{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/decision-making/papers/6","list_of":"/task/decision-making","task":"Decision Making","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":6,"pages_in_order":124,"rows_per_page":100,"rows":[501,600],"of":12311,"counts":{"archive_papers_tagged":12311,"with_a_code_link":2946,"where_syntology_ran_a_sample":678,"not_listed_spam_title":0,"listed":12311,"listed_where_code_ran":678,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":560,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":560,"listed_every_run_a_failure_of_syntologys_instrument":118,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/decision-making","prev":"/task/decision-making/papers/5","next":"/task/decision-making/papers/7","papers":[{"url":"/paper/value-gradient-sampler-sampling-as-sequential","slug":"value-gradient-sampler-sampling-as-sequential","title":"Value Gradient Sampler: Sampling as Sequential Decision Making","date":"2025-02-18","arxiv_id":"2502.13280","repositories_listed":1,"syntology":null},{"url":"/paper/nuclear-deployed-analyzing-catastrophic-risks","slug":"nuclear-deployed-analyzing-catastrophic-risks","title":"Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents","date":"2025-02-17","arxiv_id":"2502.11355","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-expert-prompt-for-large-language","slug":"hierarchical-expert-prompt-for-large-language","title":"Hierarchical Expert Prompt for Large-Language-Model: An Approach Defeat Elite AI in TextStarCraft II for the First Time","date":"2025-02-16","arxiv_id":"2502.11122","repositories_listed":1,"syntology":null},{"url":"/paper/automated-hypothesis-validation-with-agentic","slug":"automated-hypothesis-validation-with-agentic","title":"Automated Hypothesis Validation with Agentic Sequential Falsifications","date":"2025-02-14","arxiv_id":"2502.09858","repositories_listed":1,"syntology":null},{"url":"/paper/decision-information-meets-large-language","slug":"decision-information-meets-large-language","title":"Decision Information Meets Large Language Models: The Future of Explainable Operations Research","date":"2025-02-14","arxiv_id":"2502.09994","repositories_listed":1,"syntology":null},{"url":"/paper/hadl-framework-for-noise-resilient-long-term","slug":"hadl-framework-for-noise-resilient-long-term","title":"HADL Framework for Noise Resilient Long-Term Time Series Forecasting","date":"2025-02-14","arxiv_id":"2502.10569","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-solve-the-min-max-mixed-shelves","slug":"learning-to-solve-the-min-max-mixed-shelves","title":"Learning to Solve the Min-Max Mixed-Shelves Picker-Routing Problem via Hierarchical and Parallel Decoding","date":"2025-02-14","arxiv_id":"2502.10233","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-to-solve-the-min-max-mixed-shelves#ran","syntology_url":"https://syntology.ai/paper/2502.10233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.10233"}},"official":{"repos":["ltluttmann/marl4msprp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/segx-improving-interpretability-of-clinical","slug":"segx-improving-interpretability-of-clinical","title":"SegX: Improving Interpretability of Clinical Image Diagnosis with Segmentation-based Enhancement","date":"2025-02-14","arxiv_id":"2502.10296","repositories_listed":1,"syntology":null},{"url":"/paper/use-of-air-quality-sensor-network-data-for","slug":"use-of-air-quality-sensor-network-data-for","title":"Use of Air Quality Sensor Network Data for Real-time Pollution-Aware POI Suggestion","date":"2025-02-13","arxiv_id":"2502.09155","repositories_listed":1,"syntology":null},{"url":"/paper/human-decision-making-is-susceptible-to-ai","slug":"human-decision-making-is-susceptible-to-ai","title":"Human Decision-making is Susceptible to AI-driven Manipulation","date":"2025-02-11","arxiv_id":"2502.07663","repositories_listed":1,"syntology":null},{"url":"/paper/habitizing-diffusion-planning-for-efficient","slug":"habitizing-diffusion-planning-for-efficient","title":"Habitizing Diffusion Planning for Efficient and Effective Decision Making","date":"2025-02-10","arxiv_id":"2502.06401","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-the-capabilities-of-large-language","slug":"unveiling-the-capabilities-of-large-language","title":"Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement","date":"2025-02-10","arxiv_id":"2502.06207","repositories_listed":1,"syntology":null},{"url":"/paper/learning-conformal-abstention-policies-for","slug":"learning-conformal-abstention-policies-for","title":"Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models","date":"2025-02-08","arxiv_id":"2502.06884","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/learning-conformal-abstention-policies-for#ran","syntology_url":"https://syntology.ai/paper/2502.06884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06884"}},"official":{"repos":["sinatayebati/vlm-uncertainty"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/the-odyssey-of-the-fittest-can-agents-survive","slug":"the-odyssey-of-the-fittest-can-agents-survive","title":"The Odyssey of the Fittest: Can Agents Survive and Still Be Good?","date":"2025-02-08","arxiv_id":"2502.05442","repositories_listed":1,"syntology":null},{"url":"/paper/agentic-reasoning-reasoning-llms-with-tools","slug":"agentic-reasoning-reasoning-llms-with-tools","title":"Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research","date":"2025-02-07","arxiv_id":"2502.04644","repositories_listed":1,"syntology":null},{"url":"/paper/how-inclusively-do-lms-perceive-social-and","slug":"how-inclusively-do-lms-perceive-social-and","title":"How Inclusively do LMs Perceive Social and Moral Norms?","date":"2025-02-04","arxiv_id":"2502.02696","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-guidance-of-flow-matching","slug":"on-the-guidance-of-flow-matching","title":"On the Guidance of Flow Matching","date":"2025-02-04","arxiv_id":"2502.02150","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/on-the-guidance-of-flow-matching#ran","syntology_url":"https://syntology.ai/paper/2502.02150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02150"}},"official":{"repos":["ai4science-westlakeu/flow_guidance"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rtbagent-a-llm-based-agent-system-for-real","slug":"rtbagent-a-llm-based-agent-system-for-real","title":"RTBAgent: A LLM-based Agent System for Real-Time Bidding","date":"2025-02-02","arxiv_id":"2502.00792","repositories_listed":1,"syntology":null},{"url":"/paper/costi-consistency-models-for-a-faster-spatio","slug":"costi-consistency-models-for-a-faster-spatio","title":"CoSTI: Consistency Models for (a faster) Spatio-Temporal Imputation","date":"2025-01-31","arxiv_id":"2501.19364","repositories_listed":1,"syntology":null},{"url":"/paper/do-llms-strategically-reveal-conceal-and","slug":"do-llms-strategically-reveal-conceal-and","title":"Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game","date":"2025-01-31","arxiv_id":"2501.19398","repositories_listed":1,"syntology":null},{"url":"/paper/vintix-action-model-via-in-context","slug":"vintix-action-model-via-in-context","title":"Vintix: Action Model via In-Context Reinforcement Learning","date":"2025-01-31","arxiv_id":"2501.19400","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vintix-action-model-via-in-context#ran","syntology_url":"https://syntology.ai/paper/2501.19400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.19400"}},"official":{"repos":["dunnolab/vintix"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/is-conversational-xai-all-you-need-human-ai","slug":"is-conversational-xai-all-you-need-human-ai","title":"Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant","date":"2025-01-29","arxiv_id":"2501.17546","repositories_listed":1,"syntology":null},{"url":"/paper/rdmm-fine-tuned-llm-models-for-on-device","slug":"rdmm-fine-tuned-llm-models-for-on-device","title":"RDMM: Fine-Tuned LLM Models for On-Device Robotic Decision Making with Enhanced Contextual Awareness in Specific Domains","date":"2025-01-28","arxiv_id":"2501.16899","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-visual-inspection-capability-of","slug":"enhancing-visual-inspection-capability-of","title":"Enhancing Visual Inspection Capability of Multi-Modal Large Language Models on Medical Time Series with Supportive Conformalized and Interpretable Small Specialized Models","date":"2025-01-27","arxiv_id":"2501.16215","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-diverse-perspectives-a-multi-agent","slug":"harnessing-diverse-perspectives-a-multi-agent","title":"Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs","date":"2025-01-27","arxiv_id":"2501.15791","repositories_listed":1,"syntology":null},{"url":"/paper/safe-gradient-flow-for-bilevel-optimization","slug":"safe-gradient-flow-for-bilevel-optimization","title":"Safe Gradient Flow for Bilevel Optimization","date":"2025-01-27","arxiv_id":"2501.16520","repositories_listed":1,"syntology":null},{"url":"/paper/towards-explainable-multimodal-depression","slug":"towards-explainable-multimodal-depression","title":"Towards Explainable Multimodal Depression Recognition for Clinical Interviews","date":"2025-01-27","arxiv_id":"2501.16106","repositories_listed":1,"syntology":null},{"url":"/paper/an-ai-driven-live-systematic-reviews-in-the","slug":"an-ai-driven-live-systematic-reviews-in-the","title":"An AI-Driven Live Systematic Reviews in the Brain-Heart Interconnectome: Minimizing Research Waste and Advancing Evidence Synthesis","date":"2025-01-25","arxiv_id":"2501.17181","repositories_listed":1,"syntology":null},{"url":"/paper/inductive-biases-for-zero-shot-systematic","slug":"inductive-biases-for-zero-shot-systematic","title":"Inductive Biases for Zero-shot Systematic Generalization in Language-informed Reinforcement Learning","date":"2025-01-25","arxiv_id":"2501.15270","repositories_listed":1,"syntology":null},{"url":"/paper/depressionx-knowledge-infused-residual","slug":"depressionx-knowledge-infused-residual","title":"DepressionX: Knowledge Infused Residual Attention for Explainable Depression Severity Assessment","date":"2025-01-24","arxiv_id":"2501.14985","repositories_listed":1,"syntology":null},{"url":"/paper/reducing-action-space-for-deep-reinforcement","slug":"reducing-action-space-for-deep-reinforcement","title":"Reducing Action Space for Deep Reinforcement Learning via Causal Effect Estimation","date":"2025-01-24","arxiv_id":"2501.14543","repositories_listed":1,"syntology":null},{"url":"/paper/ai-biases-towards-rich-and-powerful-surnames","slug":"ai-biases-towards-rich-and-powerful-surnames","title":"Algorithmic Inheritance: Surname Bias in AI Decisions Reinforces Intergenerational Inequality","date":"2025-01-23","arxiv_id":"2501.19407","repositories_listed":1,"syntology":null},{"url":"/paper/human-alignment-influences-the-utility-of-ai","slug":"human-alignment-influences-the-utility-of-ai","title":"Human-Alignment Influences the Utility of AI-assisted Decision Making","date":"2025-01-23","arxiv_id":"2501.14035","repositories_listed":1,"syntology":null},{"url":"/paper/making-reliable-and-flexible-decisions-in","slug":"making-reliable-and-flexible-decisions-in","title":"Making Reliable and Flexible Decisions in Long-tailed Classification","date":"2025-01-23","arxiv_id":"2501.14090","repositories_listed":1,"syntology":null},{"url":"/paper/filmagent-a-multi-agent-framework-for-end-to","slug":"filmagent-a-multi-agent-framework-for-end-to","title":"FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces","date":"2025-01-22","arxiv_id":"2501.12909","repositories_listed":1,"syntology":null},{"url":"/paper/utilising-deep-learning-to-elicit-expert","slug":"utilising-deep-learning-to-elicit-expert","title":"Utilising Deep Learning to Elicit Expert Uncertainty","date":"2025-01-21","arxiv_id":"2501.11813","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-uncertainty-estimation-in-semantic","slug":"enhancing-uncertainty-estimation-in-semantic","title":"Enhancing Uncertainty Estimation in Semantic Segmentation via Monte-Carlo Frequency Dropout","date":"2025-01-20","arxiv_id":"2501.11258","repositories_listed":1,"syntology":null},{"url":"/paper/mygo-multiplex-cot-a-method-for-self","slug":"mygo-multiplex-cot-a-method-for-self","title":"MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking","date":"2025-01-20","arxiv_id":"2501.13117","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-attention-during-dimensional-shifts","slug":"modeling-attention-during-dimensional-shifts","title":"Modeling Attention during Dimensional Shifts with Counterfactual and Delayed Feedback","date":"2025-01-19","arxiv_id":"2501.11161","repositories_listed":1,"syntology":null},{"url":"/paper/bias-in-decision-making-for-ai-s-ethical","slug":"bias-in-decision-making-for-ai-s-ethical","title":"Bias in Decision-Making for AI's Ethical Dilemmas: A Comparative Study of ChatGPT and Claude","date":"2025-01-17","arxiv_id":"2501.10484","repositories_listed":1,"syntology":null},{"url":"/paper/ns-gym-open-source-simulation-environments","slug":"ns-gym-open-source-simulation-environments","title":"NS-Gym: Open-Source Simulation Environments and Benchmarks for Non-Stationary Markov Decision Processes","date":"2025-01-16","arxiv_id":"2501.09646","repositories_listed":1,"syntology":null},{"url":"/paper/on-learning-informative-trajectory-embeddings","slug":"on-learning-informative-trajectory-embeddings","title":"On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression","date":"2025-01-16","arxiv_id":"2501.09327","repositories_listed":1,"syntology":null},{"url":"/paper/ansr-dt-an-adaptive-neuro-symbolic-learning","slug":"ansr-dt-an-adaptive-neuro-symbolic-learning","title":"ANSR-DT: An Adaptive Neuro-Symbolic Learning and Reasoning Framework for Digital Twins","date":"2025-01-15","arxiv_id":"2501.08561","repositories_listed":1,"syntology":null},{"url":"/paper/visual-wetlandbirds-dataset-bird-species","slug":"visual-wetlandbirds-dataset-bird-species","title":"Visual WetlandBirds Dataset: Bird Species Identification and Behavior Recognition in Videos","date":"2025-01-15","arxiv_id":"2501.08931","repositories_listed":1,"syntology":null},{"url":"/paper/fairttts-a-tree-test-time-simulation-method","slug":"fairttts-a-tree-test-time-simulation-method","title":"FairTTTS: A Tree Test Time Simulation Method for Fairness-Aware Classification","date":"2025-01-14","arxiv_id":"2501.08155","repositories_listed":1,"syntology":null},{"url":"/paper/leapvad-a-leap-in-autonomous-driving-via","slug":"leapvad-a-leap-in-autonomous-driving-via","title":"LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking","date":"2025-01-14","arxiv_id":"2501.08168","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/leapvad-a-leap-in-autonomous-driving-via#ran","syntology_url":"https://syntology.ai/paper/2501.08168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08168"}},"official":null}},{"url":"/paper/optichat-bridging-optimization-models-and","slug":"optichat-bridging-optimization-models-and","title":"OptiChat: Bridging Optimization Models and Practitioners with Large Language Models","date":"2025-01-14","arxiv_id":"2501.08406","repositories_listed":1,"syntology":null},{"url":"/paper/procedural-fairness-and-its-relationship-with","slug":"procedural-fairness-and-its-relationship-with","title":"Procedural Fairness and Its Relationship with Distributive Fairness in Machine Learning","date":"2025-01-12","arxiv_id":"2501.06753","repositories_listed":1,"syntology":null},{"url":"/paper/o1-replication-journey-part-3-inference-time","slug":"o1-replication-journey-part-3-inference-time","title":"O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning","date":"2025-01-11","arxiv_id":"2501.06458","repositories_listed":1,"syntology":null},{"url":"/paper/mechanistic-understanding-and-validation-of","slug":"mechanistic-understanding-and-validation-of","title":"Mechanistic understanding and validation of large AI models with SemanticLens","date":"2025-01-09","arxiv_id":"2501.05398","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mechanistic-understanding-and-validation-of#ran","syntology_url":"https://syntology.ai/paper/2501.05398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.05398"}},"official":{"repos":["jim-berend/semanticlens"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/uav-vla-vision-language-action-system-for","slug":"uav-vla-vision-language-action-system-for","title":"UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generation","date":"2025-01-09","arxiv_id":"2501.05014","repositories_listed":1,"syntology":null},{"url":"/paper/who-does-the-giant-number-pile-like-best","slug":"who-does-the-giant-number-pile-like-best","title":"Who Does the Giant Number Pile Like Best: Analyzing Fairness in Hiring Contexts","date":"2025-01-08","arxiv_id":"2501.04316","repositories_listed":1,"syntology":null},{"url":"/paper/co-activation-graph-analysis-of-safety","slug":"co-activation-graph-analysis-of-safety","title":"Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies","date":"2025-01-06","arxiv_id":"2501.03142","repositories_listed":1,"syntology":null},{"url":"/paper/icfnet-integrated-cross-modal-fusion-network","slug":"icfnet-integrated-cross-modal-fusion-network","title":"ICFNet: Integrated Cross-modal Fusion Network for Survival Prediction","date":"2025-01-06","arxiv_id":"2501.02778","repositories_listed":1,"syntology":null},{"url":"/paper/mixture-of-experts-graph-transformers-for","slug":"mixture-of-experts-graph-transformers-for","title":"Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection","date":"2025-01-06","arxiv_id":"2501.03432","repositories_listed":1,"syntology":null},{"url":"/paper/prmbench-a-fine-grained-and-challenging","slug":"prmbench-a-fine-grained-and-challenging","title":"PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models","date":"2025-01-06","arxiv_id":"2501.03124","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prmbench-a-fine-grained-and-challenging#ran","syntology_url":"https://syntology.ai/paper/2501.03124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.03124"}},"official":{"repos":["ssmisya/PRMBench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lattereview-a-multi-agent-framework-for","slug":"lattereview-a-multi-agent-framework-for","title":"LatteReview: A Multi-Agent Framework for Systematic Review Automation Using Large Language Models","date":"2025-01-05","arxiv_id":"2501.05468","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-cvar-leveraging-static-spectral-risk","slug":"beyond-cvar-leveraging-static-spectral-risk","title":"Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning","date":"2025-01-03","arxiv_id":"2501.02087","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/beyond-cvar-leveraging-static-spectral-risk#ran","syntology_url":"https://syntology.ai/paper/2501.02087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.02087"}},"official":{"repos":["mehrdadmoghimi/qrsrm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/mirage-exploring-how-large-language-models","slug":"mirage-exploring-how-large-language-models","title":"MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive Environments","date":"2025-01-03","arxiv_id":"2501.01652","repositories_listed":1,"syntology":null},{"url":"/paper/a-tale-of-two-imperatives-privacy-and","slug":"a-tale-of-two-imperatives-privacy-and","title":"Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquiry","date":"2024-12-30","arxiv_id":"2412.20798","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-ai-for-automatic-classification-of","slug":"leveraging-ai-for-automatic-classification-of","title":"Leveraging AI for Automatic Classification of PCOS Using Ultrasound Imaging","date":"2024-12-30","arxiv_id":"2501.01984","repositories_listed":1,"syntology":null},{"url":"/paper/plancraft-an-evaluation-dataset-for-planning","slug":"plancraft-an-evaluation-dataset-for-planning","title":"Plancraft: an evaluation dataset for planning with LLM agents","date":"2024-12-30","arxiv_id":"2412.21033","repositories_listed":1,"syntology":null},{"url":"/paper/a-fuzzy-rank-based-ensemble-of-cnn-models-for-1","slug":"a-fuzzy-rank-based-ensemble-of-cnn-models-for-1","title":"A fuzzy rank-based ensemble of CNN models for MRI segmentation","date":"2024-12-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/modality-projection-universal-model-for","slug":"modality-projection-universal-model-for","title":"Modality-Projection Universal Model for Comprehensive Full-Body Medical Imaging Segmentation","date":"2024-12-26","arxiv_id":"2412.19026","repositories_listed":1,"syntology":null},{"url":"/paper/constraint-adaptive-policy-switching-for","slug":"constraint-adaptive-policy-switching-for","title":"Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning","date":"2024-12-25","arxiv_id":"2412.18946","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/constraint-adaptive-policy-switching-for#ran","syntology_url":"https://syntology.ai/paper/2412.18946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18946"}},"official":{"repos":["yassinech/caps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/big-moe-bypass-isolated-gating-moe-for","slug":"big-moe-bypass-isolated-gating-moe-for","title":"BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing","date":"2024-12-24","arxiv_id":"2412.18065","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-optimization-of-portfolio-allocation","slug":"dynamic-optimization-of-portfolio-allocation","title":"A Deep Reinforcement Learning Framework for Dynamic Portfolio Optimization: Evidence from China's Stock Market","date":"2024-12-24","arxiv_id":"2412.18563","repositories_listed":1,"syntology":null},{"url":"/paper/minsstudio-a-streamlined-package-for","slug":"minsstudio-a-streamlined-package-for","title":"MineStudio: A Streamlined Package for Minecraft AI Agent Development","date":"2024-12-24","arxiv_id":"2412.18293","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minsstudio-a-streamlined-package-for#ran","syntology_url":"https://syntology.ai/paper/2412.18293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18293"}},"official":{"repos":["craftjarvis/minestudio"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-dual-perspective-metaphor-detection","slug":"a-dual-perspective-metaphor-detection","title":"A Dual-Perspective Metaphor Detection Framework Using Large Language Models","date":"2024-12-23","arxiv_id":"2412.17332","repositories_listed":1,"syntology":null},{"url":"/paper/carl-gt-evaluating-causal-reasoning","slug":"carl-gt-evaluating-causal-reasoning","title":"CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models","date":"2024-12-23","arxiv_id":"2412.17970","repositories_listed":1,"syntology":null},{"url":"/paper/legalagentbench-evaluating-llm-agents-in","slug":"legalagentbench-evaluating-llm-agents-in","title":"LegalAgentBench: Evaluating LLM Agents in Legal Domain","date":"2024-12-23","arxiv_id":"2412.17259","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-learning-with-uncertainty","slug":"multimodal-learning-with-uncertainty","title":"Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion","date":"2024-12-23","arxiv_id":"2412.18024","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-sampling-scaling-inference","slug":"multi-agent-sampling-scaling-inference","title":"Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration","date":"2024-12-22","arxiv_id":"2412.17061","repositories_listed":1,"syntology":null},{"url":"/paper/breaking-the-context-bottleneck-on-long-time","slug":"breaking-the-context-bottleneck-on-long-time","title":"Breaking the Context Bottleneck on Long Time Series Forecasting","date":"2024-12-21","arxiv_id":"2412.16572","repositories_listed":1,"syntology":null},{"url":"/paper/quantifying-the-benefit-of-load-uncertainty","slug":"quantifying-the-benefit-of-load-uncertainty","title":"Quantifying the benefit of load uncertainty reduction for the design of district energy systems under grid constraints using the Value of Information","date":"2024-12-20","arxiv_id":"2412.16105","repositories_listed":1,"syntology":null},{"url":"/paper/segmentation-of-arbitrary-features-in-very","slug":"segmentation-of-arbitrary-features-in-very","title":"Segmentation of arbitrary features in very high resolution remote sensing imagery","date":"2024-12-20","arxiv_id":"2412.16046","repositories_listed":1,"syntology":null},{"url":"/paper/a-shapley-value-estimation-speedup-for","slug":"a-shapley-value-estimation-speedup-for","title":"A Shapley Value Estimation Speedup for Efficient Explainable Quantum AI","date":"2024-12-19","arxiv_id":"2412.14639","repositories_listed":1,"syntology":null},{"url":"/paper/defeasible-visual-entailment-benchmark","slug":"defeasible-visual-entailment-benchmark","title":"Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization","date":"2024-12-19","arxiv_id":"2412.16232","repositories_listed":1,"syntology":null},{"url":"/paper/spatiotemporally-coherent-probabilistic","slug":"spatiotemporally-coherent-probabilistic","title":"A Generative Framework for Probabilistic, Spatiotemporally Coherent Downscaling of Climate Simulation","date":"2024-12-19","arxiv_id":"2412.15361","repositories_listed":1,"syntology":null},{"url":"/paper/previous-knowledge-utilization-in-online","slug":"previous-knowledge-utilization-in-online","title":"Previous Knowledge Utilization In Online Anytime Belief Space Planning","date":"2024-12-17","arxiv_id":"2412.13128","repositories_listed":1,"syntology":null},{"url":"/paper/embodied-cot-distillation-from-llm-to-off-the","slug":"embodied-cot-distillation-from-llm-to-off-the","title":"Embodied CoT Distillation From LLM To Off-the-shelf Agents","date":"2024-12-16","arxiv_id":"2412.11499","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/embodied-cot-distillation-from-llm-to-off-the#ran","syntology_url":"https://syntology.ai/paper/2412.11499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11499"}},"official":{"repos":["osu-nlp-group/llm-planner"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/revelations-a-decidable-class-of-pomdps-with","slug":"revelations-a-decidable-class-of-pomdps-with","title":"Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives","date":"2024-12-16","arxiv_id":"2412.12063","repositories_listed":1,"syntology":null},{"url":"/paper/auctionnet-a-novel-benchmark-for-decision","slug":"auctionnet-a-novel-benchmark-for-decision","title":"AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games","date":"2024-12-14","arxiv_id":"2412.10798","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/auctionnet-a-novel-benchmark-for-decision#ran","syntology_url":"https://syntology.ai/paper/2412.10798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10798"}},"official":{"repos":["alimama-tech/auctionnet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/explainable-fuzzy-neural-network-with-multi","slug":"explainable-fuzzy-neural-network-with-multi","title":"Explainable Fuzzy Neural Network with Multi-Fidelity Reinforcement Learning for Micro-Architecture Design Space Exploration","date":"2024-12-14","arxiv_id":"2412.10754","repositories_listed":1,"syntology":null},{"url":"/paper/gaussianad-gaussian-centric-end-to-end","slug":"gaussianad-gaussian-centric-end-to-end","title":"GaussianAD: Gaussian-Centric End-to-End Autonomous Driving","date":"2024-12-13","arxiv_id":"2412.10371","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gaussianad-gaussian-centric-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2412.10371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10371"}},"official":{"repos":["wzzheng/gaussianad"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/wisead-knowledge-augmented-end-to-end","slug":"wisead-knowledge-augmented-end-to-end","title":"WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language Model","date":"2024-12-13","arxiv_id":"2412.09951","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wisead-knowledge-augmented-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2412.09951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09951"}},"official":{"repos":["wyddmw/WiseAD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/doe-1-closed-loop-autonomous-driving-with","slug":"doe-1-closed-loop-autonomous-driving-with","title":"Doe-1: Closed-Loop Autonomous Driving with Large World Model","date":"2024-12-12","arxiv_id":"2412.09627","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/doe-1-closed-loop-autonomous-driving-with#ran","syntology_url":"https://syntology.ai/paper/2412.09627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09627"}},"official":{"repos":["wzzheng/doe"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/forest-of-thought-scaling-test-time-compute","slug":"forest-of-thought-scaling-test-time-compute","title":"Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning","date":"2024-12-12","arxiv_id":"2412.09078","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":11,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/forest-of-thought-scaling-test-time-compute#ran","syntology_url":"https://syntology.ai/paper/2412.09078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09078"}},"official":{"repos":["iamhankai/Forest-of-Thought"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/detecting-conversational-mental-manipulation","slug":"detecting-conversational-mental-manipulation","title":"Detecting Conversational Mental Manipulation with Intent-Aware Prompting","date":"2024-12-11","arxiv_id":"2412.08414","repositories_listed":1,"syntology":null},{"url":"/paper/genplan-generative-sequence-models-as","slug":"genplan-generative-sequence-models-as","title":"GenPlan: Generative Sequence Models as Adaptive Planners","date":"2024-12-11","arxiv_id":"2412.08565","repositories_listed":1,"syntology":null},{"url":"/paper/learn-how-to-query-from-unlabeled-data","slug":"learn-how-to-query-from-unlabeled-data","title":"Learn How to Query from Unlabeled Data Streams in Federated Learning","date":"2024-12-11","arxiv_id":"2412.08138","repositories_listed":1,"syntology":null},{"url":"/paper/harp-hesitation-aware-reframing-in","slug":"harp-hesitation-aware-reframing-in","title":"HARP: Hesitation-Aware Reframing in Transformer Inference Pass","date":"2024-12-10","arxiv_id":"2412.07282","repositories_listed":1,"syntology":null},{"url":"/paper/how-should-we-represent-history-in","slug":"how-should-we-represent-history-in","title":"How Should We Represent History in Interpretable Models of Clinical Policies?","date":"2024-12-10","arxiv_id":"2412.07895","repositories_listed":1,"syntology":null},{"url":"/paper/digital-transformation-in-the-water","slug":"digital-transformation-in-the-water","title":"Digital Transformation in the Water Distribution System based on the Digital Twins Concept","date":"2024-12-09","arxiv_id":"2412.06694","repositories_listed":1,"syntology":null},{"url":"/paper/discrete-time-distribution-steering-using","slug":"discrete-time-distribution-steering-using","title":"Discrete-Time Distribution Steering using Monte Carlo Tree Search","date":"2024-12-09","arxiv_id":"2412.06220","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-an-overview","slug":"reinforcement-learning-an-overview","title":"Reinforcement Learning: An Overview","date":"2024-12-06","arxiv_id":"2412.05265","repositories_listed":1,"syntology":null},{"url":"/paper/surgbox-agent-driven-operating-room-sandbox","slug":"surgbox-agent-driven-operating-room-sandbox","title":"SurgBox: Agent-Driven Operating Room Sandbox with Surgery Copilot","date":"2024-12-06","arxiv_id":"2412.05187","repositories_listed":1,"syntology":null},{"url":"/paper/deep-causal-inference-for-point-referenced","slug":"deep-causal-inference-for-point-referenced","title":"Deep Causal Inference for Point-referenced Spatial Data with Continuous Treatments","date":"2024-12-05","arxiv_id":"2412.04285","repositories_listed":1,"syntology":null},{"url":"/paper/ai-driven-day-to-day-route-choice","slug":"ai-driven-day-to-day-route-choice","title":"AI-Driven Day-to-Day Route Choice","date":"2024-12-04","arxiv_id":"2412.03338","repositories_listed":1,"syntology":null},{"url":"/paper/are-explanations-helpful-a-comparative","slug":"are-explanations-helpful-a-comparative","title":"Are Explanations Helpful? A Comparative Analysis of Explainability Methods in Skin Lesion Classifiers","date":"2024-12-04","arxiv_id":"2412.03166","repositories_listed":1,"syntology":null}],"record_sha256":"0fa6ebe9fea5ac7b8502434378804664241f11f13334216ecbb7475b24d90578","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}