AI News Archive: July 6, 2026 — Part 10
Sourced from 500+ daily AI sources, scored by relevance.
- Agent Data Injection Attacks are Realistic Threats to AI Agents
AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security has primarily focused on indirect prompt injection (IPI). Its most well-studied category is instruction injection, where attacker-controlled untrusted d...
- From Multiplicity to Vulnerability: Privacy Amplification Risk from One-Dataset-Multiple-Model Exposure
To efficiently exploit a valuable data source (e.g., facial or medical images), it is frequently harnessed to fulfill multiple learning objectives (e.g., facial recognition, age estimation, and race classification). Each trained model is then deployed as an independent API service for corresponding ...
- Look-Ahead-Freedom as Temporal Non-Interference: A Verifiable Correctness Property for Backtesting and Agentic Trading Pipelines
Look-ahead bias (using information from after a decision epoch to make the decision at that epoch) is the dominant way a backtest or a machine-learning evaluation flatters a system that will disappoint in deployment. The field manages it with construct-specific recipes and empirical detectors, which...
- Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers
Fully homomorphic encryption (FHE) enables computation on encrypted data, but practical encrypted Transformer inference is bottlenecked by the sequential composition of many nonlinear blocks. We study whether Structured Newton Layer Parallelism (SNLP) can make this inter-layer composition more FHE-f...
- Towards Personalized Differentially Private Learning for Decentralized Local Graphs
Graph-structured data is increasingly generated and stored in decentralized environments, such as social platforms, mobile applications, and edge networks, where users maintain control over their local graph data. However, collecting and analyzing such decentralized graph data for downstream learnin...
- F-ACVAE: A Federated Adaptive Conditional Variational Auto-Encoder for Privacy-Preserving Intrusion Detection in IoT Networks
The rapid proliferation of Internet of things (IoT) devices has significantly expanded the cyber-attack surface, necessitating robust and privacy-preserving intrusion detection systems (IDS). However, centralized learning approaches often suffer from severe performance degradation due to high-dimens...
- Governed Caste Reassignment in Heterogeneous Swarms: An Asymmetric-Trust Protocol with Audited Operator Countersignature
In heterogeneous robot swarms, caste reassignment (rebinding a robot to a new capability-bound role) is a high-frequency runtime event driven by battery, payload, and priority changes. Existing approaches treat it as an internal allocation algorithm and do not expose the reassignment to external aut...
- Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority
Autonomous agents are moving from sandboxed text generators to operators of code, data, and physical infrastructure, and they increasingly learn while deployed. This reopens a question that alignment techniques answer only probabilistically: after an agent has adapted in the field, is the running sy...
- Is Three the Magic Number? An Empirical Evaluation of LLM-Based Repair Loops
Iterative repair loops have become a core design pattern in LLM-based software engineering systems. These workflows repeatedly generate, validate, and repair artifacts using feedback such as compiler errors or test failures. Despite their widespread use, the impact of repair-loop iteration limits re...
- Latent Programming Horizons in Coding Agents
A coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests, yet little is known about what the underlying language model internally represents about the program it is working on. We show that the residual streams of language models under codi...
- On the risk of coding before testing: An empirical study on LLM-based test generation workflow
Large Language Models (LLMs) are increasingly used in software engineering workflows to generate both source code and test suites. This dual capability has enabled emerging development paradigms, including test-first and agentic workflows, where a single model is producing and validating implementat...
- From Failing to Passing: Evolving Natural Language Prompt Optimization Rules for LLM Code Generation
Large language models are known to be sensitive to prompt formulation. Even minor variations in wording can substantially degrade performance. This sensitivity reveals an opportunity: if prompt phrasing can harm performance, can it be used to improve it? To investigate this question, we introduce a ...
- LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review
Large language models (LLMs) are increasingly used to produce test oracles, the part of a test that decides whether observed behavior is correct. Yet a clear account of where these oracles draw their authority is missing. Prior secondary studies organize the area by oracle form or by LLM technique. ...
- A Comprehensive Study of Implementation Bugs in Multi-modal Agents
Multi-Modal Agents (M-agents), empowered by Large Language Models (LLMs), excel in various complex, open-world scenarios such as autonomous driving and robotics. However, their unique requirements to interact with dynamic and diverse multi-modal environments introduce novel implementation challenges...
- Real-World Perturbation Testing of Autonomous Driving Systems
Autonomous Driving Systems (ADS) must operate reliably under diverse conditions, yet representative data for rare or adverse scenarios is difficult to obtain. Perturbation-based testing is widely used to assess robustness, but most studies focus on offline datasets or simulation, leaving open questi...
- Teaching LLMs a Low-Resource Language: Enhancing Code Completion in Pharo
Large Language Models (LLMs) unlocked new possibilities in automated code writing, becoming the backbone of most code completion tools. While LLMs excel in mainstream languages, they often lack support for the so-called low-resource languages where training data is scarce. As a result, these languag...
- E-CoDrive: A Co-Simulation Framework for Testing Energy-Critical Driving Scenarios
Autonomous driving research has largely focused on safety while giving limited attention to non-functional aspects such as energy consumption and sustainability. As Autonomous Electric Vehicles (AEVs) become increasingly common in urban traffic, understanding how complex traffic dynamics influence t...
- Cam2Sim: Neural Scenario Reconstruction for Closed-Loop Autonomous Driving Simulation
Simulation-based testing enables safe and repeatable evaluation of autonomous driving systems, but its effectiveness is limited by the gap between synthetic simulator outputs and real-world camera observations. To address this problem, we present Cam2Sim, a tool that transforms real-world driving re...
- Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards
Automatic data visualization generation has advanced rapidly with multi-modal large language models, yet existing efforts largely focus on static charts and overlook the interactive dashboards commonly used for real-world data exploration. We introduce Dashboard2Code, a novel task that requires a mo...
- ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents
Tool calling is central to modern language model agents, but aggregate benchmark scores often hide where tool use fails. A model that never calls a needed tool and a model that calls the tool but ignores the result can look similar under final task accuracy. We introduce ToolFailBench, a diagnostic ...
- Can LLMs Really Recover Microservice Failures? A Recovery-Aware Evaluation of Diagnosis-to-Action Reasoning
Large language models (LLMs) are increasingly used to interpret operational evidence and assist incident response in cloud-native microservice systems. However, recovery-oriented use cases require more than identifying a root cause. After observing symptoms and diagnosing a fault, an operator or age...
- Finetuning Lightweight LLMs for Control Flow Graph Generation
Control Flow Graph (CFG) is an important program representations for software analysis, code understanding, and software maintenance. Traditional CFG generation techniques mainly rely on bytecode or abstract syntax trees. However, these approaches usually require complete, compilable, and syntax err...
- LLM-Driven CI-CD Workflow Intelligence for Cyber Systems Engineering
CI/CD workflows have become executable operational policy: they decide what gets built, tested, released, and deployed, and they mediate how maintainers interact with delivery infrastructure. That makes them an important measurement point for cyber-systems engineering. Recent large language model (L...
- Three-Phase Evaluation of AI-Assisted Software Development Life Cycle
This paper presents an exploratory evaluation of how increasing levels of AI autonomy affect software development productivity, requirement adherence, and developer cognitive workload. A team of four developers reimplemented the same full-stack web application across three sequential phases: partial...
- When AI Is Wrong on Purpose: How Students Respond to Buggy GenAI Code
As Generative AI (GenAI) becomes increasingly central to software development, CS education is integrating prompt-centered workflows where students describe intended program behavior in natural language to elicit code. However, professional practice requires careful review and verification of GenAI-...
- Using Process Mining to Generate AI Agents from Software Engineering Process Records
Integrating AI agents into Software Engineering (SE) raises an important challenge: how can we specify and realize AI agents that work effectively alongside humans in hybrid SE teams? Determining the right granularity and separation of concerns for such agents is non-trivial. Coarse-grained agents m...
- A Temporal Reasoning Benchmarking Framework for LRMs via Difficulty-controlled and Dynamic Test Generation
Defining the reasoning boundaries and ensuring the reliability of Large Reasoning Models (LRMs) remains a critical challenge. Current benchmarks primarily rely on static datasets susceptible to data contamination or synthetic tasks lacking fine-grained difficulty control. Furthermore, standard outco...
- AI Agent Pull Requests on GitHub: Frequency, Structure, and Merge Conflict Rates
AI coding agents can create and submit pull requests (PRs) to a common repository at the same time; however, there is little research on the frequency of such concurrent submissions or the cost associated with them. In this study, we use the AIDev-pop dataset (33,596 PRs across 2,807 repositories) t...
- Correctness, confidence, and context: Framing software assurance in the AI age
Software engineering has a complicated relationship with "correctness". We recognize the challenges of full formal rigor as well as many required properties beyond functional correctness. Although we satisfice in practice, we are still stuck in the mindset that we could reason our way to correctness...
- Unified Audio Intelligence Without Regressing on Text Intelligence
Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM. Audex adopts a simple unified design with a sing...
- SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech. However, standard speech and text benchmarks do not capture whether these systems behave naturally in conversations, where timing, turn-taking, prosody, interpersonal stance, language and dialect ...
- ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions
Speaker embeddings, or x-vectors, are widely used to represent speaker identity and speaker-related attributes, but existing embedding extractors are typically descriptive rather than generative: they map an observed speech segment to an x-vector, which is then used for downstream applications. We i...
- Towards Language-Agnostic Speech Inversion
Characteristic timing patterns are reflected in the acoustic speech signal, encompassing both vocal tract configuration and acoustic excitation. Previous studies have demonstrated that speech inversion (SI) systems can recover these timing patterns from speech, including oral tract variables (tongue...
- DuplexChat: Constructing Speaker-Separated Full-Duplex Dialogue Speech at Scale for Spoken Dialogue Language Modeling
Full-duplex spoken dialogue models are trained on conversational speech in which each speaker is represented as a separate stream, but existing large-scale public speech corpora are mostly monaural, making them unsuited for SDLM training. We present DuplexChat, an open-source corpus for full-duplex ...
- Ranking the Impact of Contextual Specialization in Neural Speech Enhancement
We systematically investigate neural speech enhancement systems, ranging from very small ($\sim$10\,k parameters) to medium-large ($\sim$2-5\,M parameters), which specialize to acoustic conditions using contextual information such as speaker identity, noise type, speaker gender, spoken language, and...
- Curated retrieval versus open web search in public AI information services: a coverage-trust trade-off
Public institutions increasingly use large language models (LLMs) to answer citizens' questions, often pairing a curated knowledge base with live web search, yet whether the sources behind these answers can be trusted has received little empirical scrutiny. We report a pre-launch expert evaluation o...
- Progressive Disclosure for LLM-Maintained Wiki Knowledge Bases: a Preregistered Ablation
LLM agents increasingly answer questions against knowledge bases they help maintain. A common intuition holds that progressive disclosure, a compact catalog plus a one-line summary per page so the agent loads only what it needs, should make this cheaper than consulting a large monolithic index. We t...
- CanniUplift: A Holistic Framework for Mitigating Seller and Incentive Cannibalization in E-commerce Uplift Modeling
Personalized incentive allocation is vital for e-commerce, where uplift modeling is the standard for estimating Individual Treatment Effects (ITE). However, traditional models often fail in complex multi-seller environments with violations of the Stable Unit Treatment Value Assumption (SUTVA). We id...
- Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval
Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interaction, but dense image-side tokens make storage and scoring expensive. Existing token compression methods reduce this cost, yet they can remove or collapse object- and region-level evi...
- SpliSync: Genomic language model-driven splice site correction of long RNA sequencing reads
Long RNA sequencing reads are rapidly replacing short reads in transcriptomic analyses, enabling full-length transcript sequencing and better identification of isoforms, alternative splicing events, and other transcript variants. However, their higher sequencing error rates can cause misalignments, especially at splice junctions, reducing the accuracy of transcript reconstruction and analysis. We developed SpliSync, a genomic language model-driven method for splice site correction that integrates a pre-trained genomic sequence model (HyenaDNA), alignment data, and a U-net architecture to predict splice sites at nucleotide resolution. SpliSync substantially improved the precision of RNA long-read alignments by 27%-194% across diverse datasets and consistently outperformed competing tools. As a preprocessing step, it increased alternative splicing detection accuracy by 26%-330%. In contrast, its benefit for transcript reconstruction was limited, likely due to the tools' built-in correction mechanisms. The code, developed in Python using the PyTorch package, is freely available at https://github.com/splicebox/SpliSync.
- Accurate ΔTm Prediction Without Protein Structure Inputs for Biomolecular Stability
Predicting protein stability, like changes in melting temperature ({Delta}Tm) caused by mutations, is a critical task in therapeutic protein engineering and drug discovery. This is reflected by a growing solution space, including both AI-based sequence and structure based methods. This paper demonstrates that accurate {Delta}Tm prediction does not require structural input features, but can achieve state-of-the-art results with a careful training design for large sequence-based protein language models. We combine an autoresearch-inspired setup search with controlled ablation studies and show that a well-tuned sequence-only ESM2-650M model outperforms structure-informed methods in our benchmark, achieving the lowest error (MAE/RMSE) and competitive Pearson correlation without pH or structural inputs. We further show that choices such as loss function, pooling strategy, auxiliary supervision, and fine-tuning regime materially affect performance.
- Benchmarking AlphaFold and related deep learning approaches for modeling antibody and TCR antigen recognition
Determining the structural basis of antigen recognition by antibodies and T cell receptors (TCRs) provides critical insights into effective immune targeting and can inform design of biotherapeutics and vaccines. Accurate computational modeling of antibodies and TCRs in complex with their targets poses a major challenge for predictive methods, including AlphaFold, which is generally accurate for modeling protein complexes but has shown limited success for immune recognition. In this study we assessed the performance of AlphaFold2, AlphaFold3, increased sampling protocols, and related deep learning methods for modeling antibody-protein, antibody-peptide, and TCR-peptide-major histocompatibility complex (pMHC) recognition. We show that increased sampling and AlphaFold3 generally improve performance relative to default sampling and AlphaFold2, however predictive accuracy and improvement levels varied considerably among interface classes, with antibody-peptide complexes representing a challenge despite their small antigen size. Comparing per-case success across methods showed some complementarity, indicating opportunities for increased success through model pooling approaches, for instance increasing antibody-peptide near-native success from 41% to 59%. Analysis of AlphaFold confidence scores and modeling of a noncanonical complex provided further insights into predictive performance. These results highlight considerations for predictive antibody and TCR complex modeling efforts, while revealing key distinctions among protocols, scoring, and immune complex classes.
- Multimodal temporal mapping of macrophage transcriptome remodeling during Salmonella infection
Macrophages are equipped to eliminate invading pathogens, yet several intracellular bacteria exploit them as replicative niches. Salmonella enterica serovar Typhimurium subverts host immunity by injecting effector proteins that remodel macrophage functions. While macrophages typically induce a pro-inflammatory program upon bacterial invasion, Salmonella can redirect them toward an anti-inflammatory and replication-permissive state via manipulation of the NFkB and STAT3 host transcription factors. How the integration of the effects on these two transcription factors and potentially others underpins this reprogramming remains poorly charted. Here, we use a multipronged approach combining a bacterial reporter, temporal single-cell RNA-seq with RNA metabolic labeling, transcription factor (TF) footprinting, and single-cell CRISPR perturbations to dissect macrophage polarization dynamics during early infection. We catch the bifurcation during infection, where a subset of macrophages transition toward the anti-inflammatory phenotype. This shift involves the activation of Salmonella pathogenicity island 2 (SPI2) leading to both the dampening of the initial NFkB-driven inflammatory program and the induction of specific transcriptional modules beyond NFkB and STAT3, with possible contributions from AP-1 and Maf family members. Together, our study uncovers host decision points in macrophage polarization circuitry and reveals a vulnerability exploited by Salmonella to modulate host immunity.
- Actors' Facial Movement Magnitude and Cardiac Dynamics Predict Observers' Emotion Believability Ratings
In non-verbal communication, observers infer emotions from visible facial movements, yet emotional experiences are described in internal bodily terms (e.g., "my heart skipped a beat"). This contrast highlights a tension between external sensory cues and internal signals. In this context, we examined an overlooked gap in affective science: what makes an emotional portrayal believable, and do believability judgments reflect only what observers can see or also the portraying person's internal cardiac dynamics? To test this, we created 311 scenario-driven acting clips designed to avoid prototypical posed displays. For each clip, we quantified facial movement magnitude from the video, recorded ECG during preparation and enactment, and collected actors' self-reports. Online participants (N = 371) viewed these clips and provided emotion recognition responses and continuous ratings of believability, valence, or arousal. The results show that believability decreased as movement magnitude increased, with a non-linear relationship indicating a stronger penalty as motion increased. Valence further shaped this pattern, with increasing movement reducing believability more strongly for portrayals with negative valence. This effect persisted after accounting for intended emotion, perceived arousal, and emotion recognizability. Cardiac dynamics varied during performance, and actors' higher heart rate variability was associated with higher believability for positively valenced portrayals. Together, these findings show that believability is driven by visible movement cues interpreted in relation to valence, with actors' cardiac dynamics showing selective alignment with believability. These results identify core components of believable emotional expressions and provide a basis for studying such judgments in everyday social interaction.
- Solvation Shapes the Conformational Landscape of a Therapeutically Relevant SMN2 Splice-Site Defect
The SMN2 exon 7 5' splice-site/U1 snRNA duplex contains an A$_{-1}$ bulge that weakens splice-site recognition and represents a therapeutically relevant RNA connectivity defect, yet its conformational landscape and coupling to solvation remain poorly understood. Here, we performed enhanced-sampling Hamiltonian replica-exchange molecular dynamics simulations of the SMN2 splice-site duplex using four explicit-solvent models (OPC, TIP4P-Ew, TIP3P, and SPC/E) and characterized the sampled ensemble using linear and machine-learned latent representations. Across representations, the A$_{-1}$ defect consistently populated three metastable conformational states distinguished by local duplex geometry, base stacking, hydrogen-bonding patterns, and solvent exposure. The relative populations of these states, together with first-shell hydration and Na$^+$ distributions around the defect, varied substantially across water models, demonstrating that hydration and ion organization actively shape the equilibrium between locally accommodated and solvent-exposed conformations of the SMN2 splice-site bulge. Our results shed light on the conformational components of this therapeutic RNA target and highlight the impact of solvation model as an important consideration for molecular simulations of RNA splice-site recognition and small-molecule repair.
- There is no convincing evidence that Methylobacterium extorquens AM1 can produce N-deoxyschizokinen A
It was recently reported that Methylobacterium extorquens AM1 produces the citrate-hydroxamate siderophore N-deoxyschizokinen A, identified by LC-HRMS. Multiple properties were inconsistent with the assignment: the feature eluted far later than the other schizokinen derivatives (17 min versus 6-8 min), a reversed-phase shift larger than a single-hydroxyl difference in a molecule can explain, further its accurate mass deviated from the calculated one by 28 ppm, well outside the error on the co-analyzed standards and its diagnostic m/z 105 and 77 fragments suggest a molecule with an aromatic moiety. A replicate comparison of identical samples in plastic versus glass autosampler vials was decisive: the m/z 387 feature was reproducibly present with plastic vials and absent with glass. We therefore conclude that the reported detection of N-deoxyschizokinen A in M. extorquens AM1 is an artifact, and recommend glass-vial and solvent-blank controls, an explicit accurate-mass threshold, and narrow MS/MS isolation when assigning trace siderophore-like features from complex extracts.
- Solvent-buffer effects in molecular dynamics simulations of nucleic acids
Molecular dynamics simulations of nucleic acids are performed using a solvent-buffer distance of 10 [A] between the solute surface and the simulation box boundary. Although this cell size has been extensively explored in protein simulations, its implications for nucleic acid dynamics are not well understood. Nucleic acids are elongated, highly charged, and flexible structures with hydration and dynamical properties distinct from those of proteins and therefore, they may require different solvent-layer considerations in simulations. In this study, we investigated the effect of simulation cell size on nucleic acid dynamics by simulating a 30-base-pair double-helical nucleic acid structure and its two single-stranded forms using solvent-buffer distances of 3, 5, 10, 15, and 20 [A]. Smaller cells may impose restricted hydration, molecular crowding, and periodic image interactions. However, larger cells provide solvent space for conformational relaxation. A total of 45 s of molecular dynamics simulations were performed (3 structures x 5 cell sizes x 3 replicates x 1 s). Our results show that while the commonly used 10 [A] buffer may be sufficient to maintain the stability of the double-stranded nucleic acid, larger cells are required to capture the conformational dynamics of single-stranded structures. In both, increasing the cell size to 15 or 20 [A] enables broader conformational sampling. The first hydration shell exhibits reduced crowding in the 20 [A] cell, consistent with more relaxed conformations. At larger cell sizes, single-stranded nucleic acids adopt compact, self-associated conformations for stability. Together, this study presents physical insight into how simulation cell size and solvent environment influence nucleic acid dynamics.
- Integrated analysis of ribosomal DNA copy number and methylation using nanopore long-read sequencing
Ribosomal RNA (rRNA) provides the structural and catalytic core of ribosomes and is encoded by ribosomal RNA genes (rDNA) arranged in tandem repeat arrays. rDNA copy number (CN) is highly dynamic, representing a clinically relevant form of structural variation, but its accurate quantification has been challenging due to its highly repetitive and GC-rich nature. Here, we present RICO (Ribosomal DNA Integrated Copy Number and Methylation Analysis), a novel computational pipeline for integrated estimation of rDNA CN and methylation using nanopore long-read sequencing. RICO leverages long sequencing reads that span entire rDNA repeats, mapped to an rDNA-augmented reference genome, and normalizes coverage using an array of single-copy genes. We show that RICO provides accurate rDNA CN estimates in simulated datasets and reproducible measurements across human samples, with strong agreement to short-read sequencing and PCR-based methods. As biological validation, RICO detects a ~40% reduction in rDNA CN in Atrx-knockout mouse cells, consistent with established effects of ATRX loss on rDNA CN, and captures detected increased total and active rDNA CN in malignant cells from a MYC-driven B-cell lymphoma mouse model, in line with prior psoralen-based chromatin studies. Applying RICO to independent human cohorts, we uncover that individuals with higher total rDNA CN consistently exhibited higher fractions of high-methylated rDNA copies, suggesting a dosage compensation mechanism that potentially maintains a similar number of active rDNA copies across individuals. Together, RICO enables integrated analysis of rDNA CN and methylation state, providing a scalable framework for investigating rDNA regulation across population and disease studies.
- FORGE reveals an information spectrum encoded in RNA tertiary-structure geometry
Coarse RNA coordinate representations are increasingly used for inverse folding and structural annotation, but the biological information encoded in such representations is not well quantified. We introduce FORGE (Feature-engineered RNA Geometry Evaluation), a feature-engineering framework that extracts 935 interpretable descriptors from six backbone atoms and one glycosidic-anchor atom per residue. In a temporal test on 4,135 post-2025 PDB RNA chains, FORGE recovered 64.6% of native nucleotides; a six-atom control without the glycosidic nitrogen retained 58.5%, and abstaining from the least-confident half of calibration positions retained 94.4% accuracy. The same representation predicted base-pair state (79.2% accuracy), a RibonanzaNet-inferred DMS reactivity proxy ($R^2=0.329$) and protein-proximal context (AUC approximately 0.67). Native-decoy, OpenKnot and solved AI-designed pseudoknot tests further show that nucleotide identifiability, foldability and design score are distinct objectives. FORGE provides a reproducible audit layer for RNA structural interpretation.
- Scop3P in 2026: an expanded proteomics-informed resource contextualizing phosphorylation sites through sequence, structure, mutation, and experimental provenance
Protein phosphorylation is a central regulatory mechanism controlling protein activity, interactions, and cellular signalling, and its dysregulation is implicated in numerous diseases. Advances in mass spectrometry--based phosphoproteomics have led to a rapid expansion in the number of reported phosphorylation sites; however, interpretation of these data remains challenging due to fragmented evidence, limited structural context, and the lack of uniform experimental provenance across resources. Interpretation is further complicated by the fact that the biological meaning of reported phosphosites can vary substantially across tissues, cell lines, perturbations, and disease settings. Here, we present a major update of Scop3P, a proteomics-informed knowledgebase that contextualizes human phosphorylation sites within integrated sequence, structural, biophysical, evolutionary, and mutational frameworks. The current release incorporates uniformly reprocessed human phosphoproteomics data from 116 PRIDE datasets alongside curated UniProt annotations, retaining peptide-spectrum matches, site localization confidence, and direct links to primary mass spectrometry evidence via Universal Spectrum Identifiers. This integration yields 152,350 unique serine, threonine, and tyrosine phosphorylation sites across 16,533 human proteins, supported by full experimental provenance. Beyond site identification, Scop3P provides residue-level contextual annotations derived from experimentally determined protein structures and proteome-wide AlphaFold models, enabling near-complete structural coverage of phosphorylation sites. Structural context is further complemented by residue-level biophysical, evolutionary, and mutational annotations, supporting integrated assessment of phosphorylation in functional and disease-related settings. The current release also introduces residue interaction network representations derived from AlphaFold-predicted structures, capturing spatial connectivity and local interaction environments of phosphorylation and mutation sites. A redesigned web interface enables interactive exploration through coordinated 1D, 2D, 2.5D, and 3D visualizations, peptide-level coverage views, and direct access to original spectra via PRIDE. By bridging experimental phosphoproteomics with structural, functional, and disease-related context, Scop3P provides a scalable and provenance-aware resource for phosphosite interpretation, hypothesis generation, and data-driven modelling of phosphorylation-dependent regulation.