Retrieval Recall

Geographic applications need every object inside a radius that satisfies a semantic threshold, yet embedding indexes return approximate top-ranked lists and may omit qualifying records silently. We present FRESH-GEORANGE, a semantic- spatial range design that separates source-watermark freshness from optional record age. Geographic cells and semantic mi- croblocks provide admissible pruning bounds; a graph proposes verification order but supplies no correctness evidence. Exact mode scans every nonprunable block and the delta overlay. Certified mode may stop early and reports a deterministic query- specific recall lower bound from verified answers and unresolved records. A reproducible CPU pilot uses 2,500 real OpenFlights airport records, a 2,000-record base, and 740 simulated insert, delete, and text-revision events; it evaluates 180 unique queries over five seeds. Exact mode achieved 100.00% set recall on every query. The 95-percent mode achieved 99.91% empirical mean recall with a 99.41% reported mean certificate and no observed bound violation. However, its 7.24 ms median latency was 5.85 times the 1.24 ms spatial-first exact baseline, and full-history delta replay became slower than rebuilding at larger batches. The prototype therefore validates the completeness mechanism, not performance superiority or production freshness. Submission- scale evaluation requires real map diffs, official recent baselines, and truly incremental versioned maintenance.

Modern LLMs and AI agents increasingly support data engineering workflows that integrate evidence from unstructured sources. Such pipelines typically do data retrieval, integration, and ranking before proceeding to more complex agentic reasoning or actions, e.g., for scientific discovery. The core retrieval problem in these workflows jointly executes multi-attribute filtering, multi-vector search, exact relational joins, and thresholded embedding-similarity joins. Given a planned query and monotone scoring function, our DASE query engine constructs and ranks candidate evidence tuples. It comprises (i) a multi-step reasoning query model over structured predicates, multiple vectors, and relational links; (ii) SemJI, a sparse materialized embedding-similarity join index for rare near-neighbor pairs; and (iii) a co-designed execution layer that combines predicate-aware ANN traversal, batched access, and threshold-based score aggregation. On scientific-discovery workloads, DASE retrieves candidate evidence for multi-step reasoning queries 6x to 46x faster than strong RDBMS, rerank, and vector-database baselines at comparable recall; and for tasks that require semantic-operator post-processing, DASE acts as a high-recall prefilter that makes downstream LLM evaluation both cheaper and more accurate -- e.g., on SemBench E-Commerce it improves BigQuery quality from 0.67 to 0.80 while cutting cost from $2.42 to$0.54.

Many operational cases are documented more than once, at different workflow stages and for different purposes, yet model evaluations normally select one of these records before model comparison begins. We treat that selection as part of the evaluation and compare matched records of the same cases under fixed labels and splits in three systems: GE Aerospace repair events, NASA ASRS safety reports and NHTSA vehicle recalls. Across the three GE fields, for events whose label comes from parts transactions independently of the narratives, held-out macro-F1 ranged from 0.33 to 0.91. A difference of 0.46 separated the customer report, written before shop work, from the technician report, written after diagnosis but before the transaction that generates the label. That difference is substantially larger than the representation and architecture differences tested on the same events. The public systems showed different patterns: the NHTSA defect summary remained strongest under every model family tested, whereas the ASRS analyst synopsis outperformed the reporter narrative under learned sequence models but not under lexical baselines. Secondary analyses showed that some model comparisons were also record-dependent. Evaluations should be run on the information available at the intended decision point and should report how both the record and the label were produced.

Long-term language-model agents rely on external memory across interactions. Atomic memories are particularly useful: their fine-grained semantic boundaries enable precise retrieval and direct comparison between observations. Yet accumulating atoms inevitably become redundant, overlapping, or conflicting. Existing methods often ask an LLM manager to add, update, delete, or rewrite memories directly, coupling semantic interpretation, storage decisions, and content generation in one error-prone operation. We introduce ROAM, a relation-guided framework that uses atomicity for management while allowing richer answer-time representations. ROAM classifies incoming--stored atom pairs as independent, equivalent, directionally subsuming, or conflicting, then organizes observations into active Primary and supporting Evidence roles. Fusion subsequently combines complementary details and temporal changes into compact, potentially non-atomic views. Only Primary views are retrieved for answering, preventing redundant or outdated atoms from competing independently. Across models and evaluation settings, ROAM improves answer accuracy by up to 29.8 percentage points. Ablations show complementary benefits from different relations and consistent gains from fusion beyond role organization. Mechanism analysis further finds 15.6-point higher answer-critical source recall and an 11.5-point lower confounder-token share. ROAM remains robust across manager scales.

Enterprises managing large X.509 certificate inventories face a prioritization problem: deterministic analysis tools that precisely identify standards violations are indispensable for remediation, but applying them exhaustively across millions of certificates is operationally impractical. We present X-amine509, a two-stage triage system that uses machine learning to rapidly rank certificates by predicted risk and route only the highest-risk items to full deterministic analysis. Certificate risk is quantified as a composite score derived from 177 defect checks grounded in CA/Browser Forum Baseline Requirements, NIST IR 8547/SP 800-57, and cryptographic strength criteria, weighted by security severity across four tiers ranging from cryptographic breaks to minor compliance deviations. We collected 1,027,714 X.509 certificates from Fortune 500, .gov, and .edu domains and scored each using this rubric. On a held-out test set of 201,976 certificates, our best model (Extra Trees) achieves $R^2$ of 0.993 with MAE of 2.26, while Decision Tree scores $R^2$ of 0.986 at 3.7 million certificates per second on a single machine. Ranking quality confirms the triage value: aggregate NDCG exceeds 0.997, and severity-tier classification reports 99.76% accuracy with 98.90% recall on critical-tier defects. Thirteen months later, we retrieved another 571,374 certificates to test our models' durability over time, and the Extra Trees and Decision Tree models maintain MAE below 6.8, $R^2$ of at least 0.915, aggregate NDCG above 0.988, severity-tier accuracy of at least 99.52%, and critical-tier recall of at least 97.03%. Feature importance analysis identifies validity period, Extended Key Usage configuration, negative serial number encoding, and self-signed status as the strongest risk predictors, providing coarse interpretability at the triage stage.

Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interactions. Conventional retrieval mechanisms optimize semantic compatibility rather than downstream utility, frequently introducing outdated, misleading, or conflicting evidence into the active context. We present MeClear, a task conditioned memory clearance framework that identifies memories featuring negative downstream utility through cooperative attribution and selectively suppresses them from agent execution. MeClear combines Leave One Out screening with sampled cooperative Shapley attribution to distribute utility across interacting evidence, effectively resolving redundant conflict masking where single removal evaluations fail. Utilizing attribution rankings, MeClear executes a query scoped minimal clearance strategy over a nested filtration, verifying task recovery on the cleared context without permanently altering the persistent memory bank. Comprehensive experimental evaluations across ten long dialogue memory pools demonstrate that MeClear achieves a target recall of 85.9% and an overall task recovery rate of 82.3%, representing a 25.5 percentage point improvement over Leave One Out (LOO) baselines.

Dense semantic segmentation allocates computational resources uniformly across the entire image, regardless of scene complexity or task relevance. Inspired by biological vision, we investigate whether semantic understanding can be achieved more efficiently through digital foveated perception. We introduce a lightweight active-vision pipeline that combines saliency-driven fixation selection, high-resolution foveal observations, low-resolution contextual information, semantic accumulation, and adaptive computation. Beyond conventional dense prediction metrics, we use object-level evaluation to measure semantic understanding under sparse observations. On ADE20K-Object, a single foveated observation achieves 95.9% of the baseline Top-1 accuracy and 96.9% of the baseline Top-3 accuracy while requiring only 4.7% of the computational cost. At the scene level, semantic accumulation recovers 90.6% of the baseline object recall while using 58.6% of the computation. These results suggest that substantial semantic understanding can emerge from sparse observations when computation is allocated selectively, highlighting active vision as an efficient alternative to uniform dense processing and motivating evaluation protocols beyond conventional pixel-wise segmentation metrics.

Retrieval Augmented Generation (RAG) is a key component for generating accurate and hallucination free answers using Large Language Models (LLMs). LLMs are improving at handling long context, but still suffer from "lost in the middle" problem. Thus, precise and accurate retrieval is important. Current retrievers chunk long context into length-based manageable chunks - in the process throwing away rich and informative semantic global structure in the corpus. We introduce a novel retrieval system STAIR that empowers an LLM to exploit global structure in a corpus such as a Table of Contents (ToC) to efficiently store and retrieve information from its model parameters. Our thorough and careful ablation studies with a finetuned Differentiable Search Index (DSI) system show that ToC helps build a low hallucination (less than 0.05%) generative Information Retrieval (IR) system and can generalize to examples where very few training samples are available. To further research in this novel direction of ToC based retrieval we release SearchTome - a diverse benchmark created from 18 books across 6 diverse domains to further research in this novel direction. STAIR achieves a high Recall@1 score of 82.6% on SearchTome as compared to DSI (76.9%), where the difference is found to be statistically significant. STAIR easily beats other strong baselines such as BM25 (59.5%), DPR (68.7%) and out-of-the-box Mistral (13.8%).

Large language models (LLMs) are increas- ingly deployed as long-horizon conversational agents, motivating growing interest in mem- ory systems. However, existing benchmarks primarily evaluate memory through QA-style probing rather than in-situ conversational usage. We introduce LOCOMO-CONV, a conversa- tional memory benchmark derived from Lo- CoMo with four query styles: dialog, implicit, counterfactual, and composed. Across five rep- resentative memory systems, we evaluate both retrieval recall and end-to-end response qual- ity. Our experiments show that conversational framing exposes substantial retrieval gaps over- looked by QA benchmarks, especially on im- plicit and composed queries, which multi-facet query rewriting narrows for raw-turn mem- ory but not abstractive memory. We further find that strong retrieval does not fully trans- late into response quality, and that implicit queries exhibit silent grounding, where mem- ory improves contextual grounding without ex- plicitly surfacing the gold fact. These results point to reasoning-based memory elaboration as a promising direction, and we release aux- iliary supportive_memory annotations captur- ing conversationally useful context beyond the original gold evidence.

Tamil spell and grammar correction is challenging because Tamil is an agglutinative low-resource language with rich verbal morphology, complex sandhi (phonetic transformation) rules at word boundaries, and a script of 247 distinct letters. Prior work targets word-level surface errors with rule-based methods, statistical n-gram models, Minimum Edit Distance, or hybrid pipelines with a transformer re-ranker; such methods cannot reliably handle contextual errors - subject-verb agreement, tense consistency, or cross-word sandhi - which require sentence-level understanding. We propose an end-to-end sequence-to-sequence formulation and fine-tune mT5-small and mBART-50 on a synthetic corpus of up to 657,720 noisy-clean Tamil sentence pairs spanning ten error categories. Both backbones follow the same four-stage progressive schedule, each stage targeting one weakness: surface noise (v2), contextual grammar (v3), single-site sandhi (v4), and multi-site cross-word sandhi (v5). On a 1,000-sentence balanced diagnostic set verified disjoint from all training data, our best model, mBART-50 v5, reaches 69.3% top-1 exact-match accuracy, with 87.5% on sandhi and 43.5% on subject-verb agreement. The schedule is what produces these gains: subject-verb accuracy rises from 1.0% to 52.5% once contextual pairs are introduced, and sandhi from 0% to 87.5% once multi-site sandhi pairs are. We additionally quantify a precision-recall trade-off this literature has not reported: sandhi recall is paid for monotonically in identity accuracy. Finally, Tamil-LLaMA-7B-Instruct reaches 19.0% zero-shot and 24.7% with three demonstrations against a 20.0% copy baseline, showing that a Tamil-adapted instruction model does not transfer to specialised sentence-level correction without task-specific supervision.

Reliable attractor recall conventionally requires broad basins of attraction. However, in reservoir-computing based associative memory, temporal cues reliably recover dynamical memories despite basins dominated by unpredictable, riddled-like regions. We reveal that memory basins exhibit an octopus-like'' structure: a robust head'' near the attractor and thin, intertwined ``tentacles'' spanning state space. Initial states in tentacular regions yield near-zero uncertainty exponents, making the recalled memory effectively unpredictable at finite precision. Yet, cue-driven generalized synchronization bypasses this unpredictability, driving the system into the robust basin head. This mechanism yields a quantitative relation linking minimum cue duration, synchronization rate, and basin-head radius. Trained recurrent neural networks exhibit similar geometry, suggesting this phenomenon extends beyond reservoir computing.

Promptable segmentation foundation models such as SAM3 accept an open-vocabulary text concept and return every instance matching it, but adapting them to a specialized domain by full fine-tuning is computationally prohibitive for the organizations that would benefit most. This study applies Low-Rank Adaptation (LoRA) to SAM3 for multi-class structural defect segmentation and examines both how such a model can be supervised from conventional annotation and whether the resulting efficiency gain transfers across datasets. Two contributions are methodological. First, we describe a supervision procedure that trains a concept-promptable model directly from COCO-style class-labeled instance segmentation by using the category name itself as the prompt, requiring no prompt templates, no synonym expansion, and no learned class embeddings. Second, we identify and mitigate a failure mode specific to this setting: because a conventional annotation file yields positive prompts exclusively, the model's presence prediction decouples from the text condition and degenerates into responding to any prompt, a collapse that is invisible to every metric computed on positive prompts alone. Exhaustive hard-negative prompting, in which every dataset category absent from an image is issued as a zero-detection query, addresses this at no annotation cost. Two adapter placements were compared under an identical protocol, updating 0.121% and 1.341% of model parameters. On a purpose-built tunnel lining dataset, pixel intersection-over-union improved from 0.017 to 0.338 and instance-level recall from 0.375 to 0.672; on the independent public Structural Defects Dataset, from 0.017 to 0.855 and from 0.574 to 1.000. Improvements were directionally consistent across ten metrics on both datasets, and the largest per-category gains occurred precisely where zero-shot competence was absent.

Credit-default prediction is an important task in financial decision making. Traditional methods use fitted classifiers such as logistic regression and random forests on tabular features. Large language models (LLMs) have recently been applied to this task through prompting. In this work we study how a fitted classifier and an LLM can be combined for credit-default prediction. We distinguish telling the LLM to imitate a classifier from using the classifier to build the prompt. We hypothesize that a fitted classifier can supply the ranking ability that an LLM prompt lacks. We experiment on the Default of Credit Card Clients dataset, and report recall, F1, and the area under the ROC and precision-recall curves, with bootstrap confidence intervals. We observe that a few-shot LLM has the highest recall (0.47) and F1 (0.50) of any single model but ranks worse than a random forest (AUC-ROC 0.72 against 0.79). Instructing the LLM to imitate a classifier gives no significant change. Pruning the prompt to the classifier's eight most important features raises recall by 0.071 and F1 by 0.032. Adding the classifier's predicted probability to the prompt raises the LLM's AUC-ROC from 0.72 to 0.78, matching the random forest, while keeping 0.118 higher recall than it. The reverse composition, and the use of several classifiers, do not help. We thus recommend a simple classifier-guided prompt for LLM-based credit prediction.

AI systems rewrite information constantly: conversations become stored memories, documents become answers. The rewrite can keep a claim while washing away what made it checkable, who said it, how sure they were, when it held. We call that failure factwashing, and release factwash, an open-source write-time gate that catches it deterministically, with named flags and evidence rather than an LLM judge. Building it answers a practical question: when does a cheap check suffice, and when do you need a model? What decides is whether the property has a bounded surface-cue inventory. Explicit negation cues are close to enumerable, so a word list finishes and transfers, reaching 0.91 F1 on untuned text. Hedging and attribution have open-ended realizations, so vocabulary plateaus near half recall, and a one-question LLM witness recovers +17 and +15 points of cue-detection recall at equal precision. Deployed, that witness may only lower a verdict, so it buys precision rather than coverage. We measure cue detection on 105,596 independently annotated sentences. A blind-labelled corpus of memory writes then locates the failure: 55% of bad writes in conversational hearsay, 7% in business email (p < 0.001), so the first deployment question is not which detector to use but whether the failure occurs at all. On unmodified mem0 2.0.7, the gate flags 5 of 8 hedged-hearsay writes.

Persistent agent memory must adapt as later outcomes change earlier evidence, yet mutable retrieval weights create an attribution problem: reviewers must distinguish authorized adaptation from database tampering. We present MutMem, an authorized-mutation protocol in HOM-AIMOS, a persistent agent-memory engine. MutMem retains memory content, records signed positive and negative outcome evidence without age-based expiry, and commits each nontrivial weight change as a housekeeper-authorized transition. Each transition binds a terminal provenance node, signer epoch, quantized old and new weights, a no-fork predecessor, and two domain-separated SHA-256 commitments. Ed25519 verification runs in both the database writer and a portable verifier. Content classified as poison-likely is retained with signed, revisable labels used by recall as trust evidence. We evaluate utility, mutation integrity, and poisoning adaptation. HOM-AIMOS answers 459/500 LongMemEval questions correctly under LLM judgment (91.8%). On LoCoMo, it obtains 74.12% judged accuracy and, under a separate upstream-compatible protocol, 58.20 token F1. A native suite passes all declared authorization, topology, tamper, signer-epoch, and post-mutation-recall cases; median signed-transition latency is 4.865 ms. In a declared N=100 PoisonedRAG adaptation, no injected poison appears in attacked top-5 disclosures (0/100; 95% Wilson upper bound 3.70%), while induced target-answer attack success among 98 clean-negative targets is 1/98 (1.02%). A preregistered four-arm ablation attributes the retrieval reduction to signed stored labels: the retriever selects poison for 94/100 targets when epistemic policy is bypassed and 0/100 when labels are restored. MutMem provides evidence of integrity, authorization, traceability, and historical continuity; it does not establish content truth.

Operational Earth observation increasingly calls for answering queries such as find the image pairs where a new building appeared.'' This means searching an archive of before-and-after (bi-temporal) satellite image pairs and ranking each pair by how well it matches a natural-language description of the change. The component that performs this match, the fusion module that combines the before'' and ``after'' views, must be run at query time across many candidate pairs, so its speed largely sets the cost of every search. We present a controlled comparison of how to build that module. Using one fixed image encoder (a frozen CLIP model) and one training recipe for all variants, we evaluate eight designs drawn from three families: attention, state-space models (Mamba), and learned compression (our Temporal Bottleneck Fusion, TBF). Each design is tested on two benchmarks (LEVIR-CC and Dubai-CC) with ten random seeds, so the reported differences are statistically grounded. We outline three findings: first, a training-free two-stage search (a cheap difference model that shortlists candidates, followed by attention fusion that re-ranks them) matches or exceeds full-fusion recall on LEVIR-CC while cutting query cost $10$-$15\times$, with comparable R@1/R@5 on Dubai-CC; second, the linear-time scan of Mamba, attractive on paper, gives no speed benefit at the patch counts typical of vision transformers ($L{=}196$): the scan is limited by memory bandwidth, whereas attention maps cleanly onto parallel hardware; and third, compressing the fused representation (TBF) reduces parameters by $2.3\times$ and latency by $1.6\times$ for a change-only BLEU-1 cost of $0.007$, although more aggressive compression quietly discards change-relevant detail that aggregate metrics fail to reveal.

Open medical language models have converged on a single scale: every widely used system runs at 7B parameters or more, leaving the sub-billion regime uncharacterized. We present MedLLM, an open 0.1B-parameter medical language model trained through a fully open three-phase pipeline: general pretraining with curriculum sequence-length scheduling, domain fine-tuning on MedFineWeb, a reference-guided medical corpus we release that is selected from general web data by embedding similarity to medical question-answering (QA) data, and preference-aligned fine-tuning combining SFT with direct preference optimization (DPO). Across medical benchmarks, MedLLM shows a pattern visible only at sub-billion scale: medical competence does not degrade uniformly under compression but splits by task type. On context-grounded QA it comes within $2.9$pp of a medically adapted 7B model and surpasses the instruction-tuned and general-purpose 7B baselines; on knowledge-recall QA it stays near the task floor on clinical-vignette MedQA yet significantly exceeds every 7B and sub-7B baseline on MedMCQA, indicating that where recall fails the constraint is model capacity rather than adaptation. This dissociation is masked at 7B, where both capabilities are present, and surfaces only when capacity is scarce.

In modern recommendation systems, retrieval serves as a primary stage responsible for filtering billions of candidate items down to thousands prior to refined ranking. To make this massive search effective and efficient, the system relies on ranking accuracy and indexing efficiency. However, these two objectives are traditionally misaligned: while the former optimizes for the alignment between ranking predictions and user behavior, the latter optimizes for a structural grouping of item representations which enables fast search among billions of candidates. Thus, despite extensive efforts to scale up interaction modeling for retrieval, they remain fundamentally limited by the structural misalignment between the ranking objectives and the proximity-learned index. In this work, we address this long-standing dichotomy by proposing a new holistic retrieval framework, OneShot. It is an end-to-end, in-model index learning framework that natively aligns index learning with ranking objectives. Using this joint learning as a structural foundation, OneShot pushes the boundaries of retrieval expressiveness by scaling interaction modeling with neural scoring beyond the persistent dot-product bottleneck. OneShot is fully deployed in Instagram's industrial short-video recommendation system, driving significant wins in user daily sessions, engagement, and time-spent. Additionally, OneShot achieves a $20\%$ recall gain at the operational ranking volume and a 10x efficiency improvement at an equivalent recall level.

We built and evaluated a self-serve entity resolution (ER) system on six benchmarks spanning 864 to 5M records, and three lessons emerged that are absent from existing ER literature. (1) No single matching algorithm wins everywhere - a self-serve pipeline cannot predict its next dataset, so we recommend training several algorithm families per dataset and letting an automatic bake-off pick the winner. (2) Precision and recall need separate fixes, not a shared threshold - precision needs hard rule-based vetoes, recall needs more diverse candidate retrieval. (3) One false-positive link can silently merge unrelated entities - assuming "A matches B" and "B matches C" implies "A matches C" lets a single bad link chain hundreds of records together, so every cross-group merge must be actively re-verified. We hope these lessons save practitioners the months of dead-end experiments that led us to them.

Long-term memory systems store what a user says in an external store and retrieve it when a related query arrives. This interface rests on an assumption so natural that it is rarely stated: a memory that is needed will resemble the query that needs it. World knowledge breaks the assumption. A tree-nut allergy should change the answer to a macaron request through their almond-flour ingredient, yet the two texts share no cue a retriever can see. We call this failure mode the implicit-association blind spot and introduce InMind, a 125-task, expert-verified benchmark spanning ten life domains, with 113 tasks grounded in citable public sources. Its paired controls separate three explanations that existing evaluations conflate: the fact was never stored, the model lacks the bridging knowledge, or the fact was stored and never surfaced. The verdict is clean. With the decisive memory placed in context, the backbone answers 84.0 percent of indirect queries; when the same memory must be retrieved, six vector, graph, and agentic memory systems reach at most 14.4 percent, even though they recall the same facts on demand at up to 100 percent. An embedding with eight times the dimensionality raises answer-blind target recall for every system yet leaves the gap essentially intact. A minimal diagnostic probe that keeps memory visible before the query arrives recovers most of the gap, locating the failure in the query-conditioned interface itself and pointing to routing, deciding which facts must stay visible, as the open problem InMind is built to score.

An initial high-recall stage in an empirical pipeline decides which items pass to later review, labelling, or modelling, and relevant items it misses are lost to every subsequent stage. We study how many audit labels are needed to certify, with finite-sample validity, that this missed relevant mass is small, and our main results characterise the label complexity of this problem. We first show that no procedure using only labels from inside the candidate set can certify any non-trivial bound on the missed mass: the audit must sample the excluded pool, the only region where unrecovered relevant items can lie. We then prove a matching finite-corpus lower bound. Any valid audit that certifies fewer than $m$ missed relevant items with high probability when none are present, even if adaptive and permitted to label the entire included pool, must inspect on the order of $N_0/m$ excluded-pool labels. Excluded-pool auditing is therefore minimax rate-optimal, not merely convenient, for missed-mass certification in the zero-miss regime. Building on this characterisation, we develop an exact finite-sample toolkit, using binomial and hypergeometric inversion rather than asymptotic approximation, that certifies missed mass, converts it to recall through a two-pool design, certifies pre-specified families of nested candidate generators simultaneously, and produces stress-test certificates against declared perturbation mechanisms. These certificates can be paired with observable review burden to select the least burdensome pre-specified candidate generator meeting a missed-mass target. Every guarantee holds under one discipline: the candidate generator, or the pre-specified family from which it is selected, and the audit rule are fixed before the certification labels are examined.

Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade. We report two controlled experiments crossing all three factors on one held, contamination-free synthetic corpus (the "Book of Veyra," 8,780 uniquely-named entities, deterministically regenerable from a fixed seed), evaluated across five models. Experiment 1 (960 calls/model) measures instruction-following decay as rule count N grows from 10 to 160, crossed with four formats and system-prompt vs. user-turn placement. Perfect-response rate collapses to zero by N=80 for every model, format, and placement. Placement produces effects at least as large as format at N=160 in most models, but the direction is model-specific. No model shows a reliable markdown advantage; one 35B model favors plain text instead. Experiment 2 (5,520 calls/model) measures recall accuracy, false-premise sycophancy, and absent-fact fabrication across a 2k-to-512k-token context ladder in the same four formats. Recall stays near ceiling through 64-128k tokens, then degrades sharply and format-dependently: one model's accuracy spread reaches 48 points at 128k tokens. Fabrication never occurs (0/5,760 probes), and sycophancy stays negligible (<=8.3%). What rises sharply near each model's context ceiling is outright refusal to answer (0% to 79-90%), distinct from sycophancy or fabrication. Neither pre-registered format ordering holds, and token overhead (+22% to +37% over plain text) further changes which format is preferable where accuracy spread is genuine. We release the full harness, corpus generator, and raw results (VeyraBench): https://github.com/iNetanel/veyrabench

Large language models leak parametric knowledge of what followed a historical date into decision tasks indexed by that date -- not necessarily a lookup of the realized outcome, but knowledge of the period all the same. Existence is settled; what users lack is a cheap way to audit a given model. We present HindsightBench, a black-box audit protocol that profiles parametric hindsight in any time-indexed LLM decision task at probe-level cost (no backtests, no logprobs, no corpus access). It chains a four-arm date-manipulation matrix (revealed/date-only/masked/transplanted), dual memory probes (date recovery; outcome recall), and six metrics -- trigger strength, transplant effect, post-cutoff placebo, recoverability, behaviorally effective cutoff, and recall-accuracy dissociation -- with explicit gates where identifiability is data-dependent. Applied to 15 models from seven vendors on a 258-node vintage-correct macro panel, it yields three patterns: (i) the date-trigger reflex is not a scale phenomenon -- it tracks training recency, though what installs it is not identified here: absent across every 2024 open-weight row where it is measurable, including a 70B tier with cutoff-aligned recall propensity, present in every tested 2026-generation model, and switching on within one vendor lineage (Qwen3 -> Qwen3.6) in the same MoE family at ~3B active; (ii) effective cutoffs span 22 months across vendors and precede vendor-reported dates by up to eight months, invalidating calendar-window placebos; (iii) results are not invariant to serving -- BF16 serving of an FP8-referenced model breaks the trigger estimate's stability while AWQ-INT4 preserves it, and a provider-locked reasoning regime makes one probe non-convergent -- so the protocol pins quantization and thinking regime as part of its contract. We release the panel, preregistrations, audit rows, transcripts, and one-command regeneration.

Retrieval-Augmented Generation (RAG) systems increasingly power enterprise LLM applications, yet the vector retrieval layer introduces two underexplored challenges: (1) trained codebook quantizers may expose corpus statistics during index construction, creating a leakage channel in multi-tenant deployments, and (2) post-hoc filtering for tenant isolation degrades recall on selective queries. We study TurboVec, an open-source vector index built on TurboQuant - a codebook-oblivious scalar quantizer requiring no corpus-dependent training. On the DBpedia OpenAI embeddings benchmark (d=1536, 100K-999K vectors), TurboQuant 4-bit outperforms trained FAISS Product Quantization at the same memory budget by 8.5-8.9 percentage points in Recall@5 across all scales. Compared to HNSW (R@5=0.991) and IVF-PQ (R@5=0.840), TurboQuant occupies a distinct design point: higher recall than IVF-PQ without training, at 4-8x less memory than HNSW. Deployed on Snowpark Container Services, TurboVec achieves 11ms median query latency at 100K vectors versus 707ms for warehouse brute-force scan. Kernel-level allowlist filtering maintains 0.86-0.93 Recall@10 across 10-1000 tenant workloads versus 0.09-0.19 for post-filter baselines. Codebook-oblivious design reduces membership inference accuracy to near-random (50.0%) versus 57.3% for PQ codebooks. Limitations include single dataset evaluation, uncompressed HNSW comparison, and privacy evaluation on synthetic data only.

Language models encode substantial factual knowledge in their parameters, which can lead to unreliable behavior when this knowledge is outdated, incomplete, or misaligned with the provided context. In this work, we study whether modifying the pretraining signal can systematically shift models away from parametric recall and toward evidence-grounded reasoning. We introduce Knowledge--''Less'' Language Models (KLLMs), a fundamentally different epistemic training paradigm for LLMs, which are pretrained on corpora in which named entities are anonymized, thereby removing a primary channel for entity-linked factual supervision. This intervention substantially reduces closed-book factual recall, while often improving performance on tasks where relevant information is provided as context. Across multiple model scales, KLLMs consistently outperform matched baselines on contextual question answering, fact verification, and hallucination detection benchmarks. Crucially, in retrieval-grounded settings with imperfect evidence, KLLMs show improved robustness and achieve up to 20--25% relative gains over standard language models. They further exhibit better calibration, with improved ECE, Brier score, and AUROC, as well as more reliable abstention behavior. Our results demonstrate that suppressing entity-linked supervision during pretraining induces a shift in epistemic behavior: KLLMs rely less on parametric knowledge and more on external evidence, leading to improved reliability under realistic conditions. This suggests that pretraining-time control over knowledge acquisition can complement retrieval-augmented and tool-based systems by providing a more evidence-sensitive base model.

On-device research agents search a corpus, read sources, and write a cited brief on a personal laptop. Whether their citations are faithful, and at what cost, is unmeasured for a deployable small model. This study fixes one 4B generator on a 24 GB laptop and asks what makes its citations faithful. It separates two quantities usually reported as one number. Cited claim faithfulness asks whether the cited source supports the claim. Trustworthy coverage asks whether the agent also cites the right sources. The study crosses how much of each source the generator sees, 400 against 1500 characters, with the quality of the sources supplied, gold papers against retrieved papers. Two levers fall out, and they act on different outcomes. Exposure sets faithfulness. More of each source lifts faithfulness from 0.45 to 0.58 on retrieved sources and from 0.37 to 0.58 on gold sources, and the two settings converge, so faithfulness is bound by exposure, not by whether the source is correct. The exposure lift is robust to a second, independent judge; the exact convergence is tight under the primary judge and only approximate under the second. Retrieval sets coverage. Trustworthy coverage stays near 0.22 on retrieved sources at any exposure, because recall is held near 0.40, so exposure cannot fix which sources are cited. The extra exposure costs about 235 output tokens. The practical recipe is to raise per source exposure first, cheaply, and then treat retrieval recall as the only remaining lever.

Foundation models such as CLIP have enabled open-vocabulary object detectors that generalise to novel categories via vision-language similarity. However, the confidence scores these detectors produce are not reliable localization probability estimates: they conflate visual scale and semantic query specificity with the true detection signal. Through controlled experiments on COCO across three foundation-model-based detectors (GroundingDINO, OWL-ViT, YOLO-World), with the scale-bias finding further replicated on LVIS (1,203 categories) using GroundingDINO, we show that s=cos(v,t) is a biased mixture of two effects. Scale bias (alpha = +0.064, r = 0.579, p = 1.29 x 10^-58) systematically inflates scores for large objects. Semantic bias (beta = -0.705, p = 5.23 x 10^-41) suppresses scores for generic queries. Both biases are structurally inevitable from CLIP's image-level pretraining. Threshold adjustment cannot remove them: oracle per-scale thresholding yields Delta F1 = +0.001 for small objects versus +0.102 for large. A parameter-free temperature scaling correction improves small-object Recall@10 by 19.6% (p < 0.01) without retraining. This comes at a modest, measurable cost to pooled-ranking precision, so the bias is partially, not freely, reversible at inference time. These findings reveal a fundamental limitation of adapting image-level foundation models to region-level detection tasks.

Financial anomaly detection suffers from extreme class imbalance, causing traditional single-objective algorithms to exhibit ``fraud collapse'', defaulting to the majority class and failing to balance anomaly interdiction with customer friction. To overcome this without distortive data resampling, we propose the Semantic Pareto-DQN, a multi-objective reinforcement learning framework. Our approach synthesizes heterogeneous transaction features into cohesive natural-language narratives, encoded by large language models, thereby producing a robust, scale-invariant state representation. The agent optimizes a vectorial reward that explicitly decouples financial efficacy, operational friction, and semantic discovery. By mapping the continuous Pareto frontier, the system dynamically navigates the asymmetric costs of missed anomalies versus false positives. Empirical evaluations across E-Commerce fraud and UCI Credit datasets show that semantic Pareto-DQN successfully shatters the zero-recall trap. It achieves superior minority-class recall compared to scalarized baselines, providing an alternative to trade bounded operational friction for financial anomaly discovery.

For fifty years, data systems have answered two questions. The relational model asked which records match a predicate; the vector model asked which vectors lie nearest a query. Neither was built for cue-driven, provenance-weighted recall across long sessions. We propose treating long-term agent memory as a distinct data model -- with its own write semantics (encoding, separation, consolidation, provenance) and read semantics (cue-driven activation across a linked memory graph) -- and present FluctlightDB, an embedded engine that implements this contract via experience() and activate(). We do not claim novelty over Mem0, Zep, or HippoRAG-style memory layers, only an embedded engine contract beneath them. Numbers are typed by metric; retrieval is not generation. On LoCoMo (official evidence-recall; 10 conversations, 1,982 gold spans), our native-Rust CHORUS stack reaches 96.8% at k=150 as raw evidence recall with no neighbor expansion, on an internally reproduced July 2026 run; at k=5 it still yields 72.6%, while end-to-end QA over date-stamped context reaches 85% at k=15 (retrieval-bound). On LongMemEval-S (500 questions), official session_recall@8 is 97.6% (488/500) and end-to-end QA with our reader/judge stack is 97.4% (487/500) -- different protocols from vendor leaderboard figures we cite for context only. On BEIR SciFact (shared MiniLM embeddings, same harness), CHORUS/PRISM edges Chroma on nDCG@10 (0.646 vs. 0.645) and Recall@10 (0.792 vs. 0.783). A graded provenance-conflict suite (n=50) scores 18% top-1 when all pairs share one brain versus 100% under per-case isolation (ceiling, not deployment evidence). Engine, harnesses and frozen JSON are MIT; pip install "fluctlightdb[native]" re-runs the published numbers. We claim no new neuroscience and no new transformer: a missing layer of the data stack, released for others to re-run and contest.

Biomedical language evolves rapidly as new discoveries emerge, causing traditional text models to lose semantic fidelity over time. Static embeddings and co-occurrence graphs cannot capture such evolution, leading to performance degradation in retrieval and knowledge discovery tasks. This paper introduces a Drift-Aware Temporal Graph Rewiring (DATGR) framework that models concept evolution by dynamically updating co-occurrence edges based on estimated semantic drift. Instead of retraining embeddings for each time slice, DATGR performs lightweight, feedback-driven rewiring using a logistic update rule applied to edge weights. Evaluated on the Biomedical Multi-Relation Corpus (BIOMRC), the method achieved a mean Area Under the Receiver Operating Characteristic (AUROC) improvement of approximately 0.066 absolute difference (0.699 vs. 0.633) over a static baseline. Area Under the Precision-Recall Curve (AUPRC) remained comparable (0.738 vs. 0.744), showing that drift-aware adaptation enhances link-prediction recall without a loss in precision. These results demonstrate that edge-level adaptation effectively captures temporal semantic change in evolving biomedical text while remaining computationally efficient and interpretable.

LongEval-Sci evaluates scientific retrieval under collection change, where a system should be effective on the current corpus and remain usable as documents accumulate over time. This paper reports both official Task 1 results and development diagnostics for LongEval-Sci 2026. We compare the official PyTerrier BM25 and Qwen3 dense baselines with full-text BM25, additive and router variants, temporal full-text retrieval, temporal+citation retrieval, RM3 query expansion, cross-encoder reranking, and reciprocal rank fusion (RRF). In the official DCTR evaluation, the temporalized full-text runs are our strongest submissions: FT BM25+temporal and FT BM25+temporal+citation obtain the best ARP on all three snapshots (0.285, 0.267, and 0.180 nDCG@10) and reduce snapshot-3 relative change from 0.481 for the BM25 pivot to 0.368. Citation features match the temporal-only variant but do not provide a measurable additional gain in the official summary. Our internal snapshot-1 diagnostics show a complementary pattern: full-text BM25 is the strongest single development retriever (DCTR nDCG@10 = 0.3302, MAP = 0.2853), RRF gives the best deep recall (Recall@1000 = 0.9667), and some uncalibrated overlays can sharply degrade top-rank quality. We therefore conclude that full-text retrieval is the strongest foundation, temporal integration can improve official longitudinal effectiveness when applied to that foundation, and citation evidence still requires cleaner ablation and calibration. Beyond ranking, we also report a qualitative weekly IR-system update-monitoring analysis based on ingestion velocity and stale-coverage drift.

Artificial Intelligence (AI) models, at their core, apply general learnings from broad datasets to individual circumstances using probabilistic behaviour. This inductive approach stands in contrast to deductive reasoning approaches which seek to prove conclusions from their premises. However, research has shown that deductive reasoning with AI models is a challenging problem and in the real-world it may not always be feasible. An alternative way forward is to leverage abductive reasoning, seeking to corroborate the output of multiple approaches to identify the most likely conclusion from the factual matrix. We apply this to synthetic media detection in forensic settings, and find we are able to disproportionately lower the risk of false positives to true positive recall. We also provide the first empirical evaluation of OpenAI's rollout of SynthID on synthetic images and evaluate how complementary different synthetic media detection approaches are.

RAG systems retrieve documents optimized for answering one query at a time. Yet enterprise users arrive with sessions, that is, coherent episodes of related questions that span semantically distant parts of the knowledge base. We show that a single retrieval call over a standard knowledge base covers only 41% of a user's session-level information need. To close this gap, we reorganize the KB offline using co-occurrence-aware clustering and expand retrieval candidates through cluster neighborhoods at query time. On WixQA (6,221 enterprise support articles), our method raises single-query session coverage to 58% (+17% absolute; 95% CI: [14.1, 20.4]), reduces retrieval calls to 70% coverage by 34%, and compresses the KB to 20% of its original size, all consistently across four embedding models and six functional domains. We argue that session-level coverage, not single-query recall, should be the primary metric for enterprise RAG evaluation.

Multi-Agent Debate (MAD) with Majority Voting is a dominant paradigm for improving LLM reasoning, yet its effectiveness rests on the Condorcet Jury Theorem's assumption of independent errors. Because contemporary LLMs share similar pretraining corpora, their errors are strongly correlated, causing the majority to systematically suppress correct minority opinions, a phenomenon we term Minority Truth. Through debates among three heterogeneous LLM agents on six benchmarks, we find that roughly one in four divergent cases has the minority holding the correct answer, yielding a 10-percentage-point theoretical recovery margin. We propose Minority Sentinel, a lightweight meta-classifier that extracts a multi-dimensional debate fingerprint from debate logs and trains a LightGBM model to decide when to overturn majority voting. Minority Sentinel achieves a stable Flip Precision of 81.2% with positive Net Gain across all six datasets and all 20 random seed trials, demonstrating that debate logs contain sufficient behavioral signals for a non-LLM classifier to reliably recover suppressed minorities without degrading system accuracy. The LLM-as-Judge baseline yields negative Net Gain despite higher recall, confirming that flip safety, not recovery volume, determines intervention value.

Medical device recalls are a critical regulatory mechanism for protecting patient safety. The growing volume of FDA recall records presents challenges in post-report recall triage, severity assessment, and root-cause interpretation. Existing studies mostly address recall occurrence prediction or root-cause analysis separately, while joint modeling of recall severity and root-cause categories has received limited attention. We develop an automated recall triage framework using 54,165 FDA medical device recall records from openFDA, covering the period from 2002 to October 2025. We first evaluate classical machine learning and boosting-based models for recall severity and root-cause category prediction. We then develop RecallRisk-BERT, a multi-task model that combines PubMedBERT-based textual representations of recall narratives with embedding-based representations of structured categorical features, including product code, regulation number, and medical specialty. The model simultaneously predicts recall severity (Class I/II/III) and a consolidated root-cause category (9 classes). Performance was evaluated using accuracy, macro-averaged precision, recall, F1-score, and ROC-AUC. In single-task severity prediction, our LightGBM-based text--tabular configuration achieved the strongest performance, with an accuracy of 0.963, macro-F1 of 0.856, and ROC-AUC of 0.974. In the multi-task setting, RecallRisk-BERT substantially outperformed the single-task PubMedBERT baseline. Model-derived risk rankings were strongly consistent with observed root-cause severity patterns (rho = 0.983, p = 1.936e-6). These findings indicate that text--tabular learning can support scalable post-report recall triage, regulatory decision support, and model-based root-cause risk analysis.

We consider an oracle that processes a limited batch of records at a time and clusters those that refer to the same real-world entity. We study how to interrogate such an oracle to resolve entities in a dataset whose size is far larger than a single batch, and where no batch is guaranteed to contain all records of any given entity. We aim at a pay-as-you-go approach, to have full control over the costs (the number of oracle consults), while achieving the highest possible recall at every step. We formally cast this problem as batched entity resolution, prove that selecting optimal batches is NP-hard, and provide an optimal solution under a natural condition on entity sizes. Finally, we evaluate our approach on six datasets and show its superiority over state-of-the-art baselines.

Clinical value sets define the standardized terminology codes used in quality measurement, phenotyping, cohort construction, and clinical decision support. The recently introduced Retrieval-Augmented Set Completion (RASC) benchmark showed that direct zero-shot large language model (LLM) generation is poorly suited to this task: clinical code systems are large, version-controlled, and not reliably memorized by language models. We study a stage-wise alternative in which candidate-pool construction is optimized for recall and a constrained LLM adjudicator is optimized for candidate selection. On the full 3,744-value-set RASC test split, Qwen3-based retrieval with vocabulary-aware expansion and code-display rescue retrieval increases candidate-pool recall from the original RASC retrieval baseline of 0.553 to 0.730; on the held-out-publisher stratum, pool recall is 0.655. The higher-recall pool alone is not sufficient: applying the original SAPBert cross-encoder to this expanded pool gives full-test macro F1 of 0.287 and held-out-publisher macro F1 of 0.233. Replacing the stage-2 selector with blinded GPT-5 adjudication over the same pool increases full-test macro F1 to 0.549 and held-out-publisher macro F1 to 0.533. These results show that retrieval-constrained LLM adjudication can substantially improve value set completion while preserving the safety constraint that all returned codes must come from an auditable candidate pool.

Multimodal agents repeatedly re-examine the same video frames, UI screenshots, and rendered artifacts as their context window slides and reasoning iterates, yet every look-back re-encodes from scratch, because prefix caches serve reuse only at a fixed leading position. We show this recompute is avoidable, and identify exactly what naive KV reuse loses: the cross-chunk conditioning a chunk absorbs from its neighbours. This loss is asymmetric. The direct readout of a cached chunk is recovered exactly and for free by the standard state-merge. What remains is a diffuse, low-rank residue concentrated in deep layers, invisible to single-hop retrieval but precisely what multi-hop reasoning binds on. Blind reuse therefore leaves single-hop recall intact while halving multi-hop accuracy; this is the failure mode prior position-independent caches, designed for single-context or single-image reuse, do not address. We repair it with a small, training-free low-rank conditioning patch stored alongside each position-free chunk. Reuse reduces to one operator across MLA, GQA, and MHA: exact RoPE re-rotation to any target position, plus the patch that restores cross-chunk binding. This makes three window operations cheap: reorder (one patch serves every ordering of a cached set), sliding-window survival (surviving chunks relocate via rotation only, zero re-encode), and recall (an evicted chunk is rehydrated by its patch, never re-encoded). A rank-m patch recovers full task accuracy on cross-chunk-binding benchmarks, MM-NIAH across two attention families and two-page doc-QA, at a fraction of the KV footprint, and reconstructs re-prefill KV to within bf16 rounding in a production SGLang kernel across six backbones. The conditioning signal is strongest in redundant vision and video streams, making our solution most impactful where multimodal agents spend their recompute budget.

Large language models have shown strong performance on software engineering (SE) tasks, yet understanding large industrial repositories remains challenging. Existing methods often retrieve only local fragments and fail to recover the broader task-relevant context needed for complex repository-level tasks. We present DeepDiscovery, a task-level repository-understanding method for large industrial codebases. DeepDiscovery uses a two-stage \textit{Location--Inference} framework to localize high-confidence task anchors and recover broader task-relevant context over multi-relational repository structure under budget constraints. Across controlled method-level evaluation, organization-internal industrial repository-understanding scenarios, and end-to-end evaluation on SWE-bench Verified, DeepDiscovery consistently improves task-relevant file recovery and downstream SE performance. On 27 medium-scale tasks, DeepDiscovery achieves the best file recovery quality among five representative baselines without offline preprocessing. On organization-internal industrial tasks from a production-scale integrated codebase ecosystem, including 27 medium-scale tasks and 40 large-scale tasks, DeepDiscovery improves Full Recall Rate across multiple AI coding systems, with absolute gains ranging from 1.6 to 9.2 percentage points on large subprojects and from 2.5 to 7.4 percentage points on medium-scale subprojects. In a controlled end-to-end evaluation on SWE-bench Verified, a system equipped with DeepDiscovery achieves a 78.6% Solve Rate, outperforming the corresponding baseline by 8.2 percentage points. These results suggest that stronger task-level repository understanding can improve coding-agent performance on complex SE tasks.

Detecting hallucinations in clinical text is increasingly framed as an explainability problem: systems should not merely flag an unreliable response but point to the offending span. Architectures built around knowledge-graph (KG) triple decomposition are marketed for exactly this auditability, yet their localization ability is typically assumed rather than measured. We introduce MedHal-Loc, a benchmark and metric for localization faithfulness -- whether a detector's top-ranked error unit actually overlaps the erroneous span. The controlled subset comprises 300 PubMedQA-derived statements with single, span-level errors injected across four localizable types (entity substitution, relation error, mechanism misattribution, invention), yielding gold spans by construction; a complementary natural subset documents that real hallucinations are dominated by diffuse conclusion-flips that resist span localization (a human expert accepted 1/18 candidate spans). Evaluating four fine-grained paradigms, we find that NLI-per-clause, consistency-per-sentence, and the dedicated span detector FAVA all localize well above chance, whereas an elaborate KG-triple pipeline localizes no better than chance (+3.3pp, n.s.), bottlenecked by ~59% entity-extraction coverage -- despite competitive detection F1 (0.609). Detection competence does not imply faithful localization; architectural explainability must be validated, not presumed.

Automated radiology report generation (RRG) has gained increasing attention because it can reduce the heavy workload of clinical report writing. However, most existing methods mainly optimize for natural language generation (NLG) metrics that focus on language fluency, while providing little control over clinically important factors such as precision and recall. As consequence, generated reports may be fluent but not well aligned with different clinical needs. To address this challenge, we propose a reinforcement learning framework for precision recall controllable RRG, where a control parameter explicitly adjusts the trade-off between clinical precision and recall during inference. This design allows the model to flexibly generate reports according to different clinical requirements. To ensure clinical correctness, we introduce a clinical reward into the training objective, which helps improve clinical efficacy (CE) beyond standard language-based optimization. In addition, we apply a group-relative training strategy that normalizes rewards within each training group, reducing reward variance and improving training stability. Extensive experiments on the MIMIC-CXR dataset show that our method consistently outperforms state-of-the-art approaches in both NLG and CE evaluation metrics, while providing reliable control over the CE precision recall trade-off.

The rapid growth of large-scale AI workloads, particularly Large Language Model (LLM) training and inference, is fundamentally reshaping the operational dynamics of hyperscale data centers. Unlike traditional cloud workloads, AI-driven jobs exhibit bursty, high-intensity, and rapidly shifting resource demands, often leading to sudden capacity stress that cannot be effectively handled by reactive threshold-based mechanisms. In this paper, we propose a deployment-oriented, burst-aware early warning framework for proactive capacity stress prediction under AI workload surges. We formulate the problem as a high-recall forecasting task over multivariate telemetry windows, with the explicit goal of enabling operational intervention before system degradation occurs. The proposed framework integrates workload intensity, temporal variation, and system pressure signals, and employs a lightweight tree-based learning model to capture nonlinear interactions in highly imbalanced environments. To evaluate the system under realistic conditions, we introduce an AI workload surge injection methodology that simulates burst-driven demand patterns observed in large-scale AI systems. Our XGBoost-based model achieves an ROC AUC of 0.697 and an AP of 0.670, significantly outperforming baseline methods. Under deployment-oriented threshold selection, the framework achieves a Recall of 0.914, enabling the detection of the majority of stress-prone periods with acceptable false-alarm cost. Beyond predictive performance, we show how the proposed framework can be integrated into operational control loops to support proactive actions such as workload throttling and resource scaling. Our results highlight the practical value of high-recall, learning-based early warning systems in enabling resilient and adaptive data center operations in the era of AI-driven workloads.

A new class of agentic review systems are emerging as a remedy to the pressure placed on peer review systems by AI-assisted research, but it is unclear how they should be evaluated. We evaluate two open-source systems (OpenAIReview and coarse), one proprietary system (Reviewer3), and a zero-shot baseline, across six LLMs spanning frontier and efficient models. First, we study whether AI reviews on ICLR/NeurIPS papers track with papers' quality as approximated by external signals such as citations and acceptance decisions. Every system performs above chance in pairwise accuracy, and the best is OpenAIReview + GPT-5.5 at 83.0%. Second, to test whether systems can catch errors with known ground truth, we construct a perturbation benchmark that injects four categories of errors into papers across eight arXiv subject classes and measure detection recall. The strongest configuration (OpenAIReview + GPT-5.5) catches 71.6% of injected errors, leaving substantial room for improvement. The union of detections across six models reaches 83.3% recall, suggesting different models detect different errors and better harness design can potentially increase performance. Beyond these benchmarks, we study a public deployment of OpenAIReview with real users. Votes on its comments skew positive at 1.44 to 1, and the most common complaints are about false positives and minor nitpicks. Together, by evaluating full review systems backed by state-of-the-art models on real research papers, we show that while AI reviews still have room for improvement, they can already track human quality judgments well, catch important errors, and earn positive feedback from real users.

RAG ingestion pipelines frequently augment search corpus index with semantic enrichment indices (e.g., synthetic queries or summaries generated from corpus chunks) that are subsequently queried alongside the base index to improve retrieval via better alignment between document representations and user intent. While these supplementary representations substantially improve retrieval quality, they introduce a computational bottleneck: the configuration space of enrichment types and generator models is combinatorial, and the cost of exhaustive index-time evaluation scales linearly with corpus size. We introduce CAMI (Cost-Aware Multi-Indexing), a framework that formalizes multi-index construction as a budgeted, multi-objective portfolio selection problem. CAMI targets the upstream decision of which enrichment views to generate and materialize before the retrieval backend is applied. CAMI incorporates three primary mechanisms: (i) an agentic discovery phase that proposes corpus-specific representation templates; (ii) an atomic-unit search procedure that evaluates individual enrichment-model pairs and recombines them via fidelity-local closure to identify synergistic portfolios; and (iii) a confidence-aware promotion schedule that prunes unpromising configurations early, decoupling optimization spend from total corpus size. We evaluate CAMI across diverse retrieval corpora. Our findings reveal that the framework systematically isolates high-recall portfolios under strict budget constraints, outperforming standard content-only baselines in challenging settings by up to 9.4% recall@10. Further, CAMI is able to systematically identify these high-recall portfolios using up to 5x less budget compared to random search baselines, making our approach practical in real production scenarios.

Diffusion models have emerged as state-of-the-art generative models for high-fidelity image synthesis, particularly in their classifier-free guided and classifier-guided forms. However, standard classifier guidance concentrates probability mass around high-density class mean, leading to poor coverage of rare samples in the tails of the class-conditional distributions. Recent work on diffusion-based tail sampling mitigates this by training an additional low-density-seeking classifier with a synthetic-vs-real discriminator, at the cost of additional networks and training. In parallel, a number of samplers and distillation techniques accelerate or refine diffusion sampling, but do not explicitly address long-tail coverage. We propose a purely sampling-time, density-aware extension of classifier-guided conditional diffusion model that targets low-density regions without any additional training. We have applied guidance at noisy images not on predicted noise like most diffusion models. Starting from a pretrained conditional diffusion model and classifier on ImageNet, we modify the guided reverse dynamics by steering trajectories toward low-confidence regions via the modified classifier gradient, and at each time step, we also guide the sampling process toward the predicted real image. 1st guidance helps explore low-probability samples, and 2nd guidance helps to generate samples to be close to the real data manifold. The proposed sampler consistently improves ADM model recall at 64x64 resolution while maintaining a comparable FID, and with a 256x256 ADM model, we showed the results visually with different combinations of both guidance. We also showed that standard ADM classifier guidance, combined with predicted real image guidance, helps generate high perceptual quality samples with a 256x256 ADM model on ImageNet.

While Large Language Models (LLMs) have advanced open-domain dialogue systems, maintaining long-term consistency remains a challenge due to inherent limitations in long-context reasoning and the inefficiency of processing extensive raw text. Existing approaches typically rely on either unstructured memory storage, which is prone to information loss, or computationally expensive LLMs that incur high latency. To address these limitations, we propose G-Long, a graph-enhanced framework that utilizes a fine-tuned small Language Model (sLM) for structured triplet extraction and associative retrieval, significantly reducing operational costs. Furthermore, we introduce the novel attention-aware importance scoring mechanism that leverages the intrinsic cross-attention signals of a T5 summarizer to identify salient memories. Extensive experiments across diverse benchmarks demonstrate that G-Long achieves state-of-the-art performance in both response generation and memory retrieval, yielding performance gains of up to 9.8% in response quality on MSC and 40.8% in retrieval recall on LME, while significantly minimizing computational overhead.

Vision-language models (VLMs) are increasingly used to detect whether AI-generated images contain visible artifacts, yet their ability to analyze such artifacts remains poorly understood. A correct image-level decision can still hide important failures: a model may correctly flag an artifact while relying on the wrong visual cue, selecting the wrong region, or describing a defect that the image does not support. To evaluate these behaviors directly, we introduce SalArt-VQA, a diagnostic benchmark for fine-grained SALient ARTifact understanding in AI-generated images. SalArt-VQA contains 950 images and 3,681 human-authored multiple-choice questions spanning artifact images, matched real reference images, and paired generated reference images. Four aligned question types evaluate presence detection, semantic localization, spatial grounding, and evidence-grounded defect identification, while the reference splits test calibration and abstention when the annotated defect is absent. Across 20 VLMs, SalArt-VQA reveals failures that image-level detection accuracy hides: the strongest model reaches 99.37% detection recall on artifact images but answers all four artifact-side questions correctly on only 53.26% of images. Comparing artifact images with artifact-free references reveals a sensitivity-calibration tradeoff: sensitive models often make unsupported artifact claims, while conservative models avoid false alarms largely by missing real artifacts. These results show that high artifact detection accuracy alone does not imply grounded artifact understanding. SalArt-VQA exposes these hidden failure modes and provides a fine-grained evaluation of whether VLM artifact claims are supported by local visual evidence.

Reference-free faithfulness metrics verify each atomic claim a model makes against ground truth, and are increasingly used to evaluate grounded generation. We show they share a blind spot: they measure only precision -- are the stated claims supported? -- and therefore reward abstention, since a model can score near-perfect faithfulness by saying almost nothing. We make this measurable using Formula 1 telemetry, a domain where strategic ground truth is derived deterministically and, crucially, completely: for each decision we know the full set of facts that mattered. This completeness -- absent in open-domain faithfulness benchmarks -- lets us measure recall (coverage of the relevant facts) exactly, alongside precision. On a multilingual (EN/ES/PT) benchmark of 7,253 decision instances spanning 157 races, the most precise frontier model covers under half of the relevant facts and ranks last by F1, so requiring coverage reorders the systems; the same effect reappears in a second complete-oracle domain (NOAA weather forecasts). Fine-tuning small models (1B-7B) on the complete oracle closes the precision-recall gap entirely (F1 ~0.98), beating every zero-shot frontier system regardless of scale. We pair faithfulness with coverage into a single score, validate the metric (controlled perturbation; agreement across a model-free regex extractor and a cross-family LLM extractor, system-level Spearman 1.0), and give a verifier-guided generation method that improves precision and recall without references. We release the benchmark, structured annotations, metric, baselines, and an interactive demo.

The classic paradigm of language identification in the limit models learning as a game between an adversary, who reveals strings from an unknown target language, and a learner tasked with identifying that language. The recently introduced framework of language generation in the limit shifted the objective to better reflect modern language modeling, requiring the learner to produce valid, unseen strings from the target language. Related work highlighted a fundamental tension: a broad coverage of the target often comes at the cost of validity. We introduce a new notion of precision and recast this problem as the classic recall-precision trade-off. We analyze generation in the limit under varying constraints on enumeration, novelty, and validity, aimed at reflecting settings closer to those encountered by large language models. A key contribution is our analysis of learners that are not eventually valid: we allow infinitely many mistakes, provided their frequency tends to zero so that precision remains one. We show that this relaxation can strictly increase recall when the adversary permanently withholds a large portion of the target language. We also study a continuous relaxation of the novelty constraint that requires only a fixed fraction of outputs to be novel. Taken together, our results move toward a more realistic model of language generation where occasional errors and repetitions are unavoidable, but their rates are controlled.

We present a method for automatic Chinese web neologism detection that operationalizes traditional linguistic identification principles as prompt-engineering skills. The method has four stages: tokenizer-independent character n-gram candidate generation; dictionary anchoring with a Pointwise Mutual Information pre-filter; a well-formedness skill based on Chinese word-formation principles; and a combined rule and three-way classification skill that distinguishes neologism, entity, and none. Applied to the BAAI CCI 3.0 corpus (267M documents), the method produces 226,959 classified candidates including 4,853 labeled neologisms. To evaluate the method, we develop a per-stage conditional recall decomposition in which the pipeline's strict recall factors mathematically into the product of stage conditional recalls. Applied to Hou (2023) (4,199 entries), the decomposition exposes Stage 1 candidate coverage and Stage 4B LLM semantic judgment as the two bottlenecks (R=41.5% and 60.0% respectively), while intermediate stages are near-lossless. A length-stratified analysis further reveals that the structural well-formedness skill is length-invariant (>= 96.9%) whereas the semantic novelty-classification skill is length-dependent (65.6%/59.0%/44.1% across 2/3/4-character candidates), mapping a current boundary of skill-based linguistic operationalization. We release the method, pipeline outputs, and evaluation protocol as public resources.

Linking FDA-approved medical devices to their underlying United States Patent and Trademark Office (USPTO) patents enables critical applications such as recall root-cause analysis, M&A-driven IP discovery, and technology trajectory mapping. However, this cross-domain entity linking task remains unexplored due to severe semantic gaps: FDA documents focus on clinical outcomes, while patents describe technical mechanisms, yielding minimal lexical overlap. We formalize medical device-patent linking as a challenging cross-domain entity linking problem characterized by label scarcity and domain shifts. Using cardiovascular devices as a high-impact, representative domain featuring diverse technologies, high recall rates, and abundant disclosures, we construct a benchmark with 434 devices, 698K patents, and 585 high-fidelity expert-verified pairs. To address these challenges, we propose Bridge-MedDevKG, a coarse-to-fine framework that integrates (1) MedDevOnto, a domain-specific ontology that anchors device concepts via three-tier UMLS normalization; (2) Multi-signal candidate generation fusing company affiliation, semantic similarity, and ontology-weighted entity overlap; and (3) Heterogeneous reranking with multi-signal scoring and XGBoost classification on hard negatives. Our approach achieves a conservative lower-bound recall of 91.6% on the gold standard with 50.9% noise reduction, substantially outperforming LLM baselines under comparable evaluation. The resulting MedDevKG provides 6.8M high-confidence links, laying a scalable foundation for regulatory-IP integration across medical specialties.

Final-answer accuracy, retrieval recall, and citation overlap do not reveal how much answer advantage a long-context or retrieval-augmented language model actually recovers from supplied evidence. A model may answer from parametric priors, fail to use evidence that is present, or cite relevant text without converting it into the final answer. This paper introduces a four-condition diagnostic protocol for evidence-utilization evaluation under matched examples, models, prompts, and scoring rules. The protocol compares no-evidence, full-context, retrieved-evidence, and oracle-evidence reference conditions, and uses Oracle-Reference Normalized Context Utilization (ONCU) as a denominator-valid estimate of recovered oracle-reference evidence advantage. The empirical study evaluates five local open-weight models from the Qwen, Gemma, Llama, and Mistral families over Controlled-ONCU-safe16K, HotpotQA-ONCU, and 2WikiMultiHopQA-ONCU, comprising 18,000 ONCU-compatible predictions. Results show a task-dependent diagnostic pattern: controlled synthetic settings expose reduced recovery when the same evidence is embedded in long input rather than supplied compactly, while realistic multi-hop reconstructions show that full-context inputs outperform the tested retrieved inputs in denominator-free answer and evidence metrics, with ONCU supporting the same direction on oracle-improving groups. Sensitivity audits with stronger retrieval settings narrow some gaps but do not overturn the scoped interpretation. The main contribution is therefore not a single utilization ratio, but a matched diagnostic protocol that separates no-evidence answerability, oracle-evidence recoverability, full-context recovery, retrieval-conditioned recovery, denominator validity, and companion answer/evidence diagnostics.

Long-horizon agents can archive large histories, but future answers still incur retrieval, rereading, and context costs. When retained memory misses answer-relevant evidence, the system must return to larger portions of the raw history. We study budgeted evidence survival: before the query is known, which source evidence should be retained so that it remains recoverable and usable under a fixed retained source-evidence token budget? We instantiate this setting as Budgeted Pre-Query Retention, where memory is written during ingestion and later read without access to the full raw stream. We introduce EMBER, a learned retention policy that constructs a compact, source-backed evidence state. EMBER stores evidence capsules: verbatim source excerpts paired with retrieval keys and update metadata, preserving both grounding and read-time access. Post-query outcome feedback trains the writer to preserve evidence across the ingestion-retrieval-answer chain. On LongMemEval-RR, our LongMemEval-derived retained-evidence protocol, EMBER-14B reaches 0.3017 F1 at the 8192-token retained-evidence comparison point, compared with 0.1765 for the strongest non-EMBER budgeted baseline. Across retained source-evidence budgets, EMBER improves F1, Retain-Recall, and Read-Recall, indicating that long-horizon memory depends on retaining evidence within the budget rather than rereading larger histories.

As LLM agents adopt large skill libraries, selecting the right subset becomes a structural problem rather than a similarity-matching one: skills depend on, conflict with, specialize, or duplicate one another, a structure invisible to both full enumeration and embedding similarity. We present SkillDAG, which models inter-skill relationships as a typed directed graph and exposes it to an LLM agent as an inference-time, agent-callable structural retrieval interface, queried and evolved during execution rather than baked into a fixed retrieval pipeline: each search returns vector matches, typed-edge neighbors, and conflict signals, and a propose-then-commit protocol lets the agent register execution-backed edges so the graph accumulates structure across episodes. On ALFWorld and SkillsBench with MiniMax-M2.7, SkillDAG reaches 67.1% success and 27.3% reward, exceeding the strongest reported Graph-of-Skills baseline by +12.8 and +8.6 points; the advantage ports to gpt-5.2-codex, and intrinsic SkillsBench Ret@K rises from 65.5 to 78.2 under matched queries. These gains trace to isolable mechanisms: candidate ranking that stays robust as the pool grows 10x where a fixed seeding-diffusion pipeline degrades, and set-monotone online edits that enlarge ground-truth recall without evicting prior hits.

Multimodal LLMs use dedicated encoders to bridge non-language modalities (vision encoders for images, depth models for audio codec tokens) because raw token embeddings alone cannot capture modality-specific structure. We argue that Semantic IDs (SIDs), the hierarchical codes used in generative recommendation, constitute another such modality: a SID level token's meaning depends on its prefix context, yet current systems simply add SID tokens to the vocabulary and rely on training to learn these context-dependent meanings from scratch. We propose PrefixMem, a lightweight SID encoder based on prefix n-gram memory tables that provides the LLM with structured, prefix-conditioned representations at SID token positions. Like vision encoders in multimodal LLMs, PrefixMem can be pre-trained independently and then attached to any LLM for joint training. We evaluate on large-scale data from Pinterest across multiple LLM families and show that PrefixMem improves deepest-level SID accuracy by up to 46% relative and full-SID retrieval recall by up to 22% relative at matched training compute. The encoder's benefit concentrates on hard examples where greedy decoding fails, with up to 77% relative accuracy gains, confirming that SID tokens benefit from a dedicated encoder just as other non-language modalities do.

Biomedical NER is deceptively simple for modern LLMs: plausible biomedical mentions are easy to surface, but corpus-convention correctness depends on annotation conventions, span boundaries, entity granularity, and type schemas. Multi-LLM agreement is a salience signal, not corpus-convention correctness. We introduce a candidate-level panel-output benchmark for panel-surfaced candidate verification, where the unit is an aligned candidate surfaced by an explicitly defined multi-model panel rather than a standalone extractor output. The benchmark aligns eight LLMs' predictions over five public biomedical NER datasets into a candidate master table. BioConCal is an in-domain supervised scorer that instantiates this layer with inference-time gold-free agreement, mention, surface-availability, and document features for a fixed candidate stream. In domain, BioConCal improves AUROC from 0.753 for raw agreement to 0.910. At a validation-selected 0.95 precision target it selects 1,340 candidates at empirical test precision 0.939, compared with 293 for raw agreement. This corresponds to candidate-level recall 0.592 and corpus-level recall 0.523 against a within-panel row-label ceiling of 0.883. The main benefit is not recovering entities missed by every panel member, but reshaping a noisy panel stream into a higher-yield review queue. Under entity-type shift, thresholds require target-domain validation, and exact character localization remains a separate deterministic post-processing step.

In large-scale benchmarking of stochastic optimization algorithms, the key challenge is no longer whether repeated runs are needed for reliability, but how to determine when sufficient evidence has been collected without incurring unnecessary computational cost. We study a learning-based extension of a recent empirical online heuristic that adaptively estimates the required number of runs using outlier handling and skewness-based symmetry checks. Using annotated outcomes from 132{,}000 Nevergrad runs on COCO (24 problems in 20 dimensions, 10 instances each, 11 optimizers), we train classifiers on 23 statistical, energy-free, and shape and stability features to predict whether a run-number estimate is reliable, prioritizing detection of incorrect estimates via minority-class recall. We evaluate reliability prediction using a within-configuration learning setup, where models are trained and tested on data sharing the same optimizer. The results show that run-number reliability can be learned in a within-configuration scenario, enabling detection of unreliable estimates with high minority-class recall, although performance remains limited by the restricted data diversity within fixed configurations.

Mean cross-entropy is the standard validation metric for language models, but it can fail to track model quality during training. We examine this in two common scenarios. First, in Qwen2.5-1.5B SFT on synthetic fact-learning, we find that mean CE rises substantially after the initial learning phase while held-out fact-recall accuracy remains near its peak. Second, we find that in top-K distillation on TinyStories, decreasing K improves median CE while worsening mean CE; the Top-5 student attains the highest LLM-judge score and crosses below its teacher on median CE, despite having the worst mean CE. In both cases, median CE correlates much more closely with task performance than does mean CE. Analyzing how bulk and tail percentile CE move during training reveals that training reshapes the empirical per-token CE distribution. In top-K distillation, smaller K yields a distribution with more mass at both extremes, decreasing the median and increasing the mean. In Qwen SFT, the bulk saturates quickly while the tail extends in the latter half of training. In both, the task-evaluation metric appears more sensitive to the bulk than to the tail. Practically, we recommend reporting a small set of percentile CE summaries alongside the mean, and using concordance among them as a tool to keep track of distribution reshaping, as well as a low-cost diagnostic for when mean and median CE disagree on model selection.

Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We study a more aggressive but explicitly lossy setting: compress text into compact codes that an LLM can expand into task-relevant meaning. We call this setting SemanticZip. Unlike lossless compression, SemanticZip does not require byte-identical reconstruction; unlike ordinary summarization, it treats model-based decompression as part of the codec and evaluates whether task-relevant semantic commitments are recovered. This paper is a pilot framework, not a benchmark claim. We formalize LLM-mediated decompression, define a protected/lossy packet architecture, and evaluate six representation regimes over five author-constructed diagnostic cases: structured prose, JSON, CCL-Core, CCL-Min, SemanticZip ASCII, and SemanticZip emoji. An independent decoder LLM reconstructs typed semantic atoms from each compressed representation, and we score Critical Atom Recall, Weighted Atom Recall, precision, and tokenizer gain. In this pilot, structured prose has the highest recoverability, with WAR = 0.956 and 19.1% o200k_base token gain. CCL-Min is the strongest balanced point, with 39.4% token gain and WAR = 0.874. SemanticZip ASCII provides the largest useful compression, with 46.5% token gain and WAR = 0.802, while emoji-heavy SemanticZip performs worse on both compression and recovery. The main contribution is not the claim that these numbers establish a universal frontier. Rather, we introduce a reproducible experimental interface for studying lossy, LLM-decompressible text codes and a design principle: safety-critical and exact commitments should remain protected, while predictable low-risk context may be semantically zipped.

Composed Image Retrieval (CIR) requires both preserving the visual continuity of the reference image and faithfully executing the semantic variables specified in the modification text, which constitute the core challenge of the task. Existing methods often suffer from Perception Myopia in a single space, or fall into Logic Drift in iterative collaboration due to the perception ceiling of the underlying retriever. To address this issue, we propose a one-stop hierarchical Perception-to-Deliberation Framework (PDF), which, to the best of our knowledge, is the first to introduce experience self-evolution and Test-Time Scaling Laws (TTS) into CIR. Relying on a hierarchical multi-agent architecture, PDF first utilizes an Intent Routing Manager to dynamically dispatch multi-view Worker perception signals based on modification intents to construct a high-recall candidate pool. Subsequently, the Decision Manager combines a Training-free Reasoning Policy Distillation mechanism with a Tournament-style TTS (T-TTS) strategy to achieve self-evolving fine-grained reasoning, yielding the final retrieval results. Experimental results demonstrate that PDF achieves SOTA performance on three benchmark datasets: CIRR, CIRCO, and FashionIQ. This study indicates that experience-driven self-evolution and TTS represent a highly promising and scalable path for achieving zero-shot fine-grained multimedia retrieval. The code will be made publicly available upon acceptance.