arXiv subjects

Chris North

Publications and source records attributed to Chris North.

At least 19 recordsLinked to original sources

arXiv2026

CanvasObs: Structured Spatial Observation for Agent Editing on 2D Infinite Canvases

Editing agents on 2D infinite canvases must reason about application state that pixels may not reveal. Targets may be offscreen or covered, while visual containment and touching arrows may disagree with recorded frame membership or connector bindings. We ask how a structured observation layer can support accurate object selection during agentic editing on 2D infinite canvases. We present CanvasObs, which augments visual context with a structured payload and guidance for reading four components: Identity & State, Visibility & Structure, Relations, and Offscreen Object bounds in action coordinates. A Remote Team Handoff case study illustrates retrieving an editable offscreen copy, choosing a covered chart by color, separating cards by frame membership, and preserving an evidence connection. We turn these cases into ten controlled configurations and compare CanvasObs with the baseline agent in 1,200 browser trials across three models. CanvasObs improves Correct target for every model. Combined across models, it raises Correct target from 16.5% to 48.3%, an increase of 31.8 percentage points (95% confidence interval [29.0, 34.7]), and Full task success from 4.3% to 25.0%. These results show that compact structured observation can improve object choice on 2D infinite canvases without redesigning the editing pipeline.

cs.HC↗

arXiv2026

Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution

Supervised fine-tuning (SFT) adapts pretrained large language models (LLMs) to downstream tasks, but the required concepts can receive substantially different levels of pretrained support. Frequent concepts are more likely to be well learned, whereas rare concepts may remain weakly represented. We introduce a novel notion named prior barrier to quantify how strongly the pretrained model supports competing concepts over the target concept. We observe that prior barriers follow a long-tail distribution, placing head and tail concepts at different starting points for SFT: head concepts face lower prior barriers, whereas tail concepts require additional instructions to overcome their higher prior barriers. Our theoretical analysis further derives a predictive risk bound for SFT under long-tail prior barriers, explicitly characterizing how the prior barrier and accumulated SFT evidence jointly determine predictive performance. Motivated by this prior barrier-dependent demand, we propose PASS, an adaptive SFT instruction selection method that constructs reference-derived concepts and estimates the distinguishing evidence provided by each instruction, and adaptively allocates the selection budget toward concepts that remain insufficiently covered under the current selection. In this way, PASS jointly considers which instructions can provide useful evidence and where additional supervision is needed under a limited budget. Experiments show that our method consistently outperforms seven state-of-the-art instruction selection methods on four backbone-budget settings. An ablation study further shows that PASS's adaptive allocation consistently improves over uniform allocation.

cs.AI↗

arXiv2026

Automating the Application of HCI Principles: Skills for On-Demand UI Construction, the Human-AI Space to Think, and the Future of HCI

Human-computer interaction (HCI) is in the middle of a transition: large language models can now generate functional user interfaces (UIs) on demand from natural-language task descriptions. A user explains what they are trying to accomplish, and the system materializes a working interface to support it. This capability already exists in systems such as Claude and ChatGPT and continues to grow in fidelity as the underlying models improve. The next step along this trajectory is to move from interfaces that are merely generated to interfaces that are generated well. We propose a framework in which the dialogue between user and artificial intelligence (AI) becomes a Space to Think: a shared, structured cognitive workspace in which task decomposition produces an on-demand user interface as an extension of the user's thinking rather than as a separate artifact. Within this paradigm, classical HCI design knowledge (Nielsen's heuristics, Norman's affordance prescriptions, Web Content Accessibility Guidelines (WCAG) success criteria, cognitive-load constraints, and mixed-initiative principles) is encoded as skills: machine-readable skill.md files that the generating agent loads at runtime as software engineering tools. Skills turn HCI design knowledge into declarative, inspectable, version-controlled, and editable artifacts owned by the HCI community itself so that accessibility, learnability, and consistency become properties of a generative process rather than properties of a finished product. We outline a research agenda depicting a future where the HCI field transitions from today's design and knowledge heuristic checklist towards a future where the craft becomes machine-readable, executable, and open.

cs.HC↗

arXiv2026

Connectedness, Cognitive Load, and Human-AI Oversight in Cyber Operations

AI-assisted cyber situational awareness triggers machine-generated reasoning traces (step-by-step justifications for anomaly classifications) that a human operator is expected to review. Because cyber signals and their traces arrive faster than any operator can process, human review is the limiting constraint on oversight. The standard approach is to identify the riskiest cyber events for review using model-side signals such as confidence or uncertainty. That framing ignores the operator's cognitive capacity which varies sharply with the operational environment. We propose an alternative where the system's environmental and connectivity telemetry serves as an available, non-invasive proxy for operator load. That same telemetry determines whether the human-AI partnership can reach the broader collective for support. In a maritime platform, environmental and connectivity attributes including depth, number of active communications paths, density of the tracked contact picture, and operational tempo all carry this signal. Need for operator oversight becomes a decision that materializes as a combination of both risk and environment-derived operator capacity. We present a reference architecture for a connectedness-aware oversight engine, demonstrating everyday use cases alongside its intended incorporation into the submarine cyber-defense toolkit. Two themes emerge: 1) the operator's environmental state is itself a connectedness measurement, and 2) connectedness drives the cognitive load and defines a collective boundary in human-AI cyber operations.

cs.HC↗

arXiv2026

Spatial Visual Analytics for Multi-Document Summary Verification

Large language models increasingly generate summaries from collections of documents to support sensemaking and reporting, but verifying whether summary statements are grounded in source materials remains difficult. In multi-document summarization (MDS), evidence is distributed across many source documents and may be incomplete, conflicting, or missing. We present Summary Verification Space (SVS), a visual analytics system for verifying multi-document summaries through spatial document organization and coordinated provenance visualization. To support scalable verification, we investigate two alternative 2D canvas layouts: a SUMMARY-GUIDED layout that organizes documents by alignment with summary sentences, and a SOURCE-GUIDED layout that arranges documents by semantic similarity. Coordinated provenance visualization then makes relationships among summary content, source documents, and supporting evidence explicit, enabling users to trace support, contradiction, and missing evidence during verification. A task-driven usage scenario illustrates an auditing workflow in which users use the layouts to locate relevant documents and coverage gaps, then inspect linked claims and source evidence to make their own grounding judgments. In a comparative study with provenance held constant, both spatial layouts improved aggregate accuracy and reduced workload relative to a linear baseline, with the clearest gains on relevance tasks. The SUMMARY-GUIDED layout provides the strongest overall balance of accuracy, efficiency, confidence, and workload.

cs.HC↗

arXiv2026

Scalable Semantic Steering of Embedding Projections

Low-dimensional projections support interactive visual analysis of high-dimensional data embeddings, but their structure often does not align with analyst-defined semantic relationships. Recent LLM-augmented semantic steering methods address this gap by externalizing analyst intent from user-defined groups of seed examples, but they propagate intent through per-item LLM reasoning, causing LLM calls and cost to grow linearly with collection size. We propose a scalable semantic steering method that shifts semantic computation from individual items to user-defined groups. A single LLM call generates structured profiles for all groups, which are embedded and combined with seed centroids to form hybrid semantic prototypes. The method then propagates intent without retraining, using embedding-space soft assignment, abstention, and alignment-scaled updates before reprojection. On a 5K-document LitCovid corpus, our method achieves global alignment comparable to per-item LLM steering while reducing LLM calls by over three orders of magnitude. An image case study shows that the same prototype-based mechanism extends to multimodal embeddings. These results suggest that group-level representations can make semantic steering more practical for larger embedding collections.

cs.HC↗

arXiv2026

Drag, Infer, Reproject: Grounding LLMs through Spatial Interaction for Image Clustering

Dimension reduction and semantic interaction support image clustering by making similarity structure visible and manipulable. Existing semantic interaction methods encode users' clustering criterion (a user-interpretable semantic dimension, e.g., action, location, or mood) from direct manipulation to steer reprojection, giving users direct control over the resulting layout. Yet they typically depend on learned embeddings or a predefined criterion. In practice, users' clustering criterion often emerges gradually and becomes refined through interaction rather than being fully clear at the outset. In this work, we present CriterionSI (Criterion-guided Semantic Interaction), a method that translates incremental drag interactions into criterion-guided reprojection. CriterionSI uses large language models to infer and refine the clustering criterion from sequential user drags, while grounding semantic interpretation in human-provided feedback rather than fixed prior assumptions. CriterionSI combines the inferred criterion with local drags to guide global reprojection. The simulation-based evaluation and usage scenario demonstrate that CriterionSI can discover and refine the target criterion from sequential interactions and progressively produce criterion-aligned clustering layouts. Our code and data are available at: https://github.com/4C79/CriterionSI.

cs.HC↗

arXiv2026

Information Terra: A Narrative-Anchored Semantic-First Projection of Document Embeddings

We introduce Information Terra, a narrative-anchored semantic-first projection that places a document corpus on an Earth-like globe whose poles are two user-chosen endpoint documents and whose prime meridian is the great-circle geodesic between them on the embedding hypersphere -- so latitude encodes narrative progress and longitude thematic deviation. Land features are recovered from document density via kernel density estimation and labeled by theme. A narrative trail built from the underlying narrative coherence graph, and constrained to be monotone in geodesic progress, provides a readable storyline. The projection's axes are semantically grounded in the user's chosen narrative endpoints, and the globe metaphor affords rotation and antipodal reading. We demonstrate the method on a 540-article Cuban Protests corpus, showing a storyline from Obama's 2016 visit to the 2021 International Aid during the protests.

cs.HC↗

arXiv2026

Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction

Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can automate narrative generation from spatial layouts, current collage-based and re-generation methods struggle to support the incremental spatial refinements inherent to the sensemaking process. We identify three critical gaps in existing spatial-textual generation: interaction-revision misalignment, human-LLM intent misalignment, and lack of granular customization. To address these, we introduce Semantic Prompting, a framework for spatial refinement that perceives semantic interactions, reasons about refinement intent, and performs targeted positional revisions. We implemented S-PRISM to realize this framework. The empirical evaluation demonstrated that S-PRISM effectively enhanced the precision of interaction-revision refinement. A user study ($N=14$) highlighted how participants leveraged S-PRISM for incremental formalization through interactive steering. Results showed that users valued its efficient, adaptable, and trustworthy support, which effectively strengthens human-LLM intent alignment.

cs.HC↗

arXiv2026

Context-Aware Explanations for Spatialized Document Layouts

Spatialized document layouts are widely used for exploratory analysis of text corpora, but interpreting the spatial organization of documents and the relationships between regions remains challenging. Existing approaches primarily summarize document content or explain how layouts are generated, providing limited support for understanding spatial relationships within the layout itself. We present CAPE, a context-aware explanation framework that generates natural-language explanations grounded in both document semantics and layout-derived spatial context. CAPE identifies salient spatial patterns (e.g., clusters, subgroups, outliers, and bridging documents) and constructs multi-level contextual representations to guide LLM-based explanation generation. It supports both AI-guided overview and user-driven exploration, with explanations available at multiple levels of detail. We demonstrate CAPE on news and scholarly document layouts and evaluate it in a controlled user study against keyword-based and content-only LLM baselines. Our results suggest that spatially grounded explanations are perceived as more helpful than content-only baselines for interpreting the spatial organization of document layouts.

cs.HC↗

arXiv2026

LLM-Augmented Semantic Steering of Text Embedding Projection Spaces

Low-dimensional projections of text embeddings support visual analysis of document collections, but their spatial organization may not reflect the relationships an analyst intends to examine. Existing semantic interaction approaches encode semantic intent indirectly through geometric constraints or model updates, limiting interpretability and flexibility. We introduce LLM-augmented semantic steering, which enables analysts to express semantic intent by grouping a small set of example documents within the projection. A large language model externalizes this intent as natural-language representations and selectively extends it to related documents; the resulting semantic information is then incorporated into document representations via text augmentation or embedding-level blending, without retraining the underlying models. A case study illustrates how the same corpus can be reorganized from different semantic perspectives, while simulation-based evaluation shows that semantic steering improves global and local alignment with target semantic structures using only minimal interaction. Embedding-level blending further enables continuous and controllable steering of projection layouts. These results position projection spaces as intent-dependent semantic workspaces that can be reshaped through explicit, interpretable, language-mediated interaction.

cs.HC↗

arXiv2026

Semantic Interaction for Narrative Map Sensemaking: An Insight-based Evaluation

Semantic interaction (SI) enables analysts to incorporate their cognitive processes into AI models through direct manipulation of visualizations. While SI frameworks for narrative extraction have been proposed, empirical evaluations of their effectiveness remain limited. This paper presents a user study that evaluates SI for narrative map sensemaking, involving 33 participants under three conditions: a timeline baseline, a basic narrative map, and an interactive narrative map with SI capabilities. The results show that the map-based prototypes yielded more insights than the timeline baseline, with the SI-enabled condition reaching statistical significance and the basic map condition trending in the same direction. The SI-enabled condition showed the highest mean performance; differences between the map conditions were not statistically significant but showed large effect sizes (d > 0.8), suggesting that the study was underpowered to detect them. Qualitative analysis identified two distinct SI approaches-corrective and additive-that enable analysts to impose quality judgments and organizational structure on extracted narratives. We also find that SI users achieved comparable exploration breadth with less parameter manipulation, suggesting that SI serves as an alternative pathway for model refinement. This work provides empirical evidence that map-based representations outperform timelines for narrative sensemaking, along with qualitative insights into how analysts use SI for narrative refinement.

cs.HC↗

arXiv2025

Agentic Reasoning and Refinement through Semantic Interaction

Sensemaking report writing often requires multiple refinements in the iterative process. While Large Language Models (LLMs) have shown promise in generating initial reports based on human visual workspace representations, they struggle to precisely incorporate sequential semantic interactions during the refinement process. We introduce VIS-ReAct, a framework that reasons about newly-added semantic interactions in visual workspaces to steer the LLM for report refinement. VIS-ReAct is a two-agent framework: a primary LLM analysis agent interprets new semantic interactions to infer user intentions and generate refinement planning, followed by an LLM refinement agent that updates reports accordingly. Through case study, VIS-ReAct outperforms baseline and VIS-ReAct (without LLM analysis) on targeted refinement, semantic fidelity, and transparent inference. Results demonstrate that VIS-ReAct better handles various interaction types and granularities while enhancing the transparency of human-LLM collaboration.

cs.HC↗

arXiv2025

Investigating Seamless Transitions Between Immersive Computational Notebooks and Embodied Data Interactions

A growing interest in Immersive Analytics (IA) has led to the extension of computational notebooks (e.g., Jupyter Notebook) into an immersive environment to enhance analytical workflows. However, existing solutions rely on the WIMP (windows, icons, menus, pointer) metaphor, which remains impractical for complex data exploration. Although embodied interaction offers a more intuitive alternative, immersive computational notebooks and embodied data exploration systems are implemented as standalone tools. This separation requires analysts to invest considerable effort to transition from one environment to an entirely different one during analytical workflows. To address this, we introduce ICoN, a prototype that facilitates a seamless transition between computational notebooks and embodied data explorations within a unified, fully immersive environment. Our findings reveal that unification improves transition efficiency and intuitiveness during analytical workflows, highlighting its potential for seamless data analysis.

cs.HC↗

arXiv2025

Towards an Embodied Composition Framework for Organizing Immersive Computational Notebooks

As immersive technologies evolve, immersive computational notebooks offer new opportunities for interacting with code, data, and outputs. However, scaling these environments remains a challenge, particularly when analysts manually arrange large numbers of cells to maintain both execution logic and visual coherence. To address this, we introduce an embodied composition framework, facilitating organizational processes in the context of immersive computational notebooks. To evaluate the effectiveness of the embodied composition framework, we conducted a controlled user study comparing manual and embodied composition frameworks in an organizational process. The results show that embodied composition frameworks significantly reduced user effort and decreased completion time. However, the design of the triggering mechanism requires further refinement. Our findings highlight the potential of embodied composition frameworks to enhance the scalability of the organizational process in immersive computational notebooks.

cs.HC↗

arXiv2025

Exploring Organizational Strategies in Immersive Computational Notebooks

Computational notebooks, which integrate code, documentation, tags, and visualizations into a single document, have become increasingly popular for data analysis tasks. With the advent of immersive technologies, these notebooks have evolved into a new paradigm, enabling more interactive and intuitive ways to perform data analysis. An immersive computational notebook, which integrates computational notebooks within an immersive environment, significantly enhances navigation performance with embodied interactions. However, despite recognizing the significance of organizational strategies in the immersive data science process, the organizational strategies for using immersive notebooks remain largely unexplored. In response, our research aims to deepen our understanding of organizations, especially focusing on spatial structures for computational notebooks, and to examine how various execution orders can be visualized in an immersive context. Through an exploratory user study, we found participants preferred organizing notebooks in half-cylindrical structures and engaged significantly more in non-linear analysis. Notably, as the scale of the notebooks increased (i.e., more code cells), users increasingly adopted multiple, concurrent non-linear analytical approaches.

cs.HC↗

arXiv2025

Narrative Trails: A Method for Coherent Storyline Extraction via Maximum Capacity Path Optimization

Traditional information retrieval is primarily concerned with finding relevant information from large datasets without imposing a structure within the retrieved pieces of data. However, structuring information in the form of narratives--ordered sets of documents that form coherent storylines--allows us to identify, interpret, and share insights about the connections and relationships between the ideas presented in the data. Despite their significance, current approaches for algorithmically extracting storylines from data are scarce, with existing methods primarily relying on intricate word-based heuristics and auxiliary document structures. Moreover, many of these methods are difficult to scale to large datasets and general contexts, as they are designed to extract storylines for narrow tasks. In this paper, we propose Narrative Trails, an efficient, general-purpose method for extracting coherent storylines in large text corpora. Specifically, our method uses the semantic-level information embedded in the latent space of deep learning models to build a sparse coherence graph and extract narratives that maximize the minimum coherence of the storylines. By quantitatively evaluating our proposed methods on two distinct narrative extraction tasks, we show the generalizability and scalability of Narrative Trails in multiple contexts while also simplifying the extraction pipeline.

cs.IR↗

arXiv2025

Explainable AI Components for Narrative Map Extraction

As narrative extraction systems grow in complexity, establishing user trust through interpretable and explainable outputs becomes increasingly critical. This paper presents an evaluation of an Explainable Artificial Intelligence (XAI) system for narrative map extraction that provides meaningful explanations across multiple levels of abstraction. Our system integrates explanations based on topical clusters for low-level document relationships, connection explanations for event relationships, and high-level structure explanations for overall narrative patterns. In particular, we evaluate the XAI system through a user study involving 10 participants that examined narratives from the 2021 Cuban protests. The analysis of results demonstrates that participants using the explanations made the users trust in the system's decisions, with connection explanations and important event detection proving particularly effective at building user confidence. Survey responses indicate that the multi-level explanation approach helped users develop appropriate trust in the system's narrative extraction capabilities. This work advances the state-of-the-art in explainable narrative extraction while providing practical insights for developing reliable narrative extraction systems that support effective human-AI collaboration.

cs.CL↗