{"total":17,"items":[{"citing_arxiv_id":"2605.15812","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling","primary_cat":"cs.HC","submitted_at":"2026-05-15T10:06:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CTEM framework links behavioral history to evolving emotional states with user feedback updates, instantiated as Auri agent and tested in a 21-day study showing gains in naturalness, coherence, and emotional harmony.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09826","ref_index":52,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents","primary_cat":"cs.AI","submitted_at":"2026-05-11T00:04:19+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EnactToM is an evolving benchmark of embodied multi-agent tasks that tests functional Theory of Mind by requiring agents to act optimally on implicit beliefs in partially observable 3D environments.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Cognition, 89(1): 25-41, 2003. ISSN 0010-0277. doi: 10.1016/S0010-0277(03)00064-7. [50] Daniel C. Dennett. Beliefs about beliefs.Behavioral and Brain Sciences, 1(4):568-570, 1978. doi: 10.1017/S0140525X00076664. [51] Daniel C. Dennett.The Intentional Stance. MIT Press, Cambridge, MA, 1987. URLhttps://mitpre ss.mit.edu/9780262540537/the-intentional-stance/. [52] Chris L. Baker, Rebecca Saxe, and Joshua B. Tenenbaum. Action understanding as inverse planning. Cognition, 113(3):329-349, 2009. ISSN 0010-0277. doi: 10.1016/j.cognition.2009.07.005. [53] Chris L. Baker, Julian Jara-Ettinger, Rebecca Saxe, and Joshua B. Tenenbaum. Rational quantitative attribution of beliefs, desires and percepts in human mentalizing."},{"citing_arxiv_id":"2605.07947","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Exploring the non-convexity in machine learning using quantum-inspired optimization","primary_cat":"cs.CE","submitted_at":"2026-05-08T16:15:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A quantum-inspired global search method called QIEO outperforms traditional solvers in recovering sparse structures and robust fitting by maintaining a broad view of possible solutions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"To transcend the limitations of both convex relaxations and local heuristics, we pro- pose reframing these non-convex challenges fundamentally as global search problems. In this paper, we introduce a unified optimization framework driven by Quantum- Inspired Evolutionary Optimization (QIEO) [17-19]. Unlike classical metaheuristics such as Genetic Algorithms (GA) [20, 21] or Differential Evolution, which explore the search space via point-to-point transitions, QIEO leverages a probabilistic represen- tation inspired by the quantum mechanical principle of superposition. By encoding candidate structural supports as quantum registers and evolving them through simu- lated quantum rotation gates, the algorithm maintains a coherent, probabilistic view"},{"citing_arxiv_id":"2605.07289","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"On the Complexity of the Matching Problem of Regular Expressions with Backreferences","primary_cat":"cs.DS","submitted_at":"2026-05-08T05:55:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"k-REWB matching cannot be solved in O(n to the 2k minus epsilon) time under SETH, is W[2]-hard parameterized by expression length, and 2-use 2-REWBs require superlinear time unless triangle detection does; 1-use REWBs admit an O(n log squared n) algorithm.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"doi:10.4171/Automata-1/18. [24] T. H. Cormen, C. E. Leiserson, R. L. Rivest, and C. Stein. Introduction to Algorithms, fourth edition . MIT Press, 2022. URL: https://mitpress.mit.edu/9780262046305/ introduction-to-algorithms/. [25] R. Cox. Regular expression matching can be simple and fast. https://swtch.com/~rsc/ regexp/regexp1.html, January 2007. [26] R. Cox. Regular expression matching in the wild. https://swtch.com/~rsc/regexp/ regexp3.html, mar 2010. [27] M. Crochemore. An optimal algorithm for computing the repetitions in a word. Information Processing Letters, 12(5):244-250, 1981. doi:10.1016/0020-0190(81)90024-7. [28] M. Crochemore, C. Hancart, and T. Lecroq. Algorithms on Strings . Cambridge University"},{"citing_arxiv_id":"2605.07031","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Deciding DFA-Primality is NP-Hard","primary_cat":"cs.FL","submitted_at":"2026-05-07T23:21:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Deciding DFA primality is NP-hard, established by reduction from propositional satisfiability using a characterization of primality for a relevant class of automata.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00768","ref_index":24,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Characterizing the Expressivity of Local Attention in Transformers","primary_cat":"cs.CL","submitted_at":"2026-05-01T16:30:52+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Local attention strictly enlarges the class of regular languages recognizable by fixed-precision transformers by introducing a second temporal operator in LTL, with global and local attention being expressively complementary.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00282","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Developing an AI Concept Envisioning Toolkit to Support Reflective Juxtaposition of Values and Harms","primary_cat":"cs.HC","submitted_at":"2026-04-30T22:47:26+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A new toolkit with cards and maps enables AI designers to juxtapose values and harms in early concept stages, shown valuable in designer surveys and interviews.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"tioners in activities like ideation and collaborative reasoning. Early contributions, such as \"design by playing\" [28] and experience pro- totyping [16], illustrate how mock-ups and tangible artifacts allow designers to explore scenarios in ways that are discussable, testable, and manipulable. Toolkits have since proliferated across multiple domains, from service design [93] to speculative design [27] and inclusive design [1, 38]. Across these studies, a consistent insight emerges that tool adoption and effectiveness are contingent on alignment with existing workflows [62, 95]. In particular, designers engage more readily with resources embedded in familiar contexts. Context-switching imposes cognitive and practical friction that reduces sustained engagement [51]."},{"citing_arxiv_id":"2604.21878","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Gradual Voluntary Participation: A Framework for Participatory AI Governance in Journalism","primary_cat":"cs.HC","submitted_at":"2026-04-23T17:21:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The study proposes the Gradual Voluntary Participation (GVP) framework to reconceptualize participatory AI governance in journalism as a gradual and voluntary process using a bidimensional matrix.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"organizations such as newsrooms, power operates through direct control, agenda-setting, preference-shaping, and the normalization of certain assumptions and discourses over others [ 17, 22, 33, 52]. This matters for AI because design and deployment do not introduce tools into neutral settings; they can also encode, formalize, and stabilize existing institutional logics [ 44, 66, 68]. Workflow technologies act not only as coordination mechanisms but also as organizationalaccounting devicesthat render work visible, allocable, and subject to managerial oversight [ 30]. In journalism, where editorial authority is already contested across managerial, commercial, technical, and professional lines [13, 32, 72], questions of participation are inseparable from questions of who defines the goals of AI adoption,"},{"citing_arxiv_id":"2604.19423","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Allow Me Into Your Dream: A Handshake-and-Pull Protocol for Sharing Mixed Realities in Spontaneous Encounters","primary_cat":"cs.HC","submitted_at":"2026-04-21T12:53:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TouchPort collapses the multi-stage process of discovering, consenting to, and syncing mixed reality encounters into one embodied handshake-and-pull gesture.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[55] studied embodied phone-to-phone sharing. Nielsen et al. [66] proposed JuxtaPinch for co-located pairing. Hamilton and Wig- dor [37] explored embodied transfer metaphors. Voelker et al. [92] demonstrate calibration-free cross-device collaboration through gaze and touch. Marquardt et al. [58] extend cross-device interac- tion to spatially-aware in-air device formations. Emmert et al. [26] present recent cross-device transfer advances. Consumer systems- AirDrop [3], Quick Share (formerly Nearby Share) [ 29], and the now-defunct Bump-implement a lightweight protocol: discover, request, accept, transfer. These systems solve a simpler version of the encounter problem. But they transferfiles. MR encounter requires transferringworld access-spatial alignment, object per-"},{"citing_arxiv_id":"2604.19341","ref_index":64,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Evaluation-driven Scaling for Scientific Discovery","primary_cat":"cs.LG","submitted_at":"2026-04-21T11:24:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"7 Appendix . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 72 2 Evaluation-driven Scaling for Scientific Discovery 1 Introduction Scientific discoveries are open-ended: progress toward unknown high-quality solutions typically requires repeated cycles of research, proposal, experiment, and refinement [64, 89]. Whether the objective is to find new mathematical constructions [ 9, 16, 46, 82, 92, 95], engineer high-performance GPU kernels [ 1, 12, 19], optimize quantum circuits [ 66, 70, 132], or discover new biological mechanisms [ 10, 71, 77, 146], cycles of trial-and-error guided by external feedback, often from physical or computational experiments, are the"},{"citing_arxiv_id":"2604.17820","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Raven: Rethinking Automated Assessment for Scratch Programs via Video-Grounded Evaluation","primary_cat":"cs.SE","submitted_at":"2026-04-20T05:19:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Raven automates Scratch program assessment by having instructors specify task-level video generation rules and using LLMs to analyze resulting videos for behavioral compliance, outperforming prior tools on real student submissions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Educators must either set fewer assessment tasks or resign themselves to a greatly increased marking load [9], making human-centric evaluation increasingly unsustainable [2]. Beyond scalability, a more fundamental challenge lies in assessment validity. As the Scratch creator Mitchel Resnick argues, current automated methods often fall into the trap of measuring \"what is easy to measure, rather than what is important\" [ 45]. Static analysis fails to capture the dynamic, interactive nature of creative coding, obscuring the actual learning process. While the program code is visible, the visual and interactive execution behavior-the primary learning artifact in Scratch-often remains unexamined. Thus, there remains a critical dearth of valid tools [ 33] capable of bridging the gap between static code structure and dynamic visual execution."},{"citing_arxiv_id":"2604.12519","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Instantiating Bayesian CVaR lower bounds in Interactive Decision Making Problems","primary_cat":"cs.LG","submitted_at":"2026-04-14T09:54:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The authors instantiate a generalized-Fano framework using squared Hellinger distance to derive explicit Bayesian CVaR lower bounds for interactive decision problems including Gaussian bandits.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09657","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Prints in the Magnetic Dust: Robust Similarity Search in Legacy Media Images Using Checksum Count Vectors","primary_cat":"cs.CV","submitted_at":"2026-03-30T12:01:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Checksum Count Vectors enable robust similarity search to identify duplicate and variant legacy media recordings with high accuracy despite substantial data damage.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.11398","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Evolution With Purpose: Hierarchy-Informed Optimization of Whole-Brain Models","primary_cat":"cs.NE","submitted_at":"2026-02-11T22:03:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Hierarchy-informed curricular optimization of heterogeneous whole-brain models enables generalization to new subjects and prediction of behavioral abilities from parameters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.15000","ref_index":59,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Bonsai: Compiling Queries to Pruned Tree Traversals","primary_cat":"cs.PL","submitted_at":"2025-11-19T00:50:20+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":"2404.11591","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The EDGE Language: Extended General Einsums for Graph Algorithms","primary_cat":"cs.DS","submitted_at":"2024-04-17T17:42:48+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":"2202.07609","ref_index":51,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Evolution of U.S. Retail Concentration","primary_cat":"econ.GN","submitted_at":"2022-02-15T17:53:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Local retail concentration increased almost as much as national concentration from 1992 to 2012, mainly from multi-market firm expansion, and accounts for one-quarter to one-third of the rise in retail gross margins.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}