{"total":23,"items":[{"citing_arxiv_id":"2606.22748","ref_index":174,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AI Fiction in the Wild","primary_cat":"cs.CL","submitted_at":"2026-06-22T01:29:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Analysis of 500k ChatGPT logs shows over one-third of conversations generate fiction, dominated by power users with repetitive and niche patterns.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21232","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multi-Source Prediction-Powered Inference","primary_cat":"stat.ME","submitted_at":"2026-06-19T08:53:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Multi-source prediction-powered inference aggregates multiple pseudo-labeled datasets via weights chosen to minimize asymptotic confidence-region volume, with asymptotic normality and comparisons to single-source and target-only baselines shown for both homogeneous and heterogeneous (covariate/domai","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12186","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Resource for Enthymeme Detection in Controversial Political Discourse","primary_cat":"cs.CL","submitted_at":"2026-06-10T15:09:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Presents a new annotated resource of 1,482 tweets for enthymeme detection that studies label variation instead of eliminating it, with preliminary evidence that disagreement-aware training improves model performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07802","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Memetic Capture: A Pluralistic Policy Framework for Governing AI-Driven Cultural Disempowerment","primary_cat":"cs.CY","submitted_at":"2026-06-05T19:32:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Defines memetic capture as AI-driven cultural disempowerment and outlines the CPGF policy architecture combining metrics, democratic assemblies, pluralistic standards, and transnational coordination.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05997","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multimodal Sexism Identification and Characterization using Large Language Models and Gradient Boosting","primary_cat":"cs.CV","submitted_at":"2026-06-04T10:43:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A late-fusion gradient-boosting pipeline with LLM semantic features is submitted to the EXIST 2026 lab for sexism identification in memes and videos, showing mixed generalization from development to test data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04903","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Provably Auditable and Safe LLM Agents from Human-Authored Ontologies","primary_cat":"cs.LO","submitted_at":"2026-06-03T14:01:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Agentic Redux claims provably correct LLM agent executions on suitable domains via typed lambda calculus with full decision logging, demonstrated on healthcare compliance and security disclosure with supporting code.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28647","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Ethics of LLM Sandbox and Persona Dynamics","primary_cat":"cs.AI","submitted_at":"2026-05-27T15:52:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Argues that LLM guardrails generate unethical reality gaps by shifting epistemic risk to users and that ethical AI can become unethical when it prioritizes institutional reassurance over accurate perception.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28616","ref_index":61,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Measuring Form and Function in Language Models","primary_cat":"cs.CL","submitted_at":"2026-05-27T15:27:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Proposes CAC prompting to benchmark language models on syntactic and discourse properties of determiners against child acquisition data, finding large models approach but do not match human performance on both.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26084","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"What is 'undone computer science'?","primary_cat":"cs.CY","submitted_at":"2026-05-25T17:48:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Introduces 'undone computer science' as a lens for spotting neglected research questions arising from the sociological, economic, and political organization of the field.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23054","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Model Collapse as Cultural Evolution","primary_cat":"cs.CL","submitted_at":"2026-05-21T21:36:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Iterated learning theory predicts and LLM experiments confirm non-monotonic compositionality during self-training, reframing model collapse as cultural transmission with matching human regularization patterns.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17510","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scale-Dependent Collective Adaptation in Self-Amending LLM Societies: A Cross-Family Study of Emergent Governance","primary_cat":"nlin.AO","submitted_at":"2026-05-17T15:45:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LLM societies in Nomic show non-monotonic collective adaptation peaking at mid-scales, with smaller models rule-inert and larger ones restrictive.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15920","ref_index":2,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Unsupervised Domain Shift Detection with Interpretable Subspace Attribution","primary_cat":"stat.ML","submitted_at":"2026-05-15T12:58:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An unsupervised method detects domain shifts via localized density anomaly search in feature space, attributes the shift to a minimal subspace, and extracts balanced subsets from two unlabeled datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12011","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CaloArt: Large-Patch x-Prediction Diffusion Transformers for High-Granularity Calorimeter Shower Generation","primary_cat":"physics.ins-det","submitted_at":"2026-05-12T12:00:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CaloArt achieves top FPD, high-level, and classifier metrics on CaloChallenge datasets 2 and 3 while keeping single-GPU generation at 9-11 ms per shower by combining large-patch tokenization, x-prediction, and conditional flow matching.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"values at the50K- and100K-step checkpoints for both formulations. successfully whilev-prediction fails to produce meaningful samples [23]. This difference is plausible because, although the(5,10,6)patch size is large and the hidden dimension480 is smaller than the image DiT settings considered in JiT, the effective dimensionality of the calorimeter shower remains lower than that of high-resolution raw images [32]. A catas- trophic failure ofv-prediction appears once the patch size is made even more aggressive. Figure 5 compares the training loss curves under the samev-loss, usingv-prediction versus x-prediction for a hidden-384CCD3 setting with patch size(5,10,9). Since the loss is computed in the same space and only the prediction parameterization differs, comparing"},{"citing_arxiv_id":"2605.11832","ref_index":83,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation","primary_cat":"cs.RO","submitted_at":"2026-05-12T09:21:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The method uses multi-view diffusion priors and action manifold learning to resolve depth ambiguity and improve action prediction in VLA robotic manipulation models, reporting higher success rates than baselines on LIBERO, RoboTwin, and real-robot tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"5 [82] 98.8 98.2 98.0 92.4 96.9 GR00T-N1.6 [20] 97.7 98.5 97.5 94.4 97.0 OpenVLA-OFT [11] 97.6 98.4 97.9 94.5 97.1 UniVLA [38] 96.5 96.8 95.6 92.0 95.2 X-VLA [35] 98.2 98.6 97.897.698.1 GeoVLA [64] 98.4 99.0 96.6 96.6 97.7 3D-CAVLA [62] 98.2 99.8 98.2 96.1 98.1 Spatial Forcing [16] 99.4 99.6 98.8 96.0 98.5 Ours98.899.8 99.096.698.6 the manifold hypothesis [83], [84], high-dimensional real- world data, such as natural images and human language, do not scatter randomly but rather reside on intrinsic low- dimensional manifolds. We extend this insight to robotics, positing that coherent and meaningful robot action se- quences also constitute highly structured entities lying on a low-dimensionalaction manifold."},{"citing_arxiv_id":"2605.12536","ref_index":109,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Information as Maximum-Caliber Deviation: A bridge between Integrated Information Theory and the Free Energy Principle","primary_cat":"q-bio.NC","submitted_at":"2026-05-03T07:22:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Information defined as maximum-caliber deviation derives IIT 3.0 cause-effect repertoires from constrained entropy maximization and equates to prediction error under CLT and LDT.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"scientific approach for studying consciousness remains elusive[84, 83]. 24 Chapter 3 Bayesian Methods in Theoretical Neurobiology HELMHOLTZ PROPOSEDin 1867 that perception arises from unconscious inference[71]. Almost a century later, Barlow identified elimination of redundant signals as a motivating factor for this[207]. In 1982, Marr proposed that perception entails recovering causes from sensory statistical noise[109]. Thereafter, the Helmholtz Machine was created, aiming to model human learning by inferring patterns from data through a stochastic generative model[145]. Theoretical neuroscience then formally adopted Bayesian inference[27], while computer scientists advanced methods to perform it more efficiently[217, 218, 219]. These synthesized, which resulted in a family of theories applying"},{"citing_arxiv_id":"2604.20195","ref_index":165,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Photometric Super-Resolution for Improving Galaxy Morphological Measurements using Conditional Generative Adversarial Networks","primary_cat":"astro-ph.IM","submitted_at":"2026-04-22T05:23:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Neo, a cGAN, super-resolves HSC images to HST-like quality and improves galaxy morphological parameter accuracy by factors of 2-10.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08200","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Towards Improving the External Validity of Software Engineering Experiments with Transportability Methods","primary_cat":"cs.SE","submitted_at":"2026-04-09T12:57:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Transportability methods can transport causal effects from experimental samples to broader target populations in software engineering by leveraging observational data to improve external validity.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"engineers [2]. Figure 2 visualizes this challenge. The black line rep- resents subjects' trial eligibility (in percentage) which decreases for higher values of 𝑋 . The distribution of the covariate 𝑋 in the experimental sample (teal bars) therefore ends up different from the distribution in the target population (red bars)-a phenomenon known ascovariate shift[ 25]. When 𝑋 is both a treatment effect modifier and experiences a covariate shift, the measurable 𝜏1 can differ from 𝜏. In our example, the experiment likely involves more easy-to-recruit but inexperienced subjects for which the measured effect is particularly strong. As a consequence, the experiment will overestimate 𝜏1 >𝜏 and suggest that using GenAI is much more"},{"citing_arxiv_id":"2604.15337","ref_index":74,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Radical Gender Neutrality: Agender Euphoria in Gaming and Play Experiences","primary_cat":"cs.HC","submitted_at":"2026-03-10T11:23:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A critical incident technique study with 142 participants identifies mechanisms by which games create or block agender euphoria and supplies empirically grounded design criteria for gender-neutral play.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Future work should sample outside of Anglocentric and WEIRD contexts. The CIT method relies on accounts retrieved from memory, i.e., post-hoc recall, a constructive process prone to decay [67, 79, 94, 131], especially if the incident happened a long time before. Follow-up work could include real-time observations of play, similar to a stimulated-recall technique [74]. Our use of the I-PANAS-SF [76, 152] was guided by future cross-cultural work. However, the scale items did not fully match euphoric experiences. We recommend using the upcoming Gender Euphoria Scale [20] instead. Finally, we included agender+ populations offering agender (non)euphoric experiences. Differ- ences among agender variants [164] may have been obscured by"},{"citing_arxiv_id":"2602.11236","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning","primary_cat":"cs.CV","submitted_at":"2026-02-11T16:47:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ABot-M0 unifies heterogeneous robot data into a 6-million-trajectory dataset and introduces Action Manifold Learning to predict stable actions on a low-dimensional manifold using a DiT backbone.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.15143","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"NaviGNN: Multi-Agent Reinforcement Learning and Graph Neural Network for Sustainable Mobility in Futuristic Smart Cities","primary_cat":"cs.AI","submitted_at":"2025-07-20T22:35:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"NaviGNN combines RL and GNNs in multi-agent simulations to achieve 7.8-8.4 minute average commutes, over 89% satisfaction, and above 91% reachability in extreme urban morphologies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2403.09631","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","primary_cat":"cs.CV","submitted_at":"2024-03-14T17:58:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"3D-VLA is a new embodied foundation model that uses a 3D LLM plus aligned diffusion models to generate future images and point clouds for improved reasoning and action planning in 3D environments.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2311.16570","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Epistemic Limits of Empirical Finance: Causal Reductionism and Self-Reference","primary_cat":"q-fin.GN","submitted_at":"2023-11-28T07:28:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Empirical finance is limited to ex post causal inference because self-reference in markets makes unidirectional causation unstable or fallacious.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2305.01626","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Basic syntax from speech: Spontaneous concatenation in unsupervised deep neural networks","primary_cat":"cs.CL","submitted_at":"2023-05-02T17:38:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"ciwGAN and fiwGAN models trained on isolated words spontaneously generate concatenated multi-word outputs and display early compositionality precursors.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}