semantic tree, which is then leveraged as structural context to guide inference on subsequent chunks. Experimental results on five benchmarks demonstrate the effectiveness of DOSA, with improvements of up to 4 F1 points and 19 TEDS points on DocHieNet, the most challenging multi-page hierarchy benchmark. --- ### FORCE-Bench: A Benchmark, Dataset, and Evaluation Harness for Agentic AI in Enterprise Finance Authors: Wolfgang M. Pauli, Sarah Panda, Kidus Admassu, Said Bleik, Ademola Okerinde, Jeremy Reynolds Published: 2026-07-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.19409v1 Recent advances in large language models have accelerated deployment of agentic systems in operational finance. Existing benchmarks emphasize measuring general capabilities, instruction following, or safety, but few directly address the operational finance workflows that agentic systems are now being deployed to automate. Finance professionals require agents to not only provide factually sound and properly grounded information, but also ensure that this information is verifiable and consistently adheres to rules and constraints of the operational finance domain. We introduce FORCE-Bench, which contains 251 expert-annotated queries and evaluates responses using a rubric-based framework calibrated to the requirements of the operational finance domain, across eight dimensions: accuracy, citations, clarity, depth, groundedness, recency, relevance, and structure. FORCE-Bench assesses agentic systems on three task types: financial obligation research (querying ERP systems for accounts receivable and payable data), financial entity performance research (answering time-bound questions from public filings and market data), and business brief generation (synthesising multi-source company intelligence reports). To reflect real deployment conditions, we evaluate our purpose-built agent, as well as the general-purpose agentic systems, under common tool access and latency-bounded settings. Results show that general-purpose agentic systems do not consistently meet finance-domain quality requirements under operational constraints, while the purpose-built Finance Agent for Microsoft 365 Copilot is more reliable across dimensions. We release the dataset, rubrics, harness, and analysis code as open-source to support reproducible comparison and adaptation to other enterprise finance environments. --- ### A Synthetic 3D Gear Dataset for Manufacturing Quality Inspection (MFGNet-Gear) Authors: Ruo-Syuan Mei, Chenhui Shao Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16288v1 Quality control in smart manufacturing increasingly relies on data-driven methods, particularly deep learning, to automate the inspection of manufactured parts. Recent advances in three-dimensional (3D) metrology have enabled fine-scale assessment of dimensional accuracy, surface quality, and shape conformity. However, deep learning methods for point-cloud-based inspection require large volumes of labeled data covering part designs and defect types, which are costly and time-consuming to obtain. Moreover, defective parts are intrinsically rare in mass production, and the resulting class imbalance can degrade model performance and make rare defect types difficult to detect. Synthetic data generation (SDG) offers a promising approach to address these challenges by producing large, balanced, and fully annotated datasets. Yet, applying SDG to precision components requires representing part geometry and defect morphology parametrically, so that design and quality can be co-varied. This article describes MFGNet-Gear, a publicly available synthetic 3D dataset comprising 24,000 paired polygon meshes and point clouds across 12 gear designs and 4 quality classes, with 500 instances per design-quality combination. Gear geometries are generated with parametric computer-aided design software, with dimensional parameters perturbed by $\pm$0.0254 mm and defect parameters sampled from distributions representing defect morphologies. For each mesh, 100,000 points are uniformly sampled using Open3D and stored as N $\times$ 3 coordinate text files. Metadata labels identify the gear design and quality class, supporting part design classification, geometric defect detection, representation learning, and dataset benchmarking. MFGNet-Gear provides an open-source dataset for deep learning-based 3D metrology, with a reproducible generation pipeline extensible to additional part designs. --- ### Identity-Consistent Expression Fields: A Disentangled Neural Radiance Field Framework for Few-Shot Facial Expression Synthesis Authors: Minh Tran Published: 2026-07-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.16287v1 Neural Radiance Fields (NeRF) have enabled photorealistic novel-view synthesis of 3D scenes and, in the facial domain, have been extended to reconstruct and animate 3D face models from a small number of images. However, existing few-shot dynamic NeRF methods for facial expression editing typically warp a single learned feature volume conditioned on target expression parameters, which can cause identity-specific appearance details (skin texture, fine geometric structure) to drift when the model is driven toward expressions far from those seen in the few-shot input set. We propose Identity-Consistent Expression Fields (ICEF), a framework that explicitly disentangles a static, identity-specific radiance component from a dynamic, expression-conditioned deformation component, and introduces an identity preservation regularizer that constrains the deformation network to modify only expression-relevant regions while leaving identity-specific canonical appearance untouched. ICEF further incorporates a confidence-weighted conditional feature warping step that down-weights unreliable warps for target expressions that are far, in parameter space, from the observed few-shot inputs, mitigating artifacts observed in prior few-shot dynamic NeRF methods when extrapolating to novel expressions. We relate ICEF to prior few-shot dynamic NeRF, static 3D-aware face generation, and disentangled face-editing radiance field methods, and describe an evaluation protocol measuring both novel-expression rendering quality and, specifically, identity-consistency metrics across a range of expression-parameter extrapolation distances. --- ### Depth Estimators Are Implicit Neural Fields for 3D Scene Geometry Inpainting and Reconstruction Authors: Yingzhao Jian, Zihao Lin, Hehe Fan Published: 2026-07-11 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.16286v1 The 3D geometry of real-world scene data is often incomplete. Mainstream methods use depth estimators to inpaint missing structure. However, their prediction results can be inconsistent with observed geometry, or unreliable on out-of-distribution data. To solve these problems, we propose Neural Depth Field (NDF). Our key insight is that a depth estimator can also be a scene-level implicit field. As an estimator, it adapts to the target domain by learning observed depth data. As an implicit field, it fits the existing geometry to maintain consistency. Under this view, NDF addresses both problems through a single test-time optimization. Experiments show that NDF produces high-fidelity and globally consistent geometry across diverse scene data, ranging from indoor scans to satellite imagery. It reduces cross-view inconsistency by 63.3\% and improves inpainting accuracy by 23.1\%, achieving state-of-the-art performance in 3D scene geometry inpainting. The code is available at: https://github.com/Shadow-Dream/Neural-Depth-Field. --- ### A Shared Latent for Partially-Labeled Multi-Task Facial Affect Recognition Authors: Hong Hai Nguyen, Sy Phan Van, Soo-Hyung Kim, Van-Thong Huynh Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16285v1 Facial affect in the wild is naturally multi-task: valence-arousal, discrete expressions, and facial action units describe the same face. Yet real corpora annotate these tasks only partially and unevenly, so most systems mask the missing labels or impute pseudo-labels and forgo the cross-task signal. We instead cast partially-labeled multi-task learning as marginalization over a shared affect latent: one variational bottleneck mediates all three task decoders, so a frame annotated for one task shapes the representation the others use, and the masked objective reappears as the reconstruction term of an evidence lower bound. On s-Aff-Wild2, where only 37% of frames carry all three labels, the classes are severely imbalanced, and pretraining on the source data is disallowed, we isolate where this coupling acts. On a single backbone it lifts expression macro-F1 from 0.403 for a dedicated specialist to 0.446, which the masked-loss model does not reach; a second, near-peer backbone with decorrelated errors then breaks an action-unit ceiling that external action-unit data could not, while valence-arousal stays within noise. Every gain is disciplined by a matched-control negative; together these controls indicate that the rare-class failure is representational, not a matter of loss shaping. As each task's source is chosen on the evaluation split, we report the assembled result, a combined multi-task score of 1.679 on validation, as an in-sample endpoint and rest our conclusions on the controlled comparisons; a small, regime-dependent transfer of the expression advantage to AffectNet and RAF-DB is presented as exploratory rather than conclusive. --- ### Compaction as Epistemic Failure: How Agentic LLM Tools Fabricate Confirmed Results from Killed Processes Authors: Hiroki Tamba Published: 2026-07-11 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.13071v1 Agentic LLM coding tools compress long session histories into compaction summaries that subsequent sessions inherit as ground truth. This paper documents a failure mode in Claude Code where partial standard output from timed-out commands (exit code 143) is recorded in compaction summaries as confirmed results, propagating false positives across sessions and model versions without re-verification. The underlying mechanism is a conflation of observation and persistence, where information that appeared in the terminal is treated as equivalent to information written to durable storage. This finding extends the analysis of LLM self-evaluation failures reported in prior work on non-determinism in LLM-as-judge grading by showing that agentic tools exhibit analogous reliability deficits when reporting on their own operational outcomes. The failure has direct implications for any workflow that relies on agentic session continuity for data processing, scientific computation, or multi-step automation. --- ### Falsifiable Release Gates for Self-Improving Systems: Standing Invariants at Scale Authors: Deepak Soni Published: 2026-07-11 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.13070v2 Safety claims for self-improving agent runtimes are almost always self-graded: a policy file, a guardrail, a promise in a README. We describe falsifiable release gates, a methodology in which every new capability must pass a pre-declared, machine-checkable acceptance suite before it ships, while a fixed set of standing invariants is preserved across every gate. We instantiate it in Antahkarana, an open runtime, then do what a method paper is only vindicated by: we follow the same runtime as it grows and ask whether the guarantees survive. The safety-critical property, that no action reaches an effector without a capability token minted by a control ring, is machine-checked exhaustively over the reachable states of a bounded model; a deliberately broken model yields the shortest counterexample, so the checker demonstrably has teeth. We then carry the runtime through six further releases. Across every one, the action-safety invariants INV-1 through INV-6 held without a single change, and one release added three capabilities while introducing no new invariant. Under the same teeth discipline, six more machine-checked families were added: memory with provable unlearning, a governed agent, calibrated abstention over a post-quantum record, a harness of many sub-agents, the self-improvement loop itself, and the residency of what it produces. The acceptance suite grew from 122 tests to 563. The load-bearing result sits in the negative space: across more than a doubling of capability, the safety core was neither weakened nor redesigned. The last families are the first on real hardware: gated self-improvement compounds a small model from 20% to 70% accuracy while auto-rejecting a candidate that only inflates confidence, and the whole governed path costs 0.021 ms per request, 0.008% of model inference. We release the runtime, tools, and gate suite; every number reproduces with a single command. --- ### Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution Authors: Hironao Nakamura Published: 2026-07-11 Categories: cs.AI, cs.CL, cs.LO arXiv: https://arxiv.org/abs/2607.13069v1 Large language models produce chain-of-thought (CoT) reasoning that appears logically sound yet may not genuinely depend on its stated premises. We introduce interventional grounding audits, a black-box, step-level test of premise dependency: we intervene on a single premise by substituting its target predicate with a fresh symbol, re-run the model, and check whether each reasoning step's normalized conclusion (canonical predicate form) changes. We evaluate on ProntoQA, a synthetic multi-hop deductive reasoning benchmark with gold proof trees, where step-level premise dependencies are known. Applied to 50 ProntoQA problems with GPT-4o, our method achieves F1 = 0.806 on detecting proof-tree dependencies (F1 = 0.885 on predicate-determining dependencies; Recall = 100%), significantly outperforming a self-consistency baseline (F1 = 0.343; 95% bootstrap CIs non-overlapping). We further identify that 66% of correctly-solved problems contain at least one aligned step insensitive to a direct proof-tree dependency under consistent substitution -- all involving entity-introduction premises, a documented blind spot of the consistent-substitution evaluator -- a "right answer, wrong reasoning" signal invisible to passive methods. All audit certificates, raw outputs, and reproduction scripts are available in a public GitHub repository, and we discuss scope limits beyond formal, parsable benchmarks. --- ### Graph-Constrained Policy Learning for Extreme Clinical Code Prediction Authors: Amritpal Singh, Sebastian Torres, Khawar Shakeel, Syed Ahmad Chan Bukhari Published: 2026-07-11 Categories: cs.LG, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2607.11954v1 Clinical code prediction maps unstructured discharge summaries to ICD-10-CM leaf codes in a large, sparse, and deeply hierarchical label space. Most systems treat the task as flat multi-label classification, scoring codes independently and providing limited training signal for rare labels. We propose a graph-constrained traversal policy that formulates ICD prediction as a finite-horizon decision process over a pruned code hierarchy. A single language model descends the graph level by level, selecting valid child nodes until billable leaf codes are reached. This converts extreme multi-label prediction into sparse, hierarchy-aware subset decisions while guaranteeing structurally valid outputs. On MIMIC-IV discharge summaries, our best supervised policy, SFT-1+, achieves 0.709 micro-F1 on a curated 50-code subset and 0.527 micro-F1 on the full 15,761-code space, outperforming flat baselines including CAML, LAAT, and PLM-ICD. In the full setting, SFT-1+ improves over the strongest flat baseline by 0.044 micro-F1 and 0.157 macro-F1, suggesting that graph-constrained decomposition mitigates the rare-code bottleneck. A controlled factorial study evaluates architecture, training algorithm, and data budget. Across both scales, one shared policy matches a three-specialist cascade while avoiding its context-window overflow on 28-32% of full-space test notes. Increasing supervised trajectory data is the only intervention that consistently improves performance, while GRPO reinforcement learning provides no benefit over supervised continuation with matched data. These results show that simple graph-constrained policy learning can outperform more complex flat, cascaded, and reinforcement-learning alternatives for extreme clinical code prediction. --- ### When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal Authors: James E. Allchin Published: 2026-07-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.11953v4 Does a reinforcement-learning agent that earns reward learn its task's hidden state? We study this question with hidden finite automata that the agent partially controls. Because each automaton is known, we can normalize reward by the best achievable return and probe the network for the true state at every step. Together the two measurements separate failures that reward alone conflates. An agent can encode too little of a state its network could hold, or encode the state and still control poorly. Weak on-policy RL matches random play while the state probe stays at chance. State learning depends on the optimizer, the training budget, and the task's structure. Permutation automata provide a warning before training: no input symbol maps two distinct states to the same successor. On a stratified held-out set, 86 of 103 permutation automata fail the state probe, and the classification is stable across probe read-outs and recovery thresholds. Most of these failures come with weak reward. High reward without the state occurs but is rare. Non-permutation automata can also fail. Oracle-normalized reward alone therefore does not establish that the task's state was learned. --- ### When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary Authors: Jim Allchin Published: 2026-07-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.11953v2 Does a reinforcement-learning agent that earns high reward represent its task's latent state, or only a reward-correlated shortcut? Usually this is unanswerable: the "true state" is undefined. We make it exactly answerable with a white-box instrument: express the task as a hidden deterministic finite automaton (DFA), let the agent observe a symbol stream and intermittently choose the next symbol under partial control, with a sparse terminal reward for acceptance. Knowing the automaton gives two things for free: the optimal return (so reward becomes an interpretable normalized score) and the exact latent state at every step (so we can probe the agent's representation without ever showing it). Reward success and latent-state learning become separately measured quantities whose coupling is governed by three axes. Optimizer strength: under weak on-policy RL the agent can lock onto a reward-shortcut, earning reward with the state probe at chance; whether it escapes is set by optimizer strength, budget, and task structure -- a pre-registered control isolates the optimizer (PPO+GAE), which escapes fastest but only partially and with high seed variance. Task structure: permutation (group-language) structure is a warning sign computable from the transition function before any training, and held out on 153 capacity-controlled fresh automata it flags perception gaps at precision 0.86 (89 of 103), in one direction only. Observation informativeness: a label-free auxiliary is vacuous when observations carry no state and recovers it sharply once they carry any (a threshold, saturating near beta=0.1). The payoff is a distinction reward-only evaluation cannot make: a perception gap (state not linearly recoverable, though representable) versus a planning gap (state recoverable but not exploited). Reward alone cannot localize which; high reward alone is not evidence the state was learned. --- ### Scalable Optimal Transport Algorithm for Network Alignment Authors: Elaheh Hassani, Durga Mandarapu, Qi Yu, Hanghang Tong, Ariful Azad Published: 2026-07-11 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2607.11952v1 Network alignment identifies node correspondences across different networks and is a fundamental primitive in many data science applications, including social network analysis, fraud detection, and knowledge graph integration. However, state-of-the-art network alignment methods often achieve high accuracy by repeatedly constructing and updating dense matrices, sacrificing scalability in the process. To address this scalability limitation without compromising alignment accuracy, we present FastAlign, a scalable, sparsity-aware framework for optimal transport-based network alignment. Rather than introducing a new alignment model, FastAlign preserves the original OT formulation and reinterprets its computation as a set of recurring mixed sparse-dense operations. FastAlign combines sparsity-aware graph computation with domain-specific kernel fusion, including a custom SpMM kernel. Our results show that FastAlign achieves alignment quality comparable to state-of-the-art OT-based methods while substantially reducing end-to-end runtime up to 3.89x-9.45x on CPU and 2.24x-32.54x on GPU. --- ### GRID: Grammar-Railed Decoding for Enterprise SQL Generation Authors: Mohsen Arjmandi Published: 2026-07-11 Categories: cs.AI, cs.CL, cs.FL, cs.PL arXiv: https://arxiv.org/abs/2607.11951v1 Large language models can write SQL, but enterprise deployment demands more than plausible text: outputs must be syntactically valid, must respect per-role and per-schema policy, must carry provable (not best-effort) guarantees, must not slow down as generations grow, and must leave a compliance-grade record of every decision. We present GRID (Grammar-Railed Decoding), a grammar-constrained decoding engine that keys exact next-token masks on parser configurations (lexer scan state x LALR(1) stack) rather than on token sequences, and uses the incrementally advanced LALR(1) parser itself as a viable-prefix oracle. LLM tokens are bridged to grammar terminals by a byte-level trie walk with a context-independent/context-dependent split that makes cache-key soundness hold by construction. Role-based access control is compiled into the language: role projections subset the grammar's productions and schema lexicons restrict identifier terminals, so forbidden verbs and identifiers are unreachable at mask level. Four guarantees (soundness, completeness, termination, and near-constant per-token cost) are stated with explicit preconditions and each paired with a test or benchmark. Rust kernels bring the per-token mask to a 3.6-6.7 us median, ahead of llguidance at p50 and p90 on two tokenizers with zero false rejects; per-token guard cost is position-flat at n=16,000. On Spider, constrained decoding is worth +13 execution-accuracy points at 0.5B, and one checker-guided repair pass over the provably mask-unenforceable residue (column-level policy) lifts a 7B model to 94.5% executable. A hash-chained per-token audit trail replays bit-identically with 100% tamper detection. We state plainly what the mask cannot do (distribution faithfulness, column-level RBAC, non-LALR(1) languages) and where measured cost remains. --- ### The RG-Flow Transformer: Encoding Scale-Free Dynamics in Scarce EEG Authors: Dibakar Sigdel Published: 2026-07-11 Categories: cs.LG, cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2607.11950v2 Brain field potentials are scale-free: their power spectra follow a $1/f^β$ law whose aperiodic exponent $β$ tracks cortical state, and sleep depth in particular is a shift in $β$. We ask whether a transformer endowed with an explicit renormalization-group (RG) inductive bias the RG-Flow Transformer, which couples ordinary self-attention to a scale-aware stream with a learnable anomalous dimension $γ$, block-spin coarse-graining, and an entropy-gated synchronization bridge has an advantage over a parameter-matched vanilla transformer on \emph{real, scarce} EEG. Using the PhysioNet Sleep-EDF corpus with a strict leakage-free by-subject hold-out, we (i) benchmark RG-Flow against a param-matched vanilla transformer and a hierarchy-only ablation on 5-class AASM sleep staging, (ii) sweep the per-subject data budget to look for the inductive-bias crossover predicted when data are scarce, and (iii) test whether RG-Flow's learned $γ$ tracks the measured spectral exponent $β$ out-of-sample a quantity the vanilla model does not possess. Across $5$ subjects and $5$ seeds under leave-one-subject-out cross-validation, RG-Flow and the vanilla transformer are statistically indistinguishable on 5-class staging (77.3\% vs 77.0\% accuracy; paired $p=0.294$), and the predicted scarce-data crossover does not appear: vanilla is numerically ahead at every data-limited budget. What does separate the models is interpretability RG-Flow recovers the continuous spectral exponent out-of-sample ($β$-recovery $R^2 = 0.416$), a capability the vanilla architecture has no analogue for. --- ### BAT-RM: A Boundary-Aware Transformer with Region-Aware Multi-Directional Mamba for Clinically Deployed Cervical Cancer Radiotherapy Auto-Contouring Authors: Istiak Ahmed, Kazi Shahriar Sanjid, Galib Ahmed, Md. Tanzim Hossain, Md. Anwarul Islam, Shahrukh Khan, Md. Ashrif Rahman Arian, Md. Nishan Khan, Md. Misbah Khan, S M Hasibul Hoque, Rahnuma Shahrin Rista, Md. Jobairul Islam et al. Published: 2026-07-11 Categories: eess.IV, cs.AI arXiv: https://arxiv.org/abs/2607.11949v1 We present a clinically deployed end-to-end auto-contouring system for cervical cancer radiotherapy planning, anchored by the Boundary-Aware Transformer with Region-Aware Mamba (BAT-RM), a hybrid architecture that integrates Sobel-gated boundary attention, a linear-time, multi-directional Mamba module for long-range context, and a boundary-skeleton-guided fusion gate. This design achieves linear-time complexity for long-range context modeling, avoiding the quadratic cost of full spatial self-attention. The full pipeline spans multi-institutional data collection, rigorous inter-rater quality assurance, external validation in an independent cohort, and a web-based clinical interface natively compatible with Varian, RayStation, and Monaco. Against four baselines, BAT-RM achieves superior performance across seven anatomical classes, with statistically significant improvements in target volumes, including GTV and CTV, and in organs at risk such as the rectum and bladder. A prospective multi-center reader study involving 13 radiation oncologists demonstrated that AI assistance elevates junior oncologists' IoU from 0.899 to 0.965, approaching senior-level accuracy, while reducing contouring time by more than 80%. The system also reduced expert consultation rates and improved inter-reader consistency, reflecting gains in both efficiency and quality assurance. Following clinical deployment at a partner hospital, the system reduced patient wait times from days to hours without additional staffing, enabling same-day or next-day initiation of treatment for routine cases. BAT-RM demonstrates that a rigorous research pipeline, from data curation to clinical deployment, can translate directly into measurable patient benefit in resource-constrained settings where the demand for radiotherapy far exceeds specialist capacity. --- ### Ontology-Amplified Distillation and Contextuality Auditing for Sovereign Enterprise Language Models: A Combined Proof-of-Mechanism and Negative-Results Method Study Authors: Thanh Luong Tuan Published: 2026-07-11 Categories: cs.AI, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2607.11948v1 Regulated financial institutions operating under data-residency rules need tenant-owned language models that can run inside the institution's perimeter. This paper combines two related FAOS studies into one mechanism-and-control article. First, it reports a reduced-power proof-of-mechanism study of ontology-amplified distillation: a Qwen3.6-27B student is adapted to the Foundation AgenticOS ontology through supervised fine-tuning on frontier-teacher trajectories and ontology-grounded direct preference optimization (DPO), trained locally on a single Apple M5 Max from 47 synthetic, English-language, cross-domain preference pairs. On 40 held-out Vietnamese financial-domain tasks, the distilled student grounds 36 of 40 tasks (grounded rate 0.90; mean ontology term-coverage r_onto = 0.95 on a metric floored at 0.50), equal to the GPT-5 frontier baseline, which also grounds 36 of 40. The outcome is underpowered to establish equivalence: the paired-difference 95% confidence interval spans +/-4 tasks, and the run does not test or show the pre-registered amplification prediction that the student should exceed the frontier. Second, the paper consolidates a contextuality-audit method for enterprise-agent routing. In a separate negative-results pilot, the corrected canonical Contextuality-by-Default degree is zero for all Phase 1.3 groups in both the local-Qwen run and an explicitly labeled Gemma replication check; the useful signal is direct influence and construct coupling, not surviving residual contextuality. Together, the studies pair an ontology-grounded model-building mechanism with a governance diagnostic for deciding when apparent disagreement should trigger prompt standardization, multi-agent synthesis, or human review. The evidence supports neither deployability, safety, superiority, statistical equivalence, nor a contextuality-positive routing rule. --- ### Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite Authors: Yushi Hirose, Hiroo Irobe, Takafumi Kanamori Published: 2026-07-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.11947v2 Typical semi-supervised learning (SSL) methods rely on distributional assumptions, and their performance degrades when these are violated. While PNU learning, a risk rewriting method, offers a distribution-free alternative, it is restricted to binary classification and its variance optimality remains unclear. In this paper, we propose a generalized framework that constructs unbiased risk estimators using linear combinations of component risks, subsuming PNU learning and extending to multiclass classification. We derive the minimum achievable variance, demonstrating our estimator can attain lower variance than PNU in asymmetric loss scenarios. Furthermore, we establish a generalization bound directly linking this variance reduction to improved learning performance. Based on these theoretical insights, we introduce two practical SSL methods that empirically match or outperform existing approaches on binary and multiclass benchmarks. --- ### Hybrid Continual Learning for Low-Resource Australian Aboriginal Language Identification Authors: Pravina Mylvaganam, Ting Dang, Eliathamby Ambikairajah, Vidhyasaharan Sethu, Jingyao Wu Published: 2026-07-11 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2607.11946v1 Language identification is an important step toward integrating endangered Australian Aboriginal languages (AALs) into speech technologies supporting language revitalisation and digital inclusion. However, extreme data scarcity limits model performance. Transfer learning from high-resource languages shows promise but often suffers from catastrophic forgetting when adapting to new languages. Continual learning (CL) can mitigate this issue, though it remains challenging with very limited data. To address this, we propose two hybrid continual learning methods: Replay Augmented Elastic Weight Consolidation and Constraint Guided Knowledge Distillation to adapt pretrained speech models for AAL identification while preserving previously learned knowledge. Experiments on Warlpiri, Dalabon and Dharawal show that the proposed methods outperform fine-tuning and existing CL baselines, improving adaptation to multiple AALs while maintaining performance on previously learnt high-resource languages. --- ### Belief-reality separation lives in routing over a shared value slot in language models Authors: Oliver Steele, Jiangtao Wen, Yuxing Han Published: 2026-07-11 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.11945v2 Capable language models hold what a character believes apart from what is true: told "Anna believes the cup is blue; in reality it is red," they answer blue about Anna and red about the world. Where in the computation does that separation live? We show it rests on two separable mechanisms at two positions. A generic value slot binds the attributed value. A router at the query position selects which frame, the character's belief or reality, a query reads out. Two routes fill the slot: an asserted belief, whose value the text supplies, binds in directly; a derived belief, whose value must be inferred from what the character could see, arrives by a visibility-gated lookback. A subspace trained on either route steers the other, and only the derived route depends on described visibility. The slot itself carries no belief-reality tag: intervening on it moves a reality readout as strongly as a belief one. The separation lives instead in a dissociated pair of routing subspaces, which flip a query between frames without injecting the donor's value. These results hold across three architectures, on stimuli de-confounded against theory-of-mind-benchmark shortcuts; the behavior itself emerges between 3B and 7B across five model families. This paper develops the single belief-reality axis in depth; a companion paper shows the same slot-and-router format is shared across the other non-actual contexts a sentence can open (counterfactual, fictional, temporal). --- ### MAGE: Understanding Stability-Performance Trade-offs in Multi-component Prompt Optimization Authors: Prateek Singh Published: 2026-07-11 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.11944v1 How do different components of iterative prompt optimization interact, and what happens when they are combined? We investigate this through MAGE (Memory-Augmented Goal-directed Prompt Evolution), a controlled analysis framework for studying component interaction in prompt optimization. MAGE is not proposed as a superior optimizer in absolute terms; it integrates episodic memory, multi-objective Pareto selection, and adaptive evaluation as a platform for controlled ablation. Our experiments uncover a previously unreported phenomenon, the Prompt Optimization Coupling Effect (POCE): when multiple stochastic optimization signals operate within a closed reflective loop, they interact in ways that simultaneously improve performance and amplify variance, behavior that cannot be predicted by analyzing components in isolation. Three main findings emerge. First, failure-grounded reflection is essential: methods relying only on scores (OPRO) or abstract critique (Self-Refine) fail to improve prompts. Second, MAGE achieves 46.4% versus GEPA's 34.0% on GSM8K-Hard (+12.4%, P(MAGE>GEPA)=0.998, 5 seeds on gpt-4o-mini), with comparable variance (7.3% vs. 7.0%). Third, increasing candidate diversity reveals the clearest POCE signal: expanding the candidate pool from n=3 to n=5 improves mean accuracy by +21.6% while increasing variance by 3.7x. We further validate on Llama 3.1 8B and show POCE is headroom-dependent: when the base model already achieves high accuracy, variance amplification disappears. Finally, in low-data regimes (Ntrain=30), well-designed fixed prompts outperform all reflective optimizers, indicating that scaffold choice dominates optimizer choice. Our results suggest prompt optimization systems behave as coupled stochastic processes and should be evaluated in terms of both performance and stability, not just peak accuracy. --- ### BattVAE-GP: Generative Modeling of Long-Horizon Battery Degradation with Uncertainty Quantification Authors: Raghvender Raghvender, Mahdi Abid, Ferran Brosa Planella, Charles Delacourt, Arnaud Demortière Published: 2026-07-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.11943v1 Long-horizon physics-based simulations of battery degradation provide mechanistic insight but remain computationally expensive, limiting their use for dense exploration of operating conditions over extended cycle life. Here, we propose a hybrid physics-probabilistic learning framework for surrogate modeling of lithium-ion battery degradation trajectories at unseen charging rates. Cycle-resolved degradation data generated with a DFN/P2D electrochemical model in PyBaMM are first transformed into capacity-aligned voltage and derivative features and encoded using a Variational Autoencoder (VAE). The resulting two-dimensional latent space organizes degradation trajectories according to both cycle progression and charging protocol. A sparse multitask Gaussian process (GP) is then trained in this latent space using cycle number and C-rate as input variables, providing continuous interpolation of latent degradation dynamics together with posterior uncertainty estimates. Under protocol-level holdout evaluation, the latent-space GP accurately recovers unseen C-rate trajectories and exhibits uncertainty behavior consistent with the support of the training data. When queried at unseen interior C-rates, the model generates latent trajectories that remain coherently positioned between neighboring simulated protocols. Decoding the GP-predicted latent states through the frozen VAE decoder yields smooth voltage-capacity evolution, while Monte Carlo propagation of the GP latent posterior through an auxiliary latent to State of Health (SOH) predictor provides uncertainty-aware SOH estimates. The proposed BattVAE-GP framework therefore offers a computationally efficient and uncertainty-aware surrogate for long-horizon degradation modeling, providing a structured basis for extending battery health prediction toward richer operating conditions and future simulation-experiment fusion. --- ### How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit Authors: Daming Luo, Christy Liang, Junyu Xuan Published: 2026-07-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.11942v1 KV-cache compression methods are predominantly evaluated with the query appended to the context before compression -- a query-aware protocol. Yet the economic case for a compressed KV cache is reuse: compress a document once, answer many future questions against it. In that deployment, compression must happen query-agnostic -- before any question is seen. We present a matched-budget audit of six published compression methods against three trivial baselines on three open 7-9B models (144,300 paired evaluations on RULER-8192; 40,800 on LongBench; 50,000-resample paired bootstrap throughout). Everything is held fixed -- model, compression ratio, instances, decoding -- except the scoring rule. Three findings. (1) Query visibility changes the rankings: under the agnostic protocol, of the five audited methods that share a common attention backend, only KeyDiff beats a best-of-3 trivial baseline consistently (31 of 36 cells), and the most widely deployed method, SnapKV, loses to "keep the start and the recent window" on average (-0.066). (2) The per-method drop between the two protocols is ordered consistently with how visible the question is to each method's scoring signal, legible in its source code: from Delta=+0.198 for SnapKV (the question sits inside its 64-token observation window) down to Delta=+0.011 for KeyDiff (its score contains no query term at all). --- ### GenDiff: A Dose and Anatomy Aware Diffusion Model with Structural Prior Refinement for Low-Dose CT Reconstruction and Generalization Authors: Md Imam Ahasan, Guangchao Yang, A F M Abdun Noor, Kah Ong Michael Goh, S. M. Hasan Mahmud, Md Mahfuzur Rahman Published: 2026-07-11 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.11941v1 Computed tomography (CT) is a critical imaging modality for clinical diagnosis, but reducing radiation dose inevitably introduces severe noise and structured artifacts that degrade image quality. Existing deep learning-based low-dose CT (LDCT) reconstruction methods are typically optimized for fixed dose levels or specific anatomical regions, limiting their robustness and generalization in realistic clinical settings. We propose GenDiff, a generalizable diffusion-based framework for LDCT reconstruction that jointly models continuous radiation dose and anatomical information within a unified reconstruction network. The proposed framework integrates a Dose-Anatomy Encoder to learn acquisition-aware embeddings, a dose- and anatomy-conditioned cold diffusion backbone for iterative refinement, a physics-consistency update to enforce fidelity to the CT forward model, and a Structural Prior Refinement Module (SPRM) that preserves anatomical structures while suppressing dose-dependent artifacts. Extensive experiments on multi-anatomy clinical datasets, including unseen ultra-low-dose conditions as well as out-of-distribution phantom and animal datasets, demonstrate that GenDiff consistently outperforms state-of-the-art convolutional neural network and diffusion-based reconstruction methods. The proposed approach achieves superior reconstruction quality while maintaining strong robustness across different dose levels, anatomical regions, and acquisition domains, making it a promising solution for practical low-dose CT imaging. --- ### CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA Authors: Gengyu Zhang, Haiyin Ran, Zhengbao He, Yuhang Liu, Hanling Tian, Zhehao Huang, Xiaolin Huang Published: 2026-07-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.11940v1 As the scale of large pre-trained models continues to grow, fine-tuning them under limited memory budgets has become increasingly challenging. Low-Rank Adaptation (LoRA), currently one of the most widely adopted parameter-efficient fine-tuning (PEFT) methods, mitigates this challenge by optimizing only low-rank adaptation matrices, thereby greatly reducing the number of trainable parameters. With the parameter overhead substantially reduced, the activations retained for backpropagation have emerged as the primary remaining memory bottleneck during LoRA fine-tuning. To address this, we propose CARE-LoRA, a data-aware Compressed Activation REconstruction framework. By exploiting the inherent projection structure of LoRA, CARE-LoRA replaces the full input activation with the low-rank compressed activation naturally produced by the LoRA branch. It further computes a lightweight reconstruction matrix during the forward pass with negligible additional computation cost, which is used during backpropagation to reconstruct the gradient signal, thereby keeping LoRA matrices fully trainable. Extensive experiments across diverse models and downstream tasks demonstrate that, while substantially reducing the overall memory footprint, CARE-LoRA achieves competitive or even superior performance compared with standard LoRA and representative LoRA variants. Our code is publicly available at https://github.com/fishandyu/CARE-LoRA . --- ### TSCA-Net: Temporal-Spatial Clique Attention for Interpretable Multimodal Pedestrian Trajectory Prediction Authors: Md Mustafizur Rahman, Guangchao Yang, A F M Abdun Noor, Md Imam Ahasan, Md Mahfuzur Rahman, Md Ariful Islam Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.11939v1 Accurate pedestrian trajectory prediction in crowded environments remains challenging due to the multimodal uncertainty of human motion and the variable complexity of motion dynamics across different scene contexts. Existing goal-conditioned models rely on static displacement structures that assign equal weight to all historical time steps, standard graph attention mechanisms, and fixed-capacity motion decoders that cannot adapt to local prediction complexity. To address these limitations, we propose TSCA-Net, a trajectory prediction framework built upon three complementary modules. The Temporal-Spatial Clique Attention (TSCA) module introduces learnable temporal gating into clique-based goal-history interaction, enabling time-aware modulation of historical observations relative to each candidate goal. The Cross-Pedestrian Clique Potential (CPCP) module models asymmetric pairwise agent relationships through a dynamic clique potential framework with a time-varying social graph. The Adaptive KAN Grid Refinement (AKGR) mechanism dynamically adjusts the B-spline grid resolution of a Kolmogorov-Arnold Network-augmented LSTM decoder based on per-agent goal distribution entropy, balancing model expressiveness against overfitting across varying motion complexities. Extensive experiments on the ETH/UCY and Stanford Drone Dataset benchmarks demonstrate that TSCA-Net achieves state-of-the-art performance, with average ADE/FDE of 0.13/0.20 m on ETH/UCY and 6.95/10.43 pixels on SDD. Comprehensive ablation studies confirm the complementary contributions of all three proposed modules. --- ### Mathematics of Data Science Authors: Afonso S. Bandeira, Amit Singer, Thomas Strohmer Published: 2026-07-11 Categories: cs.LG, cs.AI, cs.IT, math.PR arXiv: https://arxiv.org/abs/2607.11938v1 This book is about the mathematical foundations of data science. 1. Introduction 2. Curses, Blessings, and Surprises in High Dimensions 3. Singular Value Decomposition and Principal Component Analysis 4. Linear Regression and Regularization 5. Graphs, Networks, and Clustering 6. Nonlinear Dimension Reduction and Diffusion Maps 7. Linear Dimension Reduction via Random Projections 8. Optimization for Data Science 9. Classification 10. A Mathematical Introduction to Deep Learning 11. Large Sample Limit of Graph Laplacians 12. Community 13. Concentration of Measure and Gaussian Analysis 14. Matrix Concentration Inequalities 15. Compressive Sensing and Sparsity 16. Low-Rank Matrix Recovery --- ### Mirror Horizon: Viable Path Entropy as a Measure of Bounded Reflection Authors: Tiantian Zhang Published: 2026-07-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.11937v1 Mirror Theory proposes that an intelligent system should be studied not only by what it represents, but by what coherent continuations it can sustain under repeated reflection. We make this claim operational through \emph{viable path entropy} (VPE), a finite-budget measure of verified continuation capacity. Given a mirror state, a rollout protocol, a verifier, and a mode map, VPE decomposes bounded capability into two parts: the probability of reaching a viable continuation and the diversity of verified continuation modes reached among successful rollouts. This paper restores the full theoretical scaffold behind the measure: intuition as local underdetermining constraint, taste as invariant-selecting pressure, reflection as taste-guided resolution of underdetermination, and geometry as the learned structure that makes future reflection stable. We then instantiate the theory in language-model reasoning experiments on GSM8K. Across Qwen2.5-Instruct models, 32 sampled rollouts per problem, and two reflection horizons, increasing the token budget from 96 to 160 substantially expands verified reachability, reduces zero-reachability, increases verified-mode entropy, and improves smoothed VPE. At 160 tokens, Qwen2.5-1.5B realizes the strongest mirror horizon among the tested models, even though Qwen2.5-3B has more parameters. This shows that mirror horizon is not parameter count, but accessible verified continuation capacity under a bounded reflection protocol. The result supports Mirror Theory as a measure-level account: capability is the structure of viable continuations made reachable, not merely one-shot accuracy or pass@k. --- ### Qubit-Efficient Quantum Search for Hyperdimensional Decomposition via Logarithmic Encoding Authors: Sanggeon Yun, Hyunwoo Oh, Ryozo Masukawa, Raheeb Hassan, Mohsen Imani Published: 2026-07-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.11936v1 Hyperdimensional Computing (HDC) represents symbols using high-dimensional hypervectors of dimension $D$. In hypervector decomposition, the objective is to recover $F$ constituent hypervectors, each drawn from a codebook of size $N$, from a bound target hypervector. This requires searching over $N^F$ candidate tuples, making the task computationally prohibitive at scale. Recent quantum approach provides a quadratic search advantage, but typically rely on qubit-inefficient $O(D)$-qubit hypervector representations. We propose a qubit-efficient quantum framework for HDC decomposition that reduces the representation cost to $O(\log D)$. The framework introduces logarithmic hypervector and binding encodings, together with a reversible hypervector lookup operator for circuit-level manipulation of dense hypervectors. Combined with a modified Dürr-Høyer search procedure, the method preserves $O(\sqrt{N^F})$ search complexity while substantially reducing qubit usage. Experimental results validate correct similarity computation, accurate decomposition in executable regimes, and significantly improved qubit scaling over baselines based on explicit $D$-qubit hypervector encodings, achieving up to $2{,}000\times$ fewer qubits. --- ### Transforming LLMs into Efficient Cross-Encoders via Knowledge Distillation for RAG Reranking Authors: Shreeya Dasa Lakshminath, Shubhan S Published: 2026-07-11 Categories: cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.11933v1 Cross-encoders achieve high reranking accuracy in Retrieval-Augmented Generation (RAG) pipelines but impose quadratic inference costs that limit real-time deployment. We address this by fine-tuning LLaMA 3 (8B) as a drop-in reranker using a two-stage pipeline: supervised fine-tuning on a custom query-document relevance dataset via the Unsloth framework with LoRA adapters, followed by 4-bit quantization for efficient inference. The resulting model replaces the cross-encoder in a dual-retriever RAG pipeline combining BM25 and dense vector search. Evaluated on a domain-specific question-answering benchmark using the RAGAS framework, our fine-tuned LLaMA 3 reranker achieves gains of 14% in answer relevancy, 16% in context precision, 19% in answer similarity, and 21% in answer correctness over the cross-encoder baseline, while reducing inference overhead through 4-bit quantization. These results demonstrate that instruction-tuned LLMs can be adapted into accurate, efficient rerankers without the quadratic complexity of traditional cross-encoders. --- ### Confining Nondeterminism: AI-Driven Research Systems as DBMSs for Reliable, Non-Wasteful, Transparent, and Collaborative Research (Vision) Authors: Kyoungmin Kim, Anastasia Ailamaki Published: 2026-07-11 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2607.10508v1 LLM agents that conduct research (proposing ideas, writing and running code, analyzing results) can already carry a study from research question to figures, yet cannot be fully trusted. The same question asked twice in a row returns different answers; the agent announces a number that no execution produced, and tool use does not prevent this, because nothing binds what the agent reports to what its tools returned; a small upstream change leaves downstream results silently stale, with no way to list which ones; and the agent re-runs preprocessing and rewrites code it has already produced. We argue these failures share one root: every step of today's agent loop is a stochastic LLM call whose internal state nobody, including the agent, can check. Rather than trying to see inside the LLM, we take a lesson from databases, which earn trust without being watched, because deterministic operators over well-defined state make their guarantees hold by construction. We propose organizing a research project the same way. The project lives in a deterministic, versioned dataflow engine (in effect, a query plan over materialized views), and the LLM, together with the user, is a stochastic compiler that may only edit that plan. The executor never calls the LLM; LLM output enters only as versioned code and data that the executor then runs, and any asserted result enters the record only with an execution behind it. Five design rules at this boundary turn familiar database machinery, from versioning and provenance to incremental maintenance and cost-based scheduling, into guarantees that make research reliable, non-wasteful, transparent, and collaborative. This report presents the diagnosis, the requirements, and the design; the guarantee walkthrough, a prototype, and the research agenda appear in the full version, in preparation. The LLM, we argue, should be the query compiler, never the executor. --- ### Learning from Noise: Effective-Rank Collapse and Out-of-Distribution Rejection in Restricted Boltzmann Machines Authors: Oshada Rathnayake, Nikhil Shukla Published: 2026-07-11 Categories: cs.LG, cond-mat.dis-nn arXiv: https://arxiv.org/abs/2607.10506v1 Restricted Boltzmann machines (RBMs) represent data by shaping an energy landscape over visible and hidden configurations, but their discriminative use is fragile under out-of-distribution (OOD) inputs: samples outside the training distribution can be absorbed into one of the learned class basins rather than rejected. Here, we analyze this failure mode through the spectrum of the induced visible--visible interaction $J=WW^{T}$, where \(W\) is the visible--hidden weight matrix. Relative to a Marchenko--Pastur random-matrix reference, conventional training spreads spectral weight into many weak, bulk-compatible directions, increasing the effective rank of $J$. When auxiliary random binary images are assigned to a rejection label during training, the learned interaction undergoes effective-rank collapse: weak bulk-like modes are depleted, spectral weight concentrates into fewer dominant eigendirections, and the effective rank of $J$ approaches that of the empirical data covariance matrix. The resulting RBM rejects structured OOD image datasets while preserving MNIST classification accuracy, showing that random auxiliary exposure can reshape both the interaction spectrum and the free-energy landscape of an energy-based classifier. --- ### NanoVSR: Towards Real-Time Video Super-Resolution on Edge Devices Authors: Filip Pawlicki, Marcel Kańduła, Marcin Pucek, Kamil Dobies Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.10495v1 Recent Video Super-Resolution (VSR) methods rely heavily on transformers and explicit optical flow, creating computational overhead and custom operations that hinder deployment on hardware accelerators like TensorRT. To address this, we introduce NanoVSR, a scalable, fully convolutional architecture designed for resource-constrained edge devices. Using structural reparameterization, NanoVSR collapses into standard convolutions during inference, ensuring seamless hardware compatibility and negligible runtime overhead. Furthermore, despite lacking explicit motion compensation, it maintains competitive restoration quality by implicitly learning spatio-temporal alignments through progressive training. Evaluated on the REDS4 benchmark, NanoVSR demonstrates an exceptional balance between accuracy and computational efficiency, significantly improving the trade-off for compact architectures. Our NanoVSR-644k baseline yields 28.64 dB PSNR while delivering 27.2 FPS on the NVIDIA Jetson Orin NX 16GB (25W), offering massive speed gains over heavier models. The scaled NanoVSR-1.7M variant reaches 29.15 dB with a throughput of 19.58 FPS, providing superior, edge-optimized upscaling. Code is available at https://github.com/filippawlicki/nanovsr. --- ### EvidentialRAG: Quantifying and Mitigating Information Conflict in Multi-Source Retrieval-Augmented Generation via Evidential Deep Learning Authors: S M Asif Hossain, Ruksat Khan Shayoni, M. F. Mridha Published: 2026-07-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.10491v1 Retrieval-augmented generation grounds large language models in external evidence, but most pipelines still treat retrieved passages as deterministic and mutually consistent context. In open information environments, retrieved sources may disagree because of temporal drift, source error, ambiguity, or genuine uncertainty. This paper introduces ERAG, an uncertainty-aware RAG framework that converts retrieved chunks into probabilistic evidence before generation. A lightweight evaluator extracts candidate claims and maps chunk-level support to Dirichlet evidence. A conflict-preserving Dempster-Shafer fusion rule then transfers unresolved disagreement into epistemic uncertainty rather than normalizing it away. The generator is routed to direct answering, conflict-aware answering, or abstention according to the fused uncertainty score. Experiments on CRAG, ConflictQA, and MuSiQue show that ERAG remains competitive with the strongest matched baseline on standard question answering while improving behavior under conflict. On the CRAG ambiguous subset, hallucination decreases from 45.3% for Corrective RAG to a human-calibrated estimate of 34.8%, conflict resolution increases from 35.2% to 51.2%, and expected calibration error improves to 0.122. These results suggest that evidential modeling is a practical mechanism for trustworthy information processing in foundation-model-based retrieval systems. --- ### NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations Authors: Ruksat Khan Shayoni, Muhammad Faraz Shoaib, S M Asif Hossain, M. F. Mridha Published: 2026-07-11 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.10490v2 Tool-using large language model (LLM) agents are attractive for network operations, but tickets, alerts, logs, runbooks, and ChatOps messages can carry indirect prompt injections. We present NetInjectBench, a 130-scenario benchmark that separates untrusted artifact text, trusted policy metadata, and evaluation labels for network-operation tool use. The sample contains 40 benign, 40 weak-attack, 40 strong-attack, and 10 approved high-impact change scenarios; each is evaluated with Qwen2.5-7B, Llama3.1-8B, and Mistral-7B. Across 240 attack instances, naive execution reached an 82.50% unsafe tool-action rate. Prompt-only safety, Self-Reminder, Spotlighting, and a Two-Pass LLM Judge reduced this rate to 25.63%, 21.67%, 18.33%, and 10.00%, respectively. Static allowlisting reached 5.00% but blocked all approved changes, yielding 0.00% usefulness and 100.00% overblocking on approved cases. Under the stated metadata-integrity assumption, the metadata-aware policy gate produced 0/240 unsafe attack actions, with a 95% Wilson upper bound of 1.58%, while preserving 99.17% attack-scenario usefulness and 100.00% approved-change usefulness. The findings show that network-operation agents need execution-time authorization boundaries alongside prompt-level instruction hygiene. --- ### NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations Authors: Ruksat Khan Shayoni, Muhammad Faraz Shoaib, S M Asif Hossain, M. F. Mridha Published: 2026-07-11 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.10490v1 Tool-using large language model (LLM) agents are attractive for network operations, but tickets, alerts, logs, runbooks, and ChatOps messages can carry indirect prompt injections. We present NetInjectBench, a 130-scenario benchmark that separates untrusted artifact text, trusted policy metadata, and evaluation labels for network-operation tool use. The sample contains 40 benign, 40 weak-attack, 40 strong-attack, and 10 approved high-impact change scenarios; each is evaluated with Qwen2.5-7B, Llama3.1-8B, and Mistral-7B. Across 240 attack instances, naive execution reached an 82.50% unsafe tool-action rate. Prompt-only safety, Self-Reminder, Spotlighting, and a Two-Pass LLM Judge reduced this rate to 25.63%, 21.67%, 18.33%, and 10.00%, respectively. Static allowlisting reached 5.00% but blocked all approved changes, yielding 0.00% usefulness and 100.00% overblocking on approved cases. Under the stated metadata-integrity assumption, the metadata-aware policy gate produced 0/240 unsafe attack actions, with a 95% Wilson upper bound of 1.58%, while preserving 99.17% attack-scenario usefulness and 100.00% approved-change usefulness. The findings show that network-operation agents need execution-time authorization boundaries alongside prompt-level instruction hygiene. --- ### Grassmannian Splatting I: Moving rank-2 Spacetime Surfels for Dynamic Scene Rendering Authors: Aaron Maurice Berman, Shantanu Dave Published: 2026-07-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.10489v1 We introduce Grassmannian splatting, a dynamic scene representation whose primitives are Gaussians supported on 3-planes in spacetime $\R^4$: generically, spatial 2-planes in uniform translation along their normals. Each primitive carries a unit normal $n \in \mathbb S^3/\{\pm 1\} \cong \mathrm{Gr}(3,4)$ and an unconstrained factor $L \in \mathbb R^{4 \times 3}$, with covariance \( Σ_{4\mathrm{D}} = (P_n L)(P_n L)^T, \qquad P_n = I - n n^T. \) For generic $L$ and $n \neq \pm e_0$, conditioning on time returns a rank-2 surfel at every frame. The normal of the disk and its velocity along that normal are read off from $n$; the disk shape and the tangential drift of its center are set by $L$. Existing native 4D Gaussian splatting methods (\it{Yang et. al. 2023,Duan et. al. 2024}) slice full-rank spacetime covariances, so their per-frame primitive is a volumetric ellipsoid; since conditioning lowers rank by exactly one, a rank-2 surfel in the slice requires a rank-3 spacetime covariance, and the parameterization above realizes exactly these. The motion model is closed form, i.e. no deformation field is learned, and no custom CUDA is required: the conditioned disk feeds a standard 3DGS rasterizer through its precomputed-covariance interface. A soft clamp in the Schur denominator regularizes the static orientation and continuously bridges rank-3 static and rank-2 dynamic behavior, so static and moving primitives form a single continuous family. On the 17 HyperNeRF scenes of MonoDyGauBench, training is fastest among all compared methods (4.9 to 5.6 times faster than the strongest quality baselines), while ranking second in PSNR, MS-SSIM, and LPIPS. Code: https://github.com/PaulCelanCoding/grassmannian-splatting --- ### Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents Authors: Igor Santos-Grueiro Published: 2026-07-11 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.10487v1 LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a DOM snapshot, approval epoch, version witness, branch token, or worker result. We study the commit boundary at which earlier authority evidence no longer authorizes a durable effect. We call this property commit-time authorization: a durable effect is authorized only if the witness that licensed its derived state remains fresh, causally prior, bound to the same effect, and eligible at commit time. We build a controlled-invalidation suite spanning browser, tool/API, and multi-agent workflows. The suite preserves the user goal and payload shape while invalidating the authority relation before durability. In the primary 54-task matrix, endpoint success remains high: 262/270 runs reach the visible result. Only 55/270 are authorized completions; among the 216 invalidating rows, 207 commit after the authorizing path has failed. All 54 clean controls remain authorized, and a separate 54-run authority-preserving check produces no unauthorized commits. We then evaluate mitigation families. Prompt caution and single-condition checks are insufficient because different hazards break different boundary conditions. Defenses work when they refresh, rebind, replan, or refuse at the durability boundary. CommitGuard, a fail-closed boundary monitor, blocks stale durable-effect attempts on protected commit surfaces when runtimes emit witness, dependency, binding, and eligibility signals. The result is a reporting and runtime-design lesson: endpoint success is a utility metric; authorized commit is a security property. --- ### ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Authors: Kexin Huang, Junkang Wu, Jinda Lu, Shuo Yang, Chiyu Ma, Jiancan Wu, Xiang Wang, Xiangnan He, Guoyin Wang, Jingren Zhou Published: 2026-07-11 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.10481v2 Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), yet the training process remains notoriously fragile. In this work, we investigate a critical source of this instability: over-optimization, where models exploit training heuristics at the expense of generalizable reasoning. While reverse KL regularization is the standard defense against such degradation, our analysis reveals that it is often insufficient in this regime, as it fails to ensure comprehensive coverage of the reference distribution. To address this, we propose ARMOR (Anchor Rollout and Mixed Optimization for RL), a framework that shifts the paradigm from passive penalty to active sample stabilization. ARMOR comprises two key components: (1) Anchor Rollout, which leverages off-policy data from the reference policy to preserve established solution patterns; and (2) Mixed Optimization, which reformulates the policy objective to enable controlled exploration without relying on auxiliary losses. Extensive experiments on reasoning benchmarks validate that ARMOR effectively mitigates validation collapse, enabling sustained performance improvements over extended training horizons. --- ### When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation Authors: Lekang Jiang, Wenjun Sun, Stephan Goetz Published: 2026-07-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.10480v1 Patent claim drafting is a challenging legal drafting task that requires technical expertise, precise linguistic control, strict adherence to formal conventions, and the preservation of complex logical relationships among claim elements. While Chain-of-Thought (CoT) prompting has been widely used to improve the reasoning capabilities of large language models (LLMs), recent evidence suggests that its benefits may be limited, or even negative, in highly structured or pattern-sensitive tasks. Therefore, this paper investigates whether CoT prompting benefits patent claim generation. We propose a task-specific CoT method for patent claim generation and evaluate its effectiveness through both automatic metrics and human expert assessment. Our results show that reasoning-enhanced prompting can improve claim quality. Moreover, we demonstrate a counter-intuitive but important empirical finding: implicit CoT, where reasoning is kept internal rather than explicitly verbalized, consistently outperforms explicit CoT. Through systematic analysis, we show that explicit CoT can introduce an unnecessary information bottleneck for claim generation. Verbalized reasoning may compromise the quality of final outputs through three specific mechanisms: abstraction of critical details, disruption of internalized generation patterns, and cascading error propagation. Our findings provide new insights into legal tasks and CoT applications. --- ### Differentiable Proxy Learning for Adaptive Quantization Control in H.264 Video Coding Authors: Qihan Xu, Ivan V. Bajić Published: 2026-07-11 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2607.10478v1 H.264 has been the most widely used video coding format for the past two decades due to its relative simplicity, efficiency, and wide availability of software and hardware implementations. However, optimizing codec parameters such as the quantization parameter (QP) for specific objectives (e.g., perceptual quality or machine vision tasks) is challenging due to the non-differentiable nature of standard video codecs. While differentiable proxies have recently been used to enable gradient-based optimization around standard codecs, their fidelity to the target codec is rarely explicitly characterized. In this paper, we propose a differentiable proxy learning method for H.264 intra codec to enable adaptive quantization control. Built upon a variable-rate learned compression model, the proposed proxy is made differentiable with respect to codec QP through a soft-indexing mechanism. It is then trained to approximate the rate-distortion behavior of H.264 under two quantization settings: global-QP, which uses one QP per image, and spatial-QP, which assigns QPs at the macroblock level. Using the frozen trained proxy, we develop a proxy-based adaptive quantization (AQ) framework for both perceptual optimization and machine vision tasks. Experimental results demonstrate that the proposed proxies closely approximate the rate-distortion behavior of H.264 intra codec. The resulting proxy-based AQ framework consistently improves rate-task trade-offs over fixed-QP H.264 baselines, achieving BD-rate reduction of up to 17.12% for semantic segmentation and 15.30% for MS-SSIM. --- ### Fast Data-Driven Modeling of Hydraulic Clutch Control Pressure with Latch-State Classification and Gaussian Process Regression Authors: Yash Bagla, Jason Schneider Published: 2026-07-11 Categories: eess.SY, cs.LG, math.OC arXiv: https://arxiv.org/abs/2607.10477v1 This paper presents a data-driven method for modeling the pressure response of a hydraulic clutch control circuit. The system consists of a variable-force solenoid, accumulator, pressure regulator valve, and latch valve, and exhibits nonlinear behavior caused by hysteresis, latch transitions, and actuator dynamics. A baseline model using commanded current variables captured the general pressure response but failed to represent hysteresis and latch behavior accurately. The input vector was therefore extended with current derivative information, and several classifiers were tested to separate latch-related operating regimes before fitting Gaussian Process regression models to the resulting partitions. Nonlinear SVC and gradient boosting produced the highest latch-classification accuracy, and nonlinear SVC was selected for the final local-regression pipeline. The proposed approach was evaluated on unseen ramp-rate data and compared against a physics-based Amesim model. The machine-learning model reproduced the measured pressure response and hysteresis behavior more accurately than the physics-based simulation for the tested operating conditions. These results suggest that machine-learning plant models can complement physics-based hydraulic models during hardware development and controller calibration when representative test-stand data are available. --- ### Hallucination Detection in Large Language Models Using Diversion Decoding Authors: Basel Abdeen, S M Tahmid Siddiqui, Meah Tahmeed Ahmed, Anoop Singhal, Latifur Khan, Punya Parag Modi, Ehab Al-Shaer Published: 2026-07-11 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.10476v2 Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions. Despite their advanced text generation capabilities, LLMs exhibit hallucination tendencies, where they generate factually incorrect statements and fabricate knowledge, undermining their reliability and trustworthiness. Multiple studies have explored methods to evaluate LLM uncertainty and detect hallucinations. However, existing approaches are often probabilistic and computationally expensive, limiting their practical applicability. In this paper, we introduce diversion decoding, a novel method for developing an LLM uncertainty heuristic by actively challenging model-generated responses during the decoding phase. Through diversion decoding, we extract features that capture the LLM's resistance to produce alternative answers and utilize these features to train a machine-learning model to develop a heuristic measure of the LLM's uncertainty. Our experimental results demonstrate that diversion decoding outperforms existing methods with significantly lower computational complexity, making it an efficient and robust solution for evaluating hallucination detection. --- ### Hallucination Detection in Large Language Models Using Diversion Decoding Authors: Basel Abdeen, S M Tahmid Siddiqui, Meah Tahmeed Ahmed, Anoop Singhal, Latifur Khan, Punya Parag Modi, Ehab Al-Shaer Published: 2026-07-11 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.10476v1 Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions. Despite their advanced text generation capabilities, LLMs exhibit hallucination tendencies, where they generate factually incorrect statements and fabricate knowledge, undermining their reliability and trustworthiness. Multiple studies have explored methods to evaluate LLM uncertainty and detect hallucinations. However, existing approaches are often probabilistic and computationally expensive, limiting their practical applicability. In this paper, we introduce diversion decoding, a novel method for developing an LLM uncertainty heuristic by actively challenging model-generated responses during the decoding phase. Through diversion decoding, we extract features that capture the LLM's resistance to produce alternative answers and utilize these features to train a machine-learning model to develop a heuristic measure of the LLM's uncertainty. Our experimental results demonstrate that diversion decoding outperforms existing methods with significantly lower computational complexity, making it an efficient and robust solution for evaluating hallucination detection. --- ### Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards Authors: Pengfei Cai, Utkarsh Utkarsh, Alan Edelman, Christopher Vincent Rackauckas, Rafael Gomez-Bombarelli Published: 2026-07-11 Categories: cs.LG, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2607.10474v1 Partial differential equations (PDEs) are foundational to modeling in science and engineering, but constructing reliable numerical solvers remains labor-intensive, demanding expert knowledge of discretization schemes, stability conditions, and boundary treatments. Recent work has begun to frame PDE solving as a code-generation task for large language models (LLMs), yet existing approaches operate primarily at inference time: relying on prompting, debugging, self-refinement, and test-time scaling rather than adapting the model itself. In parallel, reinforcement learning with verifiable rewards has emerged as a post-training paradigm for code and math reasoning, but its verifiers are typically binary: a compiler runs, or a test passes. Such signals discard the graded structure of scientific correctness, where two solvers may both execute and yet differ in solution accuracy by orders of magnitude. In this work, we introduce RLVP: Reinforcement Learning with Verifiable Physics, an RL post-training framework for multi-PDE solver code generation. RLVP addresses this verifiability gap with a hybrid verifier: hard program-validity checks ensure executability, while continuous physics rewards score function-space accuracy and PDE-residual consistency. A single policy is post-trained across diverse PDE families spanning hyperbolic, parabolic, elliptic, and incompressible-flow systems. RLVP improves over both pre-trained and supervised-only baselines on PDE benchmarks, and shows zero-shot improvement transfer to held-out PDEs. We show that a smaller LLM post-trained with RLVP can outperform prompting a frontier model on in-distribution PDE solver generation. The trained policy shows evidence of compositionality in numerical motifs: it recombines stencils, time-stepping schemes, and boundary-handling primitives learned from the PDEs used in training into generated solvers for unseen PDE problems. --- ### On the Real-World Generalisability of Optical Flow Models Authors: Petter Reijalt, Sander Gielisse, Rickard Karlsson, Jan van Gemert Published: 2026-07-11 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2607.10470v1 Real-world deployment of vision models to broadly benefit society is arguably a main research objective. In optical flow, however, the difficulty to obtain the ground truth has focused research mainly on synthetic data and domain-specific benchmarks. Here, we investigate the severity of this mismatch. We study how well modern optical flow estimation models generalise to real-world video and question if accuracy on synthetic benchmark proxies actually predicts accuracy on real-world optical flow. To address this, we build a real-world evaluation benchmark and evaluate the real-world generalisability of a broad set of recent optical flow models using standard checkpoints. Our benchmark contains 8,204 frame pairs across TAP-Flow, Slow Flow, and our own dataset FlowFactor. FlowFactor is a manually annotated real-world benchmark of 1,000 HD frame pairs organised into four confounding factors: large displacements, repetitive textures, occlusions, and lighting variation. Each setting mainly varies only one factor, enabling diagnostic, confounder-specific analysis. Using FlowFactor, we reveal that performance on varying lighting and large displacements correlates most strongly with real-world accuracy, and that improvements on large-motion regimes can trade off against robustness in small-motion, stationary scenes. Our experiments show that progress on Sintel, KITTI and Spring only weakly predicts accuracy on real-world data, highlighting the need for a broad real-world optical flow benchmark. Interestingly, scaling up the amount of training data does not necessarily resolve the gap, calling for new innovative research instead of simply scaling data and compute. --- ### Toward Production-Ready Federated Learning in Healthcare: Privacy, Orchestration, and Governance in MLOps Authors: Sakshi Gorkhali, Jonesh Shrestha Published: 2026-07-11 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2607.10467v2 Healthcare organizations often cannot freely centralize patient data because medical records are sensitive, regulated, and institutionally controlled. Federated learning offers a practical alternative by allowing hospitals and clinics to train a shared model while keeping raw data local. However, federated learning is not automatically production-ready or private by default. Model updates can still leak information, and decentralized training introduces operational challenges in deployment, monitoring, rollback, debugging, and governance. This paper examines how MLOps practices and the emerging idea of Federated Learning Operations (FLOps) can make federated healthcare machine learning systems scalable, reliable, and trustworthy. It answers three research questions: how containerization and orchestration support federated deployment, how privacy-preserving mechanisms affect trade-offs among privacy, utility, scalability, and operational complexity, and which post-deployment practices are most important for long-term governance. The central argument is that federated healthcare ML requires more than privacy-preserving algorithms. It needs an integrated MLOps architecture that combines reproducible deployment, secure orchestration, model versioning, audit logging, drift monitoring, heterogeneity management, and clear governance. --- ### Pitfalls of Administrative Censoring in Survival Models with Time-Indexed Inputs Authors: Yanqi Xu, Hui Dai, Carlos Fernandez-Granda, Krzysztof J. Geras, Yiqiu Shen Published: 2026-07-11 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2607.10466v1 Survival models can model time-to-event outcomes using partially observed data. They are widely used in clinical prediction, including cancer risk, disease progression, treatment response, and mortality. Recent models often rely on rich inputs collected at a specific clinical encounter, such as medical images, laboratory tests, electronic health record snapshots, or sensor measurements. In large retrospective datasets, these inputs are usually collected over many calendar years. As a result, they may contain clues about when they were acquired through changes in devices, protocols, documentation, patient mix, or clinical practice. This creates a potential failure mode when outcomes are observed only up to a fixed study end date. More recent records necessarily have less potential follow-up than older records. A model that can infer the record date from the input may therefore learn to predict how much follow-up was available rather than the patient's true risk of experiencing the event. We call this failure mode administrative-cutoff leakage. In this paper, we characterize when this leakage can occur, distinguish it from classical informative censoring and genuine temporal changes in risk, and propose practical ways to detect it. In simulations, we show that administrative-cutoff leakage can inflate fixed-horizon AUC and can also affect Harrell's C-index under realistic follow-up patterns. We then demonstrate the same behavior in a real mammography cohort. These results motivate a simple design principle for survival prediction: for an n-year prediction task, the dataset should provide at least n years of potential follow-up after the latest input date. Otherwise, the models may be subject to bias induced by administrative-cutoff leakage. ---