CS Paper Radar

Weekly top 20 · cs.DB

2026-W47 Nov 16 – Nov 22, 2026

Ranked from 1,465 papers submitted on 2 days — week in progress, ranks can still change.

Score = weighted mean ofCitations 20%Upvotes 10%Code stars 10%Venue 15%Code/data 10%Novelty 15%Momentum 15%Substance 5%how it works
1

SiGMA: Site-Grounded Multi-Modal ISAC Data Generation for Environment-Aware Communications

eess.SP cs.DB ·2026-11-16 ·Yijie Bian, Wei Guo, Kai Zhang, Xiao Ye, Shurui Xu +3 more
code/data
Abstract

Learning-based multi-modal integrated sensing and communication (ISAC) requires data that associate environmental observations with the wireless response generated by the same site and dynamic scene state. Acquiring such data at new sites requires sensor calibration, coordinated measurements, and cross-modal association. We present site-grounded multi-modal ISAC data generation (SiGMA), which combines OpenStreetMap (OSM), Overture Maps, and procedural three-dimensional (3D) reconstruction to create georeferenced urban scenes. A shared scene geometry and time-indexed actor state link synchronized red-green-blue (RGB) images, light detection and ranging (LiDAR) point clouds, positioning records, frequency-modulated continuous-wave (FMCW) Radar in-phase and quadrature (IQ) samples, and ray-traced wireless channels. For configurable reflected propagation under direct-link blockage, SiGMA generates optional reconfigurable intelligent surface (RIS) component channels for phase-configuration evaluation across shared scene states. The evaluation results demonstrate that the framework improves zero-shot beam prediction performance on real DeepSense 6G measurements compared with an OSM-derived synthetic-data baseline. A camera-assisted RIS case study further demonstrates the generation of sensing-associated supervision for configurable reflected propagation. The dataset generation pipeline is available at https://github.com/Trans-cending/SiGMA-main.

0.47
2

Living Context Graphs: Continual Semantic Learning for Enterprise Data Reasoning

cs.CL cs.AIcs.DBcs.ET+1 ·2026-11-16 ·Varun Agrawal, Ayush Srivastava, Eshan Gujar, Kaushal Kumar, Ayush Gupta
publishedcode/data
Abstract · 22 pages, 5 figures. Accepted at the NeurIPS 2026 Workshop on Continual Learning in the Era of Foundation Models and Embodied Agents. Data s…

Enterprise AI can now perform analytics, reporting, and data-driven workflows, yet the data foundations it relies on remain hard to operationalize: business meaning, relationships, metric definitions, and reporting conventions are absent from database schemas and scattered across undocumented systems and tribal knowledge. We introduce the Living Context Graph (LCG), a continually learned context layer that makes existing enterprise data operational for AI without requiring a copy or transformation of the underlying warehouse. LCG bootstraps base semantics and relationships from the data itself, builds a concept graph that indexes business context as queries are served, writes durable semantic learnings from verified outcomes, and withdraws or re-earns context when later outcomes contradict prior routes. We evaluate LCG through text-to-SQL, a core data-reasoning task, on a transfer-aware split of three BIRD databases comprising 499 questions: 353 form the learning history and 146 are held out and never used to update the context layer. Bootstrapping alone improves overall accuracy by +4.6 percentage points. Learning only from the history raises accuracy on the untouched held-out transfer set by +22.6 points (95% CI [+14.4, +30.8]), exceeding five-shot retrieval from the same history by +12.3 points. Incremental learning reaches the one-shot endpoint within observed evaluation noise on every database. Ablating the graph changes held-out accuracy by at most one question per database but increases per-query cost 2.3-3.3x and median latency 1.8-3.4x: continually learned semantics drive accuracy, while the graph makes that context efficient to serve.

0.43
3

Pelorus: Warped-Product Graph Indexing for Hyperbolic Vector Search

cs.DB ·2026-11-17 ·Wenxuan Xiao, Xu Cao
code/data
Abstract · 30 pages, 6 figures. Full version with proofs and supplementary experiments. Code and artifacts available at https://github.com/Astrmira/Pel…

Hyperbolic embeddings capture hierarchical relations, but million-scale approximate nearest neighbor search must reconcile geodesic fidelity with memory efficiency. Flat inner-product indices distort order across radial shells, while native hyperbolic graphs repeatedly access full-precision vectors or quantize coordinates with singular conformal scales. We present Pelorus, a warped-product proximity-graph index for hyperbolic vector search. Pelorus separates unquantized FP32 radial and conformal scalars from scale-invariant 2-bit spherical directional codes and defers full-vector FP64 evaluation to a compact reranking tail. A conformal distortion analysis motivates orthogonal-projection debiasing, purity-gated tangent-cone residuals, and Conformal Jacobian gating. QuadriPrune allocates edges across geodesic fibers, same-shell rings, and radial elevators, with spanning-tree chord swaps restoring entry reachability. A single-page record layout and carry-save AVX2 kernel accelerate traversal. Across eight real and synthetic benchmarks on AMD EPYC 9654, Pelorus builds Cohere-1M indices 5.44x faster than full-precision polar graphs on 32 threads, reducing hot navigation memory to 517.0 MB. At 99% Recall@10, it improves Cohere-1M throughput by 4.30x on one thread and 6.31x on 24 threads, and delivers 53,483 QPS on MERU-1M. On clustered narrow shells, tangent-cone residuals raise recall from 34.22% to 99.385%, while isotropic narrow-shell stress tests expose remaining recall limits.

0.42
4

Tight Width Minimisation of Self-Join-Free Quantified Conjunctive Queries

cs.DB cs.LO ·2026-11-16 ·Hubie Chen, Fabio Mogavero, Sam M. Thompson
top venue
Abstract · To appear at PODS 2027

Query minimisation is a classical problem in database theory and the width of a formula, defined as the maximum number of free variables over all subformulae, is a central measure for query evaluation. We study width minimisation for a subclass of quantified conjunctive queries (QCQs), namely self-join-free QCQs. For this subclass, we show that rewriting optimality coincides with semantic optimality: given a query $φ$, the minimum-width query obtainable from $φ$ by applying natural and established rewriting rules has minimum width among all first-order formulae logically equivalent to $φ$. As a consequence, the width of a self-join-free QCQ can be optimised by a logical-equivalence-preserving rewriting algorithm.

0.39
5

Errpedia: Is Your Exact $k$-NN Vector Search Really Exact?

cs.DB ·2026-11-17 ·Yinuo Deng, Ying Zhang, Hanchen Wang, Wenjie Zhang
benchmarkdatasetcode/data
Abstract

Exact $k$-nearest-neighbor ($k$-NN) vector search is a common feature of vector libraries and database systems. It serves applications that require exact results and provides the ground truth for evaluating approximate search. However, floating-point rounding and overflow can cause an exact search to return mathematically incorrect top-$k$ result sets. These errors can go unnoticed and affect downstream tasks that rely on exact results. We present Errpedia, a purpose-built dataset for testing the numerical correctness of exact vector search. Errpedia contains 1,616 queries across 21 error categories, with ground truth independently verified using exact rational arithmetic. We evaluate 20 widely used library and database configurations and find that every tested configuration returns mathematically incorrect top-10 result sets on at least 1 applicable query. Failures include misranking nearly equidistant vectors and returning incomplete results: 1 library omits all 10 exact matches to a query, and several systems return fewer than $k$ neighbors. We release Errpedia as a reproducible benchmark for developers and researchers to test their implementations. The dataset is publicly available at https://github.com/dynos01/errpedia.

0.34
6

SIMQ: A Single Graph-based Index for Multi-Vector Query

cs.IR cs.DB ·2026-11-17 ·Yifan Lu, Jiabao Jin, Xiaoyao Zhong, Peng Cheng, Xiangyu Wang +5 more
publishedcode/data
Abstract · under ICDE 2027 review, 13 pages

Multi-vector retrieval models such as ColBERT achieve state-of-the-art effectiveness by representing documents as sets of token-level vectors and scoring via MaxSim, but their high computational cost limits scalability to large corpora. Existing approximate methods face fundamental bottlenecks: centroid interaction matrix approaches require computing a full matrix at every query and rely on GPU-accelerated clustering, while data-oblivious compression methods yield unstable recall that requires repeated compensation. We propose SIMQ (Single graph Index for Multi-vector Query), a framework that bridges single-vector graph indices and multi-vector retrieval through data-aware sampling-based clustering and per-token graph navigation, simultaneously bypassing all aforementioned bottlenecks. SIMQ organizes all token vectors into fine-grained clusters via data-aware sampling, builds a single graph index over cluster centroids independently of PLAID's residual representation, and approximates the MaxSim score through per-token graph search without materializing any interaction matrix or relying on GPU acceleration. We provide theoretical analysis showing that, under a manifold assumption and successful cell retrieval, data-aware partitioning has a smaller expected approximation error than a data-oblivious partition. Building on this foundation, SIMQ+ further introduces count-based scoring and a dynamic candidate set to improve robustness across varying query conditions. Experiments on five benchmarks compare recall, throughput, and construction time against several baselines, primarily on CPU; large-scale PLAID k-means centroids are built on a separate GPU machine. SIMQ has been integrated into VSAG, an Ant Group's open-source vector search library.

0.33
7

A Temporal Algebraic Framework for Data Stream Evaluation Under Delayed Labels and Distribution Shifts

cs.LG cs.AIcs.DB ·2026-11-16 ·Ronaldo C. Prati, Elaine Ribeiro de Faria
code/data
Abstract · 53 pages, 25 tables, 2 figures. Code: https://github.com/rcprati/data-stream-evaluation (experiments), https://github.com/rcprati/aggmetrics…

In data streams, labels often arrive late or only for some instances, class prevalence drifts, and rare classes vanish from short windows. Standard evaluation then confuses a degraded decision boundary with a change in prevalence, and is biased when labels are delayed or selected by the model. We extend an algebraic framework that obtains pooled (micro) and per-class (macro) measures from one confusion matrix to streams, weighting the counts in time by exponential fading or a sliding window; the update costs O(m^2) per step, whatever the stream length, and each pooled measure stays a weighted combination of the per-class ones. Delayed and selective feedback enter as an observation mask: until its label arrives, an instance is counted with the model's calibrated class probabilities, and the bias of this interim estimate is driven by their calibration error. Audited conventions report no value for a class without verified instances. We separate prior shift from concept drift by monitoring prior-free coordinates (recall and specificity) and attribute a change in a measure to the two sources with a first-order Jacobian decomposition. On synthetic streams and four real datasets, a detector on these coordinates with a memory per class raises no excess false alarms under label shift, unlike the Jacobian alarm and error-rate detectors. The correction for delayed labels recovers recall in some real settings and is only partial for precision, specificity and F1. Twenty-five statements are checked in Lean 4, and the code is in the aggmetrics package.

0.33
8

Optimizing Query Decomposition for Reliable Validation

cs.DB ·2026-11-16 ·Shuo Zhang, Sudeepa Roy, Jun Yang
Abstract · 20 pages, 7 figures, 6 tables

Large language models (LLMs) have made querying databases more accessible, but cannot guarantee that the SQL they generate is correct. Without a trusted reference query, a validator (human or LLM) must decide whether a generated query answers the intended question. Enterprise questions often require queries with multiple joins, nested subqueries, and multi-level aggregation, and validating such a query in one judgment is error-prone. Decomposition simplifies this task by rewriting a query into smaller queries (blocks) that recompose to the original, each checked against its own sub-question. Decompositions differ, however: smaller blocks make each judgment easier but require more judgments, and the best balance depends on the validator's ability. We formulate validation-aware query decomposition as an optimization problem. Just as a query optimizer chooses among equivalent plans by estimated cost, we choose among decompositions by how reliably a given validator is expected to check them. We model how task difficulty and validator ability jointly affect reliability and define an objective that balances reliability against the number of judgments. Over a space of decompositions derived from logical-plan rewrites, our search finds an optimal one. We implement it in DecoVal, a pipeline that presents each block with its sub-question and input interface, combines local verdicts into a query-level decision, and localizes errors to blocks. A user study shows that decomposition helps human validators catch and locate errors: with DecoVal, participants caught 91% of the errors, up from 36% without decomposition, and located the error in nearly every rejection. Experiments on BEAVER and Spider 2.0 with LLM validators show that DecoVal also raises error-detection recall over whole-query validation while keeping precision high, and that the best granularity depends on the validator.

0.29
9

QuarkDB: A Hybrid Database System for Quantum Data Management

cs.DB cs.AR ·2026-11-16 ·Wenrui Zhang, Yu Wang, Xiao Zhang
Abstract · 14 pages, 12 figures, Submitted to ICDE2027

Emerging quantum applications like quantum communication generate large volumes of high-dimensional quantum data, requiring efficient data analysis and storage. However, classical database systems often struggle to meet requirements such as quantum processing or version management. This paper presents QuarkDB designed for efficient quantum data management. QuarkDB establishes a unified object model for relational and quantum data and defines the syntax of Quantum Structured Query Language. To support efficient quantum data management, QuarkDB integrates three key components: (1) a Hybrid Query Engine with cost-based hybrid plan selection over classical and quantum operators, (2) an Execution Engine with a three-level instructions intermediate representation, QuarkDB-IR, to support quantum execution and reduce quantum processing costs, and (3) a Storage Engine supporting quantum data version management, state reconstruction and data reuse. Compared with classical databases such as SQLite and PostgreSQL or quantum databases like Qute, our QuarkDB achieves query-latency speedups ranging from 2.14x to 25.86x speedup under extensive real-world workloads.

0.28
10

UniGraph: A Unified Graph-based Index for Dynamic Hybrid Dense-Sparse Vector Retrieval

cs.IR cs.DB ·2026-11-16 ·Keyu Chen, Xiaoyao Zhong, Jiabao Jin, Peng Cheng, Wangze Ni +2 more
published
Abstract · Under ICDE 2027 Review, 14 pages

Hybrid dense-sparse vector retrieval combines semantic signals from dense representations with lexical signals from sparse representations, typically ranking items by a query-dependent weighted sum of dense and sparse vector distances. Existing systems commonly search separate dense and sparse vector indexes and rerank the union of their candidates, incurring two retrieval passes and potentially discarding items that rank highly only after the semantic and lexical signals are combined. Constructing a graph-based index directly under a hybrid distance can mitigate this premature candidate loss. However, because varying the hybrid weight alters the underlying neighborhood relationships, a single static graph built at a fixed weight cannot accommodate dynamic query-specific weights. Therefore, we propose a Unified Hybrid Graph (UniGraph), which merges neighbor sets computed at multiple hybrid weights into a single bounded-degree graph index, enabling hybrid vector retrieval with different query-specific weights without index reconstruction. We further develop an adaptive weight-guided search framework that chooses between sparse- and dense-guided entry points according to the query weight, together with a dense-first hybrid distance pruning strategy that avoids unnecessary exact sparse distance computations. Extensive experiments show that UniGraph provides a favorable Recall-QPS trade-off across different query weights. In the mixed-weight setting, UniGraph delivers 27.6%~52.3% higher QPS than the fastest baseline on each dataset at Recall@100 greater than or equal to 0.95. UniGraph has been deployed at scale in Ant Group's production environment, where hybrid retrieval with query-dependent weights is in strong demand.

0.28
11

Growing Clusters Lower the Bar: Profile Accretion in LLM-Based Incremental Entity Resolution

cs.CL cs.DB ·2026-11-17 ·Huixue Han, Shangzhi Xu, Anqi Xiong, Yu-Chu Tian
unusual
Abstract

Incremental entity resolution pipelines ask a large language model (LLM) whether a new record belongs to an existing cluster and show it the records already linked. Analyses of matching oracles assume that the answer depends only on the records compared. For the LLM matchers we test, it depends on cluster size, and the model lowers its bar for joining a cluster as the cluster grows. On French procurement suppliers from FOPPA, with SIREN identifiers as ground truth, we hold the new record fixed and vary only the number of verified members shown. Sixteen members instead of one raise the false match rate on similarly named companies by \dfmrMin--\dfmrMax{} percentage points in six open-weight models, while their area under the ROC curve rises by only \aucGainMin--\aucGainMax. In Claude Sonnet~5 and Haiku~5.5 the rise is \clSonD{} and \clHaiD{} points. The shift persists with street addresses, prompt variants and the BatchER and ComEM formats, and one false merge raises acceptance of the intruder's other records in every open model. It does not arise on Czech and Bulgarian TED notices, where one record with its full address already identifies the company. In online linking on confusable blocks, a single threshold set on labelled data raises recall by a factor of \fxRRmin--\fxRRmax{} for five models with no detectable loss of precision and no extra LLM calls.

0.27
12

MoL-SQL: A Controlled Benchmark for Mixture-of-Language Text-to-SQL

cs.DB ·2026-11-17 ·Tianqi Luo, Boyan Li, Yuyu Luo
benchmark
Abstract

Text-to-SQL systems are usually built and evaluated under a monolingual assumption, yet in international applications users often query databases stored in a different language. Existing multilingual benchmarks mostly translate only the question without aligning schema and value entities, so they can neither locate the source of an accuracy drop nor rule out translation errors. Hence, we introduce MoL-SQL, a benchmark for mixture-of-language Text-to-SQL that switches the languages of the question, schema, and stored values independently while keeping each task fixed, and grades every cross-lingual entity mapping into four difficulty levels. We migrate five Text-to-SQL benchmarks of different domains and source languages through a unified alignment pipeline that builds a shared cross-lingual entity map, migrates each database with its constraints, rewrites the gold SQL under execution-equivalence checks, and regenerates the question from the verified SQL, keeping all language versions of a task aligned in entities, intent, and execution result. MoL-SQL provides two splits: MoL-Full (16,892 samples) for overall evaluation and MoL-Cube (3,840 samples) covering every language combination to isolate question, schema, and value effects. Experiments with eight LLMs and four families of Text-to-SQL methods show that schema and value languages have distinct effects, with stored values costing up to 23 points, and that these effects mainly stem from cross-lingual entity mapping. Neither question translation nor additional reasoning narrows the value gap, whereas access to target-database values substantially reduces it, indicating that mixture-of-language Text-to-SQL benefits most from language-aware context grounding.

0.25
13

Revisiting Index Performance under High Cache-Miss Penalties

cs.DB ·2026-11-16 ·Mathew M. Kim, Beomseok Nam
Abstract

Modern data-intensive applications often query very large datasets, making index performance critical. Recent index structures exploit the fine-grained access capabilities of emerging storage devices such as DCPMM and CXL. However, existing benchmarks typically evaluate indexes in isolation using saturated, closed-loop workloads that emphasize maximum throughput. Such workloads favor highly concurrent designs while overlooking the application work that follows an index lookup and competes for cache, memory bandwidth, and CPU resources. We present AuxBench - a microbenchmark that evaluates indexes as auxiliary access paths within larger application workloads. Using AuxBench, we evaluate four byte-addressable indexes under controlled post-lookup memory activity, concurrency, and request arrival patterns. Our experiments show that post-lookup memory activity can change the relative performance of competing indexes, that concurrency-oriented designs may lose their advantages when substantial application work is introduced, and that time-varying request arrivals can produce severe tail latency near saturation. These findings demonstrate why index-only benchmarks may not adequately predict performance in larger application workloads

0.23
14

A Gaussian Primitive Data Management Framework for Efficient 3DGS Trajectory Rendering

cs.DB cs.CVcs.GR ·2026-11-16 ·Haolun Ma, Ziyi Liu, Zizhuo Xu, Chuhan Hu, Lei Li
Abstract

Trajectory rendering, which renders novel views of a reconstructed 3D scene along a camera path, is a core operation in digital twins and autonomous inspection. Structured 3D Gaussian Splatting (3DGS) renders a single view in real time by decoding sparse anchors into Gaussians on demand, but it renders a trajectory view by view: every view projects all anchors to select them, re-decodes anchors already requested by neighboring views, and runs all steps on the GPU while the CPU idles. We treat this as a spatial data management problem, where anchors are spatial objects, views are range queries, and decoded Gaussians are shared derived data, and propose GDM-GS, which removes redundancy at three levels. Within a view, an anchor index and an occluder index answer each view as a holed-frustum range query, so out-of-view and provably hidden anchors are never decoded. Across views, shared materialization decodes each requested anchor once per group of consecutive views while preserving each view's selection. Across processors, a hybrid pipeline balances selections between the CPU and the GPU before grouped decoding under bounded memory. Experiments on large-scale public scenes show that GDM-GS substantially reduces trajectory rendering latency while preserving image quality.

0.20
15

Readie: Low-Latency Code Sandboxes for AI Agents

cs.AI cs.DBcs.SE ·2026-11-17 ·Arjun Sivaraman, Zhaoheng Li, Alan Shi, Sanjay Malisetty, Eugene Wu +1 more
Abstract

From quantitative research to personal assistance, AI agents act by iteratively generating and executing code. To decouple the agent harness from code execution, many agents offload execution to dedicated systems called code sandboxes. However, existing code sandboxes suffer from slow startup. Whether they rely on custom snapshots or a single fat image, the root cause is the same: it is hard to build a compact, pre-warmed snapshot that can be shared across diverse agent-generated code while covering nearly all the artifacts (e.g., packages, datasets) it requires. In this work, we propose learned startup snapshots for low-latency code sandboxes. Our insight is that while it is hard for a single snapshot to be both compact and cover most workloads, a set of snapshots can achieve both. Each snapshot is small, initializes quickly, and covers a fraction of agent-generated code; together, the set covers most of it. We learn this set from a large training workload by formulating snapshot construction as an optimization problem and solving it with an approximation algorithm. Planned on 15K public and LLM-synthesized scripts, our system, Readie, reduces startup latency by 3-22$\times$ and end-to-end runtime by 1.3-3.3$\times$ compared to existing approaches at the same storage budget.

0.16
16

Adaptive-Elbow Graph Traversal for Schema Retrieval in Text-to-SQL

cs.DB cs.IR ·2026-11-16 ·Fabio Picariello, Salvatore Cipolla, Susanna Bonura, Vito Morreale
Abstract · Presented at the 5th Italian Conference on Big Data and Data Science (ITADATA 2026). To appear in CEUR Workshop Proceedings

LLM-based natural-language interfaces to relational databases are gated by a schema-retrieval step: the generator can only be as good as the slice of schema it is shown. On a database with hundreds of tables, that slice must be selected and the selection is two-sided---omit a needed table and the query becomes unrecoverable, include too many and the irrelevant ones act as noise that degrades the model's output. When an agentic retriever that lets the model inspect the schema can be too costly or too slow, the fallback is an embedder that ranks tables by cosine similarity and keeps a top-k. This fallback has two weaknesses: a fixed budget is suboptimal question by question, and embedding similarity overlooks foreign-key-linked tables that are necessary for joins. We present Adaptive-Elbow Graph Traversal (AEGT, ElbowHop for short), a property-graph table retriever that addresses both: an adaptive elbow cutoff replaces the fixed budget with a per-question one under a single aggressiveness parameter, and bidirectional foreign-key traversal deterministically recovers the bridge tables embedding similarity misses. We evaluate the retriever on 3 corpora of increasing candidate-pool size (BIRD Mini-Dev queried per database, 3--13 tables; its eleven schemas merged, 74; and a merged Spider-train graph, 546) and isolate the two mechanisms under a per-question budget-matched protocol. Across these settings the adaptive elbow emerges as the dominant mechanism---at matched recall it roughly doubles precision over a fixed budget on the larger pools, the margin widening as the pool grows---while the foreign-key traversal pays off on the join-critical bridge tables dense retrieval cannot reach, in the single-hop tight-budget case. We characterize the method as a low-cost, recall-robust first stage for schema retrieval on which a downstream selection or generation step can build.

0.15
17

STORMGUIDE-FL: Stochastic Remote Guidance for Efficient Mining of Federated Streaming Data

cs.LG cs.DBcs.DC ·2026-11-16 ·Manuel Röder, Frank-Michael Schleif
Abstract · 21 pages, 7 figures, 4 tables

Federated Learning enables collaborative model training across distributed edge devices ("clients") while preserving data privacy. However, real-world deployments involve clients that observe continuous data streams from evolving environments while operating under strict resource limitations. Existing solutions still face two major challenges: local concept drift, where each client's data distribution shifts over time, and global client drift, arising from asynchronous engagement and imbalanced contributions across heterogeneous training participants, formally described as dual client heterogeneity. We propose STORMGUIDE-FL, a federated optimization and data-mining framework that mitigates both types of drift using a server-guided pipeline for data acquisition and local training. For data acquisition, a lightweight client-side sampling strategy incrementally selects informative and diverse instances from non-stationary, non-IID local streams under bounded memory, compute, and labeling budget. For local training, the server's remote guidance is embedded directly into local optimization as an update-level correction, counteracting client drift without discarding scarce labeled samples. We empirically verify the effectiveness of the proposed sampling strategy on federated data streams across gradual, sudden, and recurring concept drift, and demonstrate that its gains compound with the update-level drift correction. Experimental results further show improved speed and robustness of global model convergence under resource-constrained, heterogeneous conditions.

0.11