{"slug": "from-imperfective-paradox-to-moorean-absurdity-single-chain-reasoning-lock-in", "title": "From Imperfective Paradox to Moorean Absurdity: Single-Chain Reasoning Lock-In and Multi-Candidate Verbalization Across Aspectual and Pragmatic Ambiguity", "summary": "A preregistered study of Qwen3-8B-Q8_0 across 16,640 formal units at temperature=0.0 found that prompt-and-readout protocols shift the model's judgments on aspectual and pragmatic ambiguity, with Direct-CoT and Multi-Candidate Verbalization (MCV) differing by 25.00 percentage points on telic high-confidence completion (Holm p=1.31239e-05) while NLI-CoT collapsed by -91.25 pp on uninterrupted atelic items (Holm p=1.81805e-21). In Experiment 4, MCU-CF raised perceived coherence on implicit Moorean sentences by 26.64 pp over Direct-CoT (Holm p=0.0006), alongside Direct-CF minus Direct-CoT at 29.15 pp and MCU-CoT minus Direct-CoT at 17.31 pp. The authors report 15 of 16 hypothesis slots retained confirmatory status (12 rejecting H0 under within-experiment Holm control at alpha_fam=0.05, with E3_H3 demoted to descriptive), and a 1,800-call OpenAI ablation plus a stage=\"dev\" P16.7 cross-model extension (4,222 valid of 4,240 planned/collected units across five external models) showed discrete NLI-CoT and scalar Direct-CoT judgments dissociate across models; the authors state internal premature lock-in remains a hypothesis, and code, stimuli and analysis plans are at github.com/asj252/llm-judgment-studies.", "body_md": "arXiv:2611.22188v1 Announce Type: new \nAbstract: Natural language entailment and coherence judgments often depend on whether an event merely occurred, reached a telic culmination, satisfied a plan, or was evaluated under multiple pragmatic standards. We test observable consequences of the single-chain premature lock-in hypothesis across four preregistered, sealed formal experiments on Qwen3-8B-Q8_0 (16,640 formal units, temperature=0.0): 15 of 16 hypothesis slots retain confirmatory status (12 rejecting H0 under within-experiment Holm control at alpha_fam=0.05; E3_H3 demoted to descriptive status). In Experiment 1, Direct-CoT vs. MCU differs by 25.00 pp on telic high-confidence completion (Holm p=1.31239e-05), while NLI-CoT collapses by -91.25 pp on uninterrupted atelic items (Holm p=1.81805e-21). Multi-Candidate Verbalization (MCV) elicits K=5 weighted estimates in one call, separating the prompt from unweighted (MCU) and self-weighted (MCW) readouts. Mandarin (E2) and English (E3) expose an Interruption-Anchored Realis Paradox under NLI-CoT. In Experiment 4, MCU-CF raises perceived coherence on implicit Moorean sentences by 26.64 pp over Direct-CoT (Holm p=0.0006), alongside Direct-CF - Direct-CoT = 29.15 pp and MCU-CoT - Direct-CoT = 17.31 pp. A 1,800-call OpenAI ablation and a stage=\"dev\" P16.7 cross-model extension (4,240 planned/collected units across five external models: 4,222 valid, 18 format-missing, 0 transport-missing; <2% missing per slice; OpenAI gpt-4o-mini at top_logprobs=20 achieves 1,000/1,000 valid units) show that discrete NLI-CoT and scalar Direct-CoT judgments dissociate across models. Confirmatory effects concern observable prompt-and-readout protocols; internal premature lock-in remains a hypothesis. All code, stimuli, preregistered analysis plans, and verification tools are available at https://github.com/asj252/llm-judgment-studies.", "url": "https://wpnews.pro/news/from-imperfective-paradox-to-moorean-absurdity-single-chain-reasoning-lock-in", "canonical_source": "https://www.machinebrief.com/news/from-imperfective-paradox-to-moorean-absurdity-single-chain-m046", "published_at": "2026-11-18 05:00:00+00:00", "updated_at": "2026-11-18 05:16:15.233974+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "natural-language-processing", "ai-safety"], "entities": ["Qwen3-8B-Q8_0", "OpenAI", "gpt-4o-mini", "Multi-Candidate Verbalization", "Direct-CoT", "NLI-CoT"], "also_reported_by": [], "takeaway": "On Qwen3-8B-Q8_0, NLI-CoT dropped 91.25 pp on uninterrupted atelic items versus Direct-CoT's 25.00 pp telic gain, so prompt-and-readout choice, not just the model, determines entailment judgments.", "recommendation": {"advice": "Test both discrete NLI-CoT and scalar Direct-CoT readouts before trusting a model's entailment judgments; the source measured a -91.25 pp collapse under NLI-CoT on atelic items.", "playbook": "evals-testing", "playbook_url": "https://wpnews.pro/playbooks/evals-testing"}, "alternates": {"html": "https://wpnews.pro/news/from-imperfective-paradox-to-moorean-absurdity-single-chain-reasoning-lock-in", "markdown": "https://wpnews.pro/news/from-imperfective-paradox-to-moorean-absurdity-single-chain-reasoning-lock-in.md", "text": "https://wpnews.pro/news/from-imperfective-paradox-to-moorean-absurdity-single-chain-reasoning-lock-in.txt", "jsonld": "https://wpnews.pro/news/from-imperfective-paradox-to-moorean-absurdity-single-chain-reasoning-lock-in.jsonld"}}