The Inference Report

Audio dramas weave dialogue, sound effects, and music into immersive stories. Creators often adapt books into audio dramas, but this process remains labor-intensive, requiring them to interpret source material, author scripts, generate audio assets, and assemble them on a timeline. Because story elements like characters and scenes manifest across many interdependent assets, a single change can ripple into manual updates across the entire project. We present Dramarrator, an audio drama authoring tool built around object-based audio editing, where these story elements are represented as editable objects. Dramarrator extracts these objects from a book, generates linked audio assets (speech, sound effects, and music), and composes a multi-track audio drama. Edits to any object (e.g., a character's voice) automatically propagate to all dependent assets. In a user study with professionals (N=8), Dramarrator significantly lowered task load when creating audio dramas. A listener study (N=300) shows that creator-refined output from Dramarrator approaches the quality of productions made with existing professional tools, and an exploratory study (N=3) suggests object-based editing lowers entry barriers and generalizes beyond audio dramas.

Virtual cells employ machine learning models to simulate and predict cellular behaviors, serving as a critical computational framework for investigating health and disease. Injecting causal graphs into virtual cells can improve the interpretability, but such graphs are usually not available in real-world applications. Recently, many methods have been proposed to construct causal graphs from data, which group genes based on their similarities to form concepts and extract their causal relationships. However, since this automatic process is unsupervised, the causal graphs usually contain errors. In this paper, we propose a human-guided causal knowledge injection method for virtual cells. We developed a gene-similarity-aware causal graph visualization supported by a hybrid optimization algorithm to help explore both the causal relationships between concepts and the similarities between genes. Based on the exploration, we further developed a counterfactual analysis strategy supported by a counterfactual visualization and a causal path visualization to help validate and refine causal graphs. The effectiveness of our method is demonstrated through two real-world case studies, the extraction of scientifically meaningful causal insights, and positive feedback from domain experts.

Previous studies have shown that people can develop shared symbols, partner-specific expressions, personal idioms, inside jokes, and other parts of a relational microculture. Recent work has also examined how humans and conversational AI negotiate and revise symbolic meanings. However, long-term human-AI systems still lack a clear design model for recording how a dyad-specific expression gains meaning, checking whether both sides still accept that meaning, and safely reusing the expression in later sessions. This concept-and-prototype paper introduces Private Etymology, a machine-representable relational provenance that records how a dyad-specific symbolic expression is proposed, interpreted, negotiated, repaired, reused, revised, stabilized, contested, forgotten, or retired over time. I also propose relational reuse: reactivating a dyad-specific expression in a later session without fully explaining its meaning again. The contribution is not the invention of shared symbols or relational microcultures. Instead, this paper integrates prior ideas into persistent, revisable, and evidence-grounded symbolic units for human-AI relationships. I present a lifecycle model, an illustrative machine-readable schema, a working Apple Watch prototype, and a longitudinal research agenda. In the prototype, a language model classifies discrete conversational evidence, while deterministic local code decides whether a Shared Symbol can be updated. This prevents a free-form model confidence score or an AI proposal by itself from directly updating the persisted symbol. Private Etymology is proposed as infrastructure for conversational agents to participate in changing relational microcultures without inventing their origins or treating relational meaning as a fixed memory value.

A graph layout is normally a table of $N$ free coordinates. We optimise a function with a fixed number of parameters instead. This gives a drawing a sample complexity and an extensible domain. Force-directed algorithms remain the standard tools for graph drawing. The most accurate among them minimise stress in the Kamada-Kawai formulation by directly optimising the node coordinates, at a full objective cost of $O(N^2)$ in time and space. Here, we propose Fling (Field Layout via Implicit Neural Geometry), a small neural network mapping the distances of each node to a set of landmarks, positioning it in the plane by training on the layout energy. The full spring system then becomes tractable without its distance matrix, as rest lengths follow from a landmark bound in constant time per pair while a second network learns the majorisation sums from exact anchor rows, at $O(|\mathcal{A}|N)$ per step for $|\mathcal{A}|\ll N$ anchors. Unlike neural drawers that read the graph by message passing, we represent the drawing as a function of node features. An unseen node costs one forward pass, where sparse and low-rank majorisation remain transductive. As the unknowns are weights rather than coordinates, the energy only requires a small fraction of the nodes, and a field fitted that way outperforms PivotMDS, landmark MDS, and a kernel ridge trained on the same energy and features, when the task is fitting the energy of a graph from a sample of its nodes. In addition, the same parameterisation enables a stochastic pivot stress variant, an aesthetics-optimised variant carrying a neighbour-embedding energy with node-edge clearance and crossing terms on the same field, and conditioning on the weight between two energies gives a whole layout family from one run.

AI tools that help people judge online claims are usually evaluated while the tool is present. This paper asks a different question: after using such a tool, what can the user still do on their own? I call this epistemic transfer. It refers to the effect of prior AI-assisted verification on later unassisted performance on new claims. In this paper, I make three contributions. First, I distinguish epistemic transfer from nearby outcomes such as correction effects, trust, reliance, and human--AI team performance. Second, I introduce two simple quantities for studying it: the Epistemic Transfer Effect (ETE), which compares delayed unassisted performance across conditions, and Tool-Removal Cost (TRC), which measures the immediate drop in performance when the tool is taken away. Third, I turn these ideas into a practical evaluation protocol that can be used in online experiments or field studies. The protocol combines answer-first and evidence-first AI conditions with active-practice and no-practice controls, delayed tests on held-out claims, behavioral measures, and participant- and item-level analyses. Putting ETE and TRC together yields a diagnostic space that separates capability building, capability plus tool advantage, epistemic inertness or de-skilling, and verification on loan. The point is not that every AI tool must teach. The point is that when independent judgment matters, we should test not only whether a tool helps now, but also what it leaves behind.

As generative AI increasingly becomes a common source of daily decision-making, including financial choices, it is critical to understand how people evaluate AI-generated financial advice. We conducted a preregistered vignette experiment (N = 285) in which substantive financial content---including facts, numerical values, recommendation direction, and core reasoning---was held constant while communication style varied across AI Financial Assistant (AI), Certified Financial Planner (Expert), and Online Community Forum (OC) advice. Displayed source attribution was independently manipulated through correctly labeled, unlabeled, and mislabeled conditions, allowing us to separate attribution effects from source-specific communication cues. Expert advice was rated more favorably than AI advice on 9 of 10 outcomes (|d|=0.20--0.47), and this advantage remained visible without source labels, where Expert advice outperformed AI advice on 8 of 10 outcomes (up to d=0.60). Correct labels added limited differentiation, whereas mislabeling increased ratings of AI advice for situational fit and overall quality (d=0.42 for each) and attenuated the Expert advantage in situational fit (d=-0.36). Descriptive analyses further showed that AI advice was most responsive to displayed attribution and, conversely, that advice-style differences were most visible under an AI label. These findings show that financial-advice evaluations are shaped jointly by displayed attribution and message-level communication cues. We position disclosure not as a neutral transparency mechanism, but as an interpretive frame whose accuracy and interaction with message cues can shape trust and reliance.