{"arxiv_id":"2601.12754","incoming":{"papers":5,"sentences":6,"groups":[{"kind":"method_or_tool","label":"Uses its method or tool","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2605.08590","title":"Causal Stories from Sensor Traces: Auditing Epistemic Overreach in LLM-Generated Personal Sensing Explanations","url":"/paper/2605.08590","section":"LLM-Based Automated Evaluations","sentence":"Following prior work on LLM-as-judge evaluation [ref] , we evaluate generated explanations with a structured rubric prompt.","intent_p":0.98,"contests_p":null}]},{"kind":"background","label":"Cites it as background","papers":4,"sentences":4,"quotes":[{"arxiv_id":"2605.30273","title":"LLUMI: Improving LLM Writing Assistance for Mental Health Support with Online Community Feedback","url":"/paper/2605.30273","section":"Related Work","sentence":"Existing approaches have primarily relied on prompt engineering, supervised fine-tuning, and reinforcement learning-based alignment methods [ref] .","intent_p":0.83,"contests_p":null},{"arxiv_id":"2605.30913","title":"Prompt PerturbAItions: Mechanisms of LLM Response Inconsistencies","url":"/paper/2605.30913","section":"Related Work","sentence":"LLMs inherit biases and toxic patterns from their training data, leading to concerns about fairness, safety, and harmful content generation [ref] .","intent_p":0.92,"contests_p":null},{"arxiv_id":"2608.29028","title":"Facts Without Rules: Boundary Metadata Collapse in Multi-Agent LLM Handoffs","url":"/paper/2608.29028","section":"Introduction","sentence":"Multi-agent LLM systems (MAS) are increasingly deployed in coordination-heavy domains such as scheduling, care coordination, financial workflows, and enterprise pipelines [ref] , where they communicate through compressed handoffs: one agent's summary, forwarded message, or memory entry becomes the next agent's ground truth.","intent_p":0.82,"contests_p":null},{"arxiv_id":"2603.19574","title":"AI Psychosis: Does Conversational AI Amplify Delusion-Related Language?","url":"/paper/2603.19574","section":"Practical and Design Implications","sentence":"Much of the current safety research on conversational AI focuses on mitigating harms in single-turn or single-session interactions, such as unsafe outputs to isolated prompts [ref] .","intent_p":0.92,"contests_p":null}]}],"unlabelled_sentences":1},"outgoing":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"claims":[],"thresholds":{"intent_p":0.8,"supports_p":0.95,"contests_p":0.7},"method":"Citing sentences come from each paper's LaTeX source; every \\cite marks the sentence and the works it cites. Pith's classifier typed each sentence. A label is shown at intent probability 0.8 or more (0.95 for support), a contest at 0.7 or more. Measured accuracy against two blind model families is at https://pith.science/accuracy. The quoted sentences are the citing authors' own.","held_up":null,"_links":{"html":"https://pith.science/paper/2601.12754"}}