{"total":16,"items":[{"citing_arxiv_id":"2605.17196","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Maxwell's Demon","primary_cat":"quant-ph","submitted_at":"2026-05-16T23:49:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Historical overview of Maxwell's Demon and Second Law challenges, proposing Heisenberg Uncertainty Principle as decisive defeat of the Demon and alternative basis for Landauer's Principle.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16758","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Language Acquisition Device in Large Language Models","primary_cat":"cs.CL","submitted_at":"2026-05-16T02:13:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Pre-pretraining on MP-STRUCT matches k-Shuffle Dyck baselines in efficiency while adding human-like resistance to implausible languages and challenges the need for C-RASP definability in effective PPT languages.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15440","ref_index":70,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis","primary_cat":"cs.CL","submitted_at":"2026-05-14T21:44:26+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Varying the number of simultaneous parses in RNNGs increases predicted garden-path effects but does not fully reconcile LM surprisal with human reading times.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14480","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Cross-Linguistic Transcription and Phonological Representation in the Hu\\`it\\'onggu\\v{a}nx\\`i Hu\\'ay\\'iy\\`iy\\v{u}","primary_cat":"cs.CL","submitted_at":"2026-05-14T07:21:18+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09747","ref_index":74,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Matching Function: A Unified Look into the Black Box","primary_cat":"econ.TH","submitted_at":"2026-05-10T20:50:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Network structures of applicant-vacancy links determine matching function forms, with dispersion in search intensities reducing match efficacy and potentially making higher average search counterproductive.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02106","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Dynamic Gist-Based Memory Model (DGMM): A Memory-Centric Architecture for Artificial Intelligence","primary_cat":"cs.AI","submitted_at":"2026-05-04T00:02:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"DGMM is proposed as an explicit graph-structured memory architecture for AI that enables persistent episodic memory, cue-based recall, and context-dependent interpretation without retraining.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Let 𝑁𝑘 (𝑣, 𝑡|𝑞) denote the 𝑘-hop neighborhood of node 𝑣 within 𝑅𝑡 (𝑞). Local divergence may be expressed as Δnbr (𝑣;𝑡 1, 𝑡2 |𝑞)=1− |𝑁𝑘 (𝑣, 𝑡1 |𝑞) ∩𝑁 𝑘 (𝑣, 𝑡2 |𝑞) | |𝑁𝑘 (𝑣, 𝑡1 |𝑞) ∪𝑁 𝑘 (𝑣, 𝑡2 |𝑞) | .(10) Embedding-Based Divergence (Post-Recall Interpretation).Embeddings in DGMM are computed after recall as query-conditioned projections of recalled structure. Let Φ𝑞 :𝑅 𝑡 (𝑞) →𝑍 𝑡 (𝑞)(11) produce transient embeddings𝑧 𝑣 (𝑡|𝑞). Representational divergence may be expressed as Δemb(𝑣;𝑡 1, 𝑡2 |𝑞)= ∥𝑧𝑣 (𝑡2 |𝑞) −𝑧 𝑣 (𝑡1 |𝑞) ∥ .(12) Embedding divergence reflects changes in how recalled structure is interpreted under a given query context. Such divergence may indicate structural reorganization in recall, shifts in contextual emphasis, or the emergence"},{"citing_arxiv_id":"2604.17490","ref_index":186,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Joint Exclusivity","primary_cat":"math.ST","submitted_at":"2026-04-19T15:27:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Joint exclusivity extends mutual exclusivity with a sharp existence condition sum of marginal survival functions at zero at most n-1, a canonical construction on lower-dimensional faces, and a link to joint mixability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10580","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Knowing What to Stress: A Discourse-Conditioned Text-to-Speech Benchmark","primary_cat":"cs.CL","submitted_at":"2026-04-12T10:57:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CAST benchmark shows language models infer correct word stress from discourse context but TTS systems frequently fail to produce it in speech.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10333","ref_index":97,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Zero-shot World Models Are Developmentally Efficient Learners","primary_cat":"cs.AI","submitted_at":"2026-04-11T19:32:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A zero-shot visual world model trained on one child's experience achieves broad competence on physical understanding benchmarks while matching developmental behavioral patterns.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"InInternational Conference on Machine Learning, 2011. URL https://api.semanticscholar.org/CorpusID:14273320. [96] Carlos E. García, David M. Prett, and Manfred Morari. Model predictive control: Theory and practice-A survey.Automatica, 25(3):335-348, 1989. ISSN 0005-1098. doi:https: //doi.org/10.1016/0005-1098(89)90002-2. URL https://www.sciencedirect.com/science/ article/pii/0005109889900022. [97] David Ha and Jürgen Schmidhuber. World Models. March 2018. doi:10.5281/zenodo.1207631. URLhttp://arxiv.org/abs/1803.10122. arXiv:1803.10122 [cs]. [98] Danijar Hafner, Timothy P . Lillicrap, Jimmy Ba, and Mohammad Norouzi. Dream to control: Learning behaviors by latent imagination.ArXiv, abs/1912.01603, 2019. URL https://api. semanticscholar.org/CorpusID:208547755."},{"citing_arxiv_id":"2604.08632","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Why Network Segmentation Projects Fail","primary_cat":"cs.CR","submitted_at":"2026-04-09T17:00:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Survey of 400 practitioners identifies four failure archetypes for network segmentation projects, with uniform preference for general IT project management fixes over segmentation-specific ones.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19791","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Stabilising Generative Models of Attitude Change","primary_cat":"cs.AI","submitted_at":"2026-04-02T13:47:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Researchers rendered cognitive dissonance, self-consistency, and self-perception theories as generative simulations that reproduce classic experimental behavioral patterns after iterative manual stabilization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.14066","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Benchmark for Multi-Party Negotiation Games from Real Negotiation Data","primary_cat":"cs.MA","submitted_at":"2026-03-14T18:12:06+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A new benchmark for sequential multi-party negotiations from climate data shows no solver dominates and performance depends on game structure.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2211.09110","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Holistic Evaluation of Language Models","primary_cat":"cs.CL","submitted_at":"2022-11-16T18:51:34+00:00","verdict":"ACCEPT","verdict_confidence":"UNKNOWN","novelty_score":7.0,"formal_verification":"none","one_line_summary":"HELM establishes a multi-metric evaluation covering 30 language models on 42 scenarios (16 core) to raise average scenario coverage from 17.9% to 96% under uniform conditions while releasing all prompts, completions, and a toolkit.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1908.11443","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"NarrativeTime: Dense Temporal Annotation on a Timeline","primary_cat":"cs.CL","submitted_at":"2019-08-29T20:09:27+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"NarrativeTime is a timeline annotation framework achieving full TLink coverage, shown via re-annotation of TimeBankDense with comparable agreement and higher density plus a new TimeBankNT corpus.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.09115","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Measuring Belief and Risk Attitude","primary_cat":"cs.GT","submitted_at":"2019-07-22T03:19:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Extends Ramsey's elicitation of subjective probabilities to risk-weighted expected utility maximizers by first deriving a measurement of risk attitudes from preferences.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.05381","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Adaptive Pricing in Insurance: Generalized Linear Models and Gaussian Process Regression Approaches","primary_cat":"econ.EM","submitted_at":"2019-07-02T08:18:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Adaptive GLM with MQLE and GP regression with UCB for dynamic insurance pricing, showing parameter convergence and regret analysis under delayed claims.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}