{"ID":5439497,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-02T19:54:01.969788673Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30875","arxiv_id":"2606.30875","title":"The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning","abstract":"Foundation model pseudo-labeling - labeling data strictly via zero-shot inference - enables massive scale, but performance is undermined by hallucinations that evade standard thresholds. To eliminate these errors, we introduce the Turing-inspired Label Imitation Game (LIG), a framework that formalizes pseudo-label pruning as an adversarial interrogation. Rather than filtering labels via isolated thresholds, we use the LIG to train a Turing Test Network (TTN), a task-agnostic \"judge\" that evaluates candidate pseudo-labels within a dataset-wide context. Experiments across four diverse datasets demonstrate the TTN's robustness, consistently enhancing label accuracy for three state-of-the-art vision-language models without costly supervision or retraining. Crucially, we demonstrate that learned semantic-contextual logic is a robust alternative to spatial-geometric verification, enabling a unique zero-shot task transfer capability - a TTN trained strictly on image classification datasets can effectively prune complex object detection pseudo-labels. This pruning yields F1-score gains of 28% for the worst-performing baseline categories and 44% with task-specific fine-tuning. Significantly, we also observe Category Revival, where the TTN pruning \"detoxifies\" the training signal for downstream models and enables them to recover from zero recall on transfer-vulnerable classes. The pre-trained TTN models and code are available at https://github.com/voxel51/ttn.","short_abstract":"Foundation model pseudo-labeling - labeling data strictly via zero-shot inference - enables massive scale, but performance is undermined by hallucinations that evade standard thresholds. To eliminate these errors, we introduce the Turing-inspired Label Imitation Game (LIG), a framework that formalizes pseudo-label prun...","url_abs":"https://arxiv.org/abs/2606.30875","url_pdf":"https://arxiv.org/pdf/2606.30875v1","authors":"[\"Brent A. Griffin\",\"Jason J. Corso\"]","published":"2026-06-29T20:06:58Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":613795,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-01T01:17:58.482524686Z","DeletedAt":null,"paper_id":5439497,"paper_url":"https://arxiv.org/abs/2606.30875","paper_title":"The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning","repo_url":"https://github.com/voxel51/ttn","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}