{"ID":6024169,"CreatedAt":"2026-07-08T01:00:23.257252134Z","UpdatedAt":"2026-07-09T22:59:56.587686154Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05689","arxiv_id":"2607.05689","title":"UCSC NLP at SemEval-2026 Task 10: Boundary-Aware Span Extraction and RoBERTa Classification for Conspiracy Detection","abstract":"We present our systems for SemEval-2026 Task 10 (PsyCoMark), addressing conspiracy marker extraction (Subtask 1) and document-level conspiracy detection (Subtask 2). For marker extraction, we formulate the task as multi-label span classification over enumerated candidate spans, using IoU \u003e= 0.95 positive labeling, hard-negative sampling, and containment-based non-maximum suppression (NMS) with boundary-aware span representations. Document classification is modeled independently using a sequence classifier with label smoothing and a stratified train-validation split. Analysis shows that entity-like roles (Actor, Victim) are detected robustly, while abstract roles (Action, Effect, Evidence) remain sensitive to boundary criteria. On the official test set, our systems rank 7th in Subtask 1 (0.2251 macro F1) and 11th in Subtask 2 (0.7694 weighted F1).","short_abstract":"We present our systems for SemEval-2026 Task 10 (PsyCoMark), addressing conspiracy marker extraction (Subtask 1) and document-level conspiracy detection (Subtask 2). For marker extraction, we formulate the task as multi-label span classification over enumerated candidate spans, using IoU \u003e= 0.95 positive labeling, hard...","url_abs":"https://arxiv.org/abs/2607.05689","url_pdf":"https://arxiv.org/pdf/2607.05689v1","authors":"[\"Dom Marhoefer\",\"Milos Suvakovic\",\"Glenn Grant-Richards\",\"Aidan Pinero\",\"Ryan King\"]","published":"2026-07-06T23:15:52Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.SI\"]","methods":"[]","has_code":false}