{"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/2","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":2,"pages_in_order":124,"rows_per_page":100,"rows":[101,200],"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","next":"/task/decision-making/papers/3","papers":[{"url":"/paper/fairness-beyond-disparate-treatment-disparate","slug":"fairness-beyond-disparate-treatment-disparate","title":"Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment","date":"2016-10-26","arxiv_id":"1610.08452","repositories_listed":3,"syntology":null},{"url":"/paper/model-free-episodic-control","slug":"model-free-episodic-control","title":"Model-Free Episodic Control","date":"2016-06-14","arxiv_id":"1606.04460","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/model-free-episodic-control#ran","syntology_url":"https://syntology.ai/paper/1606.04460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.04460"}},"official":null}},{"url":"/paper/bowfire-detection-of-fire-in-still-images-by","slug":"bowfire-detection-of-fire-in-still-images-by","title":"BoWFire: Detection of Fire in Still Images by Integrating Pixel Color and Texture Analysis","date":"2015-06-10","arxiv_id":"1506.03495","repositories_listed":3,"syntology":null},{"url":"/paper/twitter-mood-predicts-the-stock-market","slug":"twitter-mood-predicts-the-stock-market","title":"Twitter mood predicts the stock market","date":"2010-10-14","arxiv_id":"1010.3003","repositories_listed":3,"syntology":null},{"url":"/paper/ragen-understanding-self-evolution-in-llm","slug":"ragen-understanding-self-evolution-in-llm","title":"RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning","date":"2025-04-24","arxiv_id":"2504.20073","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/ragen-understanding-self-evolution-in-llm#ran","syntology_url":"https://syntology.ai/paper/2504.20073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.20073"}},"official":{"repos":["ragen-ai/ragen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/charms-cognitive-hierarchical-agent-with","slug":"charms-cognitive-hierarchical-agent-with","title":"CHARMS: A Cognitive Hierarchical Agent for Reasoning and Motion Stylization in Autonomous Driving","date":"2025-04-03","arxiv_id":"2504.02450","repositories_listed":2,"syntology":null},{"url":"/paper/pc-agent-a-hierarchical-multi-agent","slug":"pc-agent-a-hierarchical-multi-agent","title":"PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC","date":"2025-02-20","arxiv_id":"2502.14282","repositories_listed":2,"syntology":null},{"url":"/paper/a-survey-of-world-models-for-autonomous","slug":"a-survey-of-world-models-for-autonomous","title":"A Survey of World Models for Autonomous Driving","date":"2025-01-20","arxiv_id":"2501.11260","repositories_listed":2,"syntology":null},{"url":"/paper/latent-reward-llm-empowered-credit-assignment","slug":"latent-reward-llm-empowered-credit-assignment","title":"Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning","date":"2024-12-15","arxiv_id":"2412.11120","repositories_listed":2,"syntology":null},{"url":"/paper/gpd-1-generative-pre-training-for-driving","slug":"gpd-1-generative-pre-training-for-driving","title":"GPD-1: Generative Pre-training for Driving","date":"2024-12-11","arxiv_id":"2412.08643","repositories_listed":2,"syntology":null},{"url":"/paper/mc-nest-enhancing-mathematical-reasoning-in","slug":"mc-nest-enhancing-mathematical-reasoning-in","title":"MC-NEST -- Enhancing Mathematical Reasoning in Large Language Models with a Monte Carlo Nash Equilibrium Self-Refine Tree","date":"2024-11-23","arxiv_id":"2411.15645","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-selection-stability-of-stability","slug":"on-the-selection-stability-of-stability","title":"On the Selection Stability of Stability Selection and Its Applications","date":"2024-11-14","arxiv_id":"2411.09097","repositories_listed":2,"syntology":null},{"url":"/paper/game-theoretic-llm-agent-workflow-for","slug":"game-theoretic-llm-agent-workflow-for","title":"Game-theoretic LLM: Agent Workflow for Negotiation Games","date":"2024-11-08","arxiv_id":"2411.05990","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/game-theoretic-llm-agent-workflow-for#ran","syntology_url":"https://syntology.ai/paper/2411.05990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05990"}},"official":{"repos":["wenyueh/game_theory"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dawn-designing-distributed-agents-in-a","slug":"dawn-designing-distributed-agents-in-a","title":"DAWN: Designing Distributed Agents in a Worldwide Network","date":"2024-10-11","arxiv_id":"2410.22339","repositories_listed":2,"syntology":null},{"url":"/paper/colacare-enhancing-electronic-health-record","slug":"colacare-enhancing-electronic-health-record","title":"ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration","date":"2024-10-03","arxiv_id":"2410.02551","repositories_listed":2,"syntology":null},{"url":"/paper/kpca-cam-visual-explainability-of-deep","slug":"kpca-cam-visual-explainability-of-deep","title":"KPCA-CAM: Visual Explainability of Deep Computer Vision Models using Kernel PCA","date":"2024-09-30","arxiv_id":"2410.00267","repositories_listed":2,"syntology":null},{"url":"/paper/maia-2-a-unified-model-for-human-ai-alignment","slug":"maia-2-a-unified-model-for-human-ai-alignment","title":"Maia-2: A Unified Model for Human-AI Alignment in Chess","date":"2024-09-30","arxiv_id":"2409.20553","repositories_listed":2,"syntology":{"n":18,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"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) · 10 unverified","sample_list":"/paper/maia-2-a-unified-model-for-human-ai-alignment#ran","syntology_url":"https://syntology.ai/paper/2409.20553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.20553"}},"official":{"repos":["csslab/maia2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/on-the-planning-abilities-of-openai-s-o1","slug":"on-the-planning-abilities-of-openai-s-o1","title":"On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability","date":"2024-09-30","arxiv_id":"2409.19924","repositories_listed":2,"syntology":null},{"url":"/paper/parco-learning-parallel-autoregressive","slug":"parco-learning-parallel-autoregressive","title":"Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization","date":"2024-09-05","arxiv_id":"2409.03811","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/parco-learning-parallel-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2409.03811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03811"}},"official":{"repos":["ai4co/parco"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ml-edm-package-a-python-toolkit-for-machine","slug":"ml-edm-package-a-python-toolkit-for-machine","title":"ml_edm package: a Python toolkit for Machine Learning based Early Decision Making","date":"2024-08-23","arxiv_id":"2408.12925","repositories_listed":2,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-for-22","slug":"multi-agent-reinforcement-learning-for-22","title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","date":"2024-08-19","arxiv_id":"2408.09675","repositories_listed":2,"syntology":null},{"url":"/paper/rationalising-data-collection-for-building","slug":"rationalising-data-collection-for-building","title":"Rationalising data collection for supporting decision making in building energy systems using Value of Information analysis","date":"2024-08-19","arxiv_id":"2409.00049","repositories_listed":2,"syntology":null},{"url":"/paper/agent-q-advanced-reasoning-and-learning-for","slug":"agent-q-advanced-reasoning-and-learning-for","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","date":"2024-08-13","arxiv_id":"2408.07199","repositories_listed":2,"syntology":null},{"url":"/paper/2407-21054","slug":"2407-21054","title":"Sentiment Reasoning for Healthcare","date":"2024-07-24","arxiv_id":"2407.21054","repositories_listed":2,"syntology":null},{"url":"/paper/unveiling-the-decision-making-process-in","slug":"unveiling-the-decision-making-process-in","title":"Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming","date":"2024-07-20","arxiv_id":"2407.14714","repositories_listed":2,"syntology":null},{"url":"/paper/adaptive-foundation-models-for-online","slug":"adaptive-foundation-models-for-online","title":"Scalable Exploration via Ensemble++","date":"2024-07-18","arxiv_id":"2407.13195","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"5 ran (of which 1 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) · 3 unverified","sample_list":"/paper/adaptive-foundation-models-for-online#ran","syntology_url":"https://syntology.ai/paper/2407.13195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13195"}},"official":{"repos":["szrlee/GPT-HyperAgent","szrlee/ensemble_plus_plus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/fincon-a-synthesized-llm-multi-agent-system","slug":"fincon-a-synthesized-llm-multi-agent-system","title":"FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making","date":"2024-07-09","arxiv_id":"2407.06567","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/fincon-a-synthesized-llm-multi-agent-system#ran","syntology_url":"https://syntology.ai/paper/2407.06567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06567"}},"official":{"repos":["the-finai/fincon"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/neuralgam-explainable-generalized-additive","slug":"neuralgam-explainable-generalized-additive","title":"neuralGAM: Explainable generalized additive neural networks with independent neural network training","date":"2024-07-08","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/multilingual-trolley-problems-for-language","slug":"multilingual-trolley-problems-for-language","title":"Language Model Alignment in Multilingual Trolley Problems","date":"2024-07-02","arxiv_id":"2407.02273","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multilingual-trolley-problems-for-language#ran","syntology_url":"https://syntology.ai/paper/2407.02273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02273"}},"official":{"repos":["causalNLP/moralmachine","causalnlp/multitp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/imageflownet-forecasting-multiscale","slug":"imageflownet-forecasting-multiscale","title":"ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images","date":"2024-06-20","arxiv_id":"2406.14794","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imageflownet-forecasting-multiscale#ran","syntology_url":"https://syntology.ai/paper/2406.14794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14794"}},"official":{"repos":["ChenLiu-1996/ImageFlowNet"],"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":["named_in_paper","official"]}}},{"url":"/paper/chg-shapley-efficient-data-valuation-and","slug":"chg-shapley-efficient-data-valuation-and","title":"CHG Shapley: Efficient Data Valuation and Selection towards Trustworthy Machine Learning","date":"2024-06-17","arxiv_id":"2406.11730","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/chg-shapley-efficient-data-valuation-and#ran","syntology_url":"https://syntology.ai/paper/2406.11730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11730"}},"official":{"repos":["caihuaiguang/CHG-Shapley-for-Data-Selection","caihuaiguang/CHG-Shapley-for-Data-Valuation"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-language-soccer-framework-an-open","slug":"cross-language-soccer-framework-an-open","title":"Cross Language Soccer Framework: An Open Source Framework for the RoboCup 2D Soccer Simulation","date":"2024-06-09","arxiv_id":"2406.05621","repositories_listed":2,"syntology":null},{"url":"/paper/llm-experiments-with-simulation-large","slug":"llm-experiments-with-simulation-large","title":"LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins","date":"2024-05-28","arxiv_id":"2405.18092","repositories_listed":2,"syntology":null},{"url":"/paper/acegen-reinforcement-learning-of-generative","slug":"acegen-reinforcement-learning-of-generative","title":"ACEGEN: Reinforcement learning of generative chemical agents for drug discovery","date":"2024-05-07","arxiv_id":"2405.04657","repositories_listed":2,"syntology":null},{"url":"/paper/axiomatic-causal-interventions-for-reverse","slug":"axiomatic-causal-interventions-for-reverse","title":"Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models","date":"2024-05-03","arxiv_id":"2405.02503","repositories_listed":2,"syntology":null},{"url":"/paper/cooperate-or-collapse-emergence-of","slug":"cooperate-or-collapse-emergence-of","title":"Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents","date":"2024-04-25","arxiv_id":"2404.16698","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/cooperate-or-collapse-emergence-of#ran","syntology_url":"https://syntology.ai/paper/2404.16698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16698"}},"official":{"repos":["giorgiopiatti/govsim"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-hallucinations-in-large-vision","slug":"mitigating-hallucinations-in-large-vision","title":"Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding","date":"2024-03-27","arxiv_id":"2403.18715","repositories_listed":2,"syntology":{"n":8,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mitigating-hallucinations-in-large-vision#ran","syntology_url":"https://syntology.ai/paper/2403.18715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18715"}},"official":{"repos":["p1k0pan/ICD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/towards-learning-contrast-kinetics-with-multi","slug":"towards-learning-contrast-kinetics-with-multi","title":"Towards Learning Contrast Kinetics with Multi-Condition Latent Diffusion Models","date":"2024-03-20","arxiv_id":"2403.13890","repositories_listed":2,"syntology":null},{"url":"/paper/probabilistic-calibration-by-design-for","slug":"probabilistic-calibration-by-design-for","title":"Probabilistic Calibration by Design for Neural Network Regression","date":"2024-03-18","arxiv_id":"2403.11964","repositories_listed":2,"syntology":null},{"url":"/paper/driving-style-alignment-for-llm-powered","slug":"driving-style-alignment-for-llm-powered","title":"Driving Style Alignment for LLM-powered Driver Agent","date":"2024-03-17","arxiv_id":"2403.11368","repositories_listed":2,"syntology":null},{"url":"/paper/behavior-generation-with-latent-actions","slug":"behavior-generation-with-latent-actions","title":"Behavior Generation with Latent Actions","date":"2024-03-05","arxiv_id":"2403.03181","repositories_listed":2,"syntology":{"n":14,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":6,"n_honours":1,"n_violates":2,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/behavior-generation-with-latent-actions#ran","syntology_url":"https://syntology.ai/paper/2403.03181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03181"}},"official":{"repos":["jayLEE0301/vq_bet_official"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/towards-democratized-flood-risk-management-an","slug":"towards-democratized-flood-risk-management-an","title":"Towards Democratized Flood Risk Management: An Advanced AI Assistant Enabled by GPT-4 for Enhanced Interpretability and Public Engagement","date":"2024-03-05","arxiv_id":"2403.03188","repositories_listed":2,"syntology":null},{"url":"/paper/multi-agent-collaboration-framework-for","slug":"multi-agent-collaboration-framework-for","title":"MACRec: a Multi-Agent Collaboration Framework for Recommendation","date":"2024-02-23","arxiv_id":"2402.15235","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-agent-collaboration-framework-for#ran","syntology_url":"https://syntology.ai/paper/2402.15235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15235"}},"official":{"repos":["wzf2000/macrec"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/testing-calibration-in-subquadratic-time","slug":"testing-calibration-in-subquadratic-time","title":"Testing Calibration in Nearly-Linear Time","date":"2024-02-20","arxiv_id":"2402.13187","repositories_listed":2,"syntology":null},{"url":"/paper/uncertainty-quantification-for-forward-and","slug":"uncertainty-quantification-for-forward-and","title":"Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global Evolution","date":"2024-02-13","arxiv_id":"2402.08383","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/uncertainty-quantification-for-forward-and#ran","syntology_url":"https://syntology.ai/paper/2402.08383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08383"}},"official":{"repos":["ai4science-westlakeu/le-pde-uq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/conformal-monte-carlo-meta-learners-for","slug":"conformal-monte-carlo-meta-learners-for","title":"Conformal Convolution and Monte Carlo Meta-learners for Predictive Inference of Individual Treatment Effects","date":"2024-02-07","arxiv_id":"2402.04906","repositories_listed":2,"syntology":{"n":9,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 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; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/conformal-monte-carlo-meta-learners-for#ran","syntology_url":"https://syntology.ai/paper/2402.04906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04906"}},"official":{"repos":["predict-idlab/cct-cmc","predict-idlab/cmc-learner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/sym-q-adaptive-symbolic-regression-via","slug":"sym-q-adaptive-symbolic-regression-via","title":"Sym-Q: Adaptive Symbolic Regression via Sequential Decision-Making","date":"2024-02-07","arxiv_id":"2402.05306","repositories_listed":2,"syntology":null},{"url":"/paper/measuring-implicit-bias-in-explicitly","slug":"measuring-implicit-bias-in-explicitly","title":"Measuring Implicit Bias in Explicitly Unbiased Large Language Models","date":"2024-02-06","arxiv_id":"2402.04105","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-implicit-bias-in-explicitly#ran","syntology_url":"https://syntology.ai/paper/2402.04105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04105"}},"official":{"repos":["baixuechunzi/llm-implicit-bias"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/position-paper-what-can-large-language-models","slug":"position-paper-what-can-large-language-models","title":"Position: What Can Large Language Models Tell Us about Time Series Analysis","date":"2024-02-05","arxiv_id":"2402.02713","repositories_listed":2,"syntology":null},{"url":"/paper/zero-shot-reinforcement-learning-via-function","slug":"zero-shot-reinforcement-learning-via-function","title":"Zero-Shot Reinforcement Learning via Function Encoders","date":"2024-01-30","arxiv_id":"2401.17173","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/zero-shot-reinforcement-learning-via-function#ran","syntology_url":"https://syntology.ai/paper/2401.17173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17173"}},"official":{"repos":["anonymousresearcher5642/functionencoderrl","tyler-ingebrand/functionencoderrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-language-model-agency-through","slug":"evaluating-language-model-agency-through","title":"Evaluating Language Model Agency through Negotiations","date":"2024-01-09","arxiv_id":"2401.04536","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluating-language-model-agency-through#ran","syntology_url":"https://syntology.ai/paper/2401.04536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04536"}},"official":{"repos":["epfl-dlab/lamen"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/autonomous-driving-using-residual-sensor","slug":"autonomous-driving-using-residual-sensor","title":"Autonomous Driving using Residual Sensor Fusion and Deep Reinforcement Learning","date":"2023-12-27","arxiv_id":"2312.16620","repositories_listed":2,"syntology":null},{"url":"/paper/pdit-interleaving-perception-and-decision","slug":"pdit-interleaving-perception-and-decision","title":"PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning","date":"2023-12-26","arxiv_id":"2312.15863","repositories_listed":2,"syntology":null},{"url":"/paper/pulaski-learning-inter-rater-variability","slug":"pulaski-learning-inter-rater-variability","title":"PULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentation","date":"2023-12-25","arxiv_id":"2312.15686","repositories_listed":2,"syntology":null},{"url":"/paper/scalable-agent-based-modeling-for-complex","slug":"scalable-agent-based-modeling-for-complex","title":"Scalable Agent-Based Modeling for Complex Financial Market Simulations","date":"2023-12-22","arxiv_id":"2312.14903","repositories_listed":2,"syntology":null},{"url":"/paper/lingoqa-video-question-answering-for","slug":"lingoqa-video-question-answering-for","title":"LingoQA: Visual Question Answering for Autonomous Driving","date":"2023-12-21","arxiv_id":"2312.14115","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/lingoqa-video-question-answering-for#ran","syntology_url":"https://syntology.ai/paper/2312.14115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14115"}},"official":{"repos":["wayveai/lingoqa"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/optimizing-heat-alert-issuance-for-public","slug":"optimizing-heat-alert-issuance-for-public","title":"Optimizing Heat Alert Issuance with Reinforcement Learning","date":"2023-12-21","arxiv_id":"2312.14196","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-the-impact-of-lay-user-feedback-for","slug":"exploring-the-impact-of-lay-user-feedback-for","title":"Human-in-the-loop Fairness: Integrating Stakeholder Feedback to Incorporate Fairness Perspectives in Responsible AI","date":"2023-12-13","arxiv_id":"2312.08064","repositories_listed":2,"syntology":null},{"url":"/paper/reads-v-real-time-automated-detection-of","slug":"reads-v-real-time-automated-detection-of","title":"VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG","date":"2023-11-24","arxiv_id":"2311.14775","repositories_listed":2,"syntology":null},{"url":"/paper/finme-a-performance-enhanced-large-language","slug":"finme-a-performance-enhanced-large-language","title":"FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design","date":"2023-11-23","arxiv_id":"2311.13743","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/finme-a-performance-enhanced-large-language#ran","syntology_url":"https://syntology.ai/paper/2311.13743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13743"}},"official":{"repos":["pipiku915/finmem-llm-stocktrading"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2311-13594","slug":"2311-13594","title":"Labeling Neural Representations with Inverse Recognition","date":"2023-11-22","arxiv_id":"2311.13594","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2311-13594#ran","syntology_url":"https://syntology.ai/paper/2311.13594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13594"}},"official":{"repos":["lapalap/invert"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tactics2d-a-multi-agent-reinforcement","slug":"tactics2d-a-multi-agent-reinforcement","title":"Tactics2D: A Highly Modular and Extensible Simulator for Driving Decision-making","date":"2023-11-18","arxiv_id":"2311.11058","repositories_listed":2,"syntology":null},{"url":"/paper/enhancing-medical-text-evaluation-with-gpt-4","slug":"enhancing-medical-text-evaluation-with-gpt-4","title":"DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation","date":"2023-11-16","arxiv_id":"2311.09581","repositories_listed":2,"syntology":null},{"url":"/paper/defn-dual-encoder-fourier-group-harmonics","slug":"defn-dual-encoder-fourier-group-harmonics","title":"DEFN: Dual-Encoder Fourier Group Harmonics Network for Three-Dimensional Indistinct-Boundary Object Segmentation","date":"2023-11-01","arxiv_id":"2311.00483","repositories_listed":2,"syntology":null},{"url":"/paper/sum-of-parts-models-faithful-attributions-for","slug":"sum-of-parts-models-faithful-attributions-for","title":"Sum-of-Parts: Faithful Attributions for Groups of Features","date":"2023-10-25","arxiv_id":"2310.16316","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sum-of-parts-models-faithful-attributions-for#ran","syntology_url":"https://syntology.ai/paper/2310.16316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16316"}},"official":{"repos":["brachiolab/sop","debugml/sop"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tree-prompting-efficient-task-adaptation","slug":"tree-prompting-efficient-task-adaptation","title":"Tree Prompting: Efficient Task Adaptation without Fine-Tuning","date":"2023-10-21","arxiv_id":"2310.14034","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/tree-prompting-efficient-task-adaptation#ran","syntology_url":"https://syntology.ai/paper/2310.14034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14034"}},"official":{"repos":["csinva/treeprompt","csinva/tree-prompt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/linear-latent-world-models-in-simple","slug":"linear-latent-world-models-in-simple","title":"Linear Latent World Models in Simple Transformers: A Case Study on Othello-GPT","date":"2023-10-11","arxiv_id":"2310.07582","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/linear-latent-world-models-in-simple#ran","syntology_url":"https://syntology.ai/paper/2310.07582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07582"}},"official":{"repos":["deanhazineh/emergent-world-representations-othello"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dsac-t-distributional-soft-actor-critic-with","slug":"dsac-t-distributional-soft-actor-critic-with","title":"Distributional Soft Actor-Critic with Three Refinements","date":"2023-10-09","arxiv_id":"2310.05858","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dsac-t-distributional-soft-actor-critic-with#ran","syntology_url":"https://syntology.ai/paper/2310.05858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05858"}},"official":{"repos":["jingliang-duan/dsac-t","jingliang-duan/dsac-v2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-financial-sentiment-analysis-via","slug":"enhancing-financial-sentiment-analysis-via","title":"Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models","date":"2023-10-06","arxiv_id":"2310.04027","repositories_listed":2,"syntology":null},{"url":"/paper/language-agent-tree-search-unifies-reasoning","slug":"language-agent-tree-search-unifies-reasoning","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","date":"2023-10-06","arxiv_id":"2310.04406","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-agent-tree-search-unifies-reasoning#ran","syntology_url":"https://syntology.ai/paper/2310.04406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04406"}},"official":{"repos":["lapisrocks/languageagenttreesearch","andyz245/LanguageAgentTreeSearch"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-large-language-models-as-ai","slug":"benchmarking-large-language-models-as-ai","title":"MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation","date":"2023-10-05","arxiv_id":"2310.03302","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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) · 5 unverified","sample_list":"/paper/benchmarking-large-language-models-as-ai#ran","syntology_url":"https://syntology.ai/paper/2310.03302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03302"}},"official":{"repos":["snap-stanford/mlagentbench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/autodan-generating-stealthy-jailbreak-prompts","slug":"autodan-generating-stealthy-jailbreak-prompts","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","date":"2023-10-03","arxiv_id":"2310.04451","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/autodan-generating-stealthy-jailbreak-prompts#ran","syntology_url":"https://syntology.ai/paper/2310.04451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04451"}},"official":{"repos":["sheltonliu-n/autodan"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-deliberation-evaluating-llms-with","slug":"llm-deliberation-evaluating-llms-with","title":"Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation","date":"2023-09-29","arxiv_id":"2309.17234","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-deliberation-evaluating-llms-with#ran","syntology_url":"https://syntology.ai/paper/2309.17234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17234"}},"official":{"repos":["s-abdelnabi/llm-deliberation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-prediction-powered-inference","slug":"cross-prediction-powered-inference","title":"Cross-Prediction-Powered Inference","date":"2023-09-28","arxiv_id":"2309.16598","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cross-prediction-powered-inference#ran","syntology_url":"https://syntology.ai/paper/2309.16598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16598"}},"official":{"repos":["tijana-zrnic/cross-ppi"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/dilu-a-knowledge-driven-approach-to","slug":"dilu-a-knowledge-driven-approach-to","title":"DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models","date":"2023-09-28","arxiv_id":"2309.16292","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dilu-a-knowledge-driven-approach-to#ran","syntology_url":"https://syntology.ai/paper/2309.16292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16292"}},"official":{"repos":["PJLab-ADG/DiLu"],"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":["listed","official"]}}},{"url":"/paper/deep-reinforcement-learning-for-image-to","slug":"deep-reinforcement-learning-for-image-to","title":"RL-I2IT: Image-to-Image Translation with Deep Reinforcement Learning","date":"2023-09-24","arxiv_id":"2309.13672","repositories_listed":2,"syntology":null},{"url":"/paper/hierarchical-multi-agent-reinforcement","slug":"hierarchical-multi-agent-reinforcement","title":"Hierarchical Multi-Agent Reinforcement Learning for Air Combat Maneuvering","date":"2023-09-20","arxiv_id":"2309.11247","repositories_listed":2,"syntology":null},{"url":"/paper/equal-long-term-benefit-rate-adapting-static","slug":"equal-long-term-benefit-rate-adapting-static","title":"Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate","date":"2023-09-07","arxiv_id":"2309.03426","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/equal-long-term-benefit-rate-adapting-static#ran","syntology_url":"https://syntology.ai/paper/2309.03426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03426"}},"official":{"repos":["umd-huang-lab/elbert","yuancheng-xu/elbert"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/on-the-impact-of-feeding-cost-risk-in","slug":"on-the-impact-of-feeding-cost-risk-in","title":"On the Impact of Feeding Cost Risk in Aquaculture Valuation and Decision Making","date":"2023-09-06","arxiv_id":"2309.02970","repositories_listed":2,"syntology":null},{"url":"/paper/cognitive-architectures-for-language-agents","slug":"cognitive-architectures-for-language-agents","title":"Cognitive Architectures for Language Agents","date":"2023-09-05","arxiv_id":"2309.02427","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cognitive-architectures-for-language-agents#ran","syntology_url":"https://syntology.ai/paper/2309.02427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.02427"}},"official":{"repos":["ysymyth/awesome-language-agents"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/emergent-linear-representations-in-world","slug":"emergent-linear-representations-in-world","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","date":"2023-09-02","arxiv_id":"2309.00941","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/emergent-linear-representations-in-world#ran","syntology_url":"https://syntology.ai/paper/2309.00941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00941"}},"official":{"repos":["ajyl/mech_int_othellogpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/fosa-full-information-maximum-likelihood-fiml","slug":"fosa-full-information-maximum-likelihood-fiml","title":"Missing Data Imputation Based on Dynamically Adaptable Structural Equation Modeling with Self-Attention","date":"2023-08-23","arxiv_id":"2308.12388","repositories_listed":2,"syntology":null},{"url":"/paper/guinea-pig-trials-utilizing-gpt-a-novel-smart","slug":"guinea-pig-trials-utilizing-gpt-a-novel-smart","title":"\"Guinea Pig Trials\" Utilizing GPT: A Novel Smart Agent-Based Modeling Approach for Studying Firm Competition and Collusion","date":"2023-08-21","arxiv_id":"2308.10974","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/guinea-pig-trials-utilizing-gpt-a-novel-smart#ran","syntology_url":"https://syntology.ai/paper/2308.10974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10974"}},"official":{"repos":["roihn/sabm","wuzengqing001225/sabm_pricing_game"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/expel-llm-agents-are-experiential-learners","slug":"expel-llm-agents-are-experiential-learners","title":"ExpeL: LLM Agents Are Experiential Learners","date":"2023-08-20","arxiv_id":"2308.10144","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/expel-llm-agents-are-experiential-learners#ran","syntology_url":"https://syntology.ai/paper/2308.10144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10144"}},"official":{"repos":["LeapLabTHU/ExpeL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/bolaa-benchmarking-and-orchestrating-llm","slug":"bolaa-benchmarking-and-orchestrating-llm","title":"BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents","date":"2023-08-11","arxiv_id":"2308.05960","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bolaa-benchmarking-and-orchestrating-llm#ran","syntology_url":"https://syntology.ai/paper/2308.05960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.05960"}},"official":{"repos":["salesforce/bolaa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-strategic-framework-for-optimal-decisions","slug":"a-strategic-framework-for-optimal-decisions","title":"A Strategic Framework for Optimal Decisions in Football 1-vs-1 Shot-Taking Situations: An Integrated Approach of Machine Learning, Theory-Based Modeling, and Game Theory","date":"2023-07-27","arxiv_id":"2307.14732","repositories_listed":2,"syntology":null},{"url":"/paper/causal-fair-machine-learning-via-rank","slug":"causal-fair-machine-learning-via-rank","title":"Causal Fair Machine Learning via Rank-Preserving Interventional Distributions","date":"2023-07-24","arxiv_id":"2307.12797","repositories_listed":2,"syntology":null},{"url":"/paper/uncertainty-quantification-for-molecular","slug":"uncertainty-quantification-for-molecular","title":"Uncertainty Quantification for Molecular Property Predictions with Graph Neural Architecture Search","date":"2023-07-19","arxiv_id":"2307.10438","repositories_listed":2,"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/uncertainty-quantification-for-molecular#ran","syntology_url":"https://syntology.ai/paper/2307.10438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10438"}},"official":{"repos":["sjiang87/deephyper"],"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/fast-model-inference-and-training-on-board-of","slug":"fast-model-inference-and-training-on-board-of","title":"Fast model inference and training on-board of Satellites","date":"2023-07-17","arxiv_id":"2307.08700","repositories_listed":2,"syntology":null},{"url":"/paper/feature-embeddings-from-large-scale-acoustic","slug":"feature-embeddings-from-large-scale-acoustic","title":"Global birdsong embeddings enable superior transfer learning for bioacoustic classification","date":"2023-07-12","arxiv_id":"2307.06292","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/feature-embeddings-from-large-scale-acoustic#ran","syntology_url":"https://syntology.ai/paper/2307.06292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06292"}},"official":{"repos":["google-research/chirp","google-research/perch"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-active-subspaces-and-discovering","slug":"learning-active-subspaces-and-discovering","title":"Learning Active Subspaces and Discovering Important Features with Gaussian Radial Basis Functions Neural Networks","date":"2023-07-11","arxiv_id":"2307.05639","repositories_listed":2,"syntology":null},{"url":"/paper/alleviating-matthew-effect-of-offline","slug":"alleviating-matthew-effect-of-offline","title":"Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation","date":"2023-07-10","arxiv_id":"2307.04571","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/alleviating-matthew-effect-of-offline#ran","syntology_url":"https://syntology.ai/paper/2307.04571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.04571"}},"official":{"repos":["chongminggao/dorl-codes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/beyond-known-reality-exploiting","slug":"beyond-known-reality-exploiting","title":"Beyond Known Reality: Exploiting Counterfactual Explanations for Medical Research","date":"2023-07-05","arxiv_id":"2307.02131","repositories_listed":2,"syntology":null},{"url":"/paper/computationally-assisted-quality-control-for","slug":"computationally-assisted-quality-control-for","title":"Computationally Assisted Quality Control for Public Health Data Streams","date":"2023-06-29","arxiv_id":"2306.16914","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/computationally-assisted-quality-control-for#ran","syntology_url":"https://syntology.ai/paper/2306.16914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16914"}},"official":{"repos":["ananya-joshi/ijcai23_supplemental","cmu-delphi/covidcast-indicators"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/milliflow-scene-flow-estimation-on-mmwave","slug":"milliflow-scene-flow-estimation-on-mmwave","title":"milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing","date":"2023-06-29","arxiv_id":"2306.17010","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/milliflow-scene-flow-estimation-on-mmwave#ran","syntology_url":"https://syntology.ai/paper/2306.17010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17010"}},"official":{"repos":["toytiny/milliflow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-superhuman-models-with-consistency","slug":"evaluating-superhuman-models-with-consistency","title":"Evaluating Superhuman Models with Consistency Checks","date":"2023-06-16","arxiv_id":"2306.09983","repositories_listed":2,"syntology":null},{"url":"/paper/fix-fairness-don-t-ruin-accuracy-performance","slug":"fix-fairness-don-t-ruin-accuracy-performance","title":"Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML","date":"2023-06-15","arxiv_id":"2306.09297","repositories_listed":2,"syntology":null},{"url":"/paper/learning-embeddings-for-sequential-tasks","slug":"learning-embeddings-for-sequential-tasks","title":"Learning Embeddings for Sequential Tasks Using Population of Agents","date":"2023-06-05","arxiv_id":"2306.03311","repositories_listed":2,"syntology":null},{"url":"/paper/libero-benchmarking-knowledge-transfer-for","slug":"libero-benchmarking-knowledge-transfer-for","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","date":"2023-06-05","arxiv_id":"2306.03310","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/libero-benchmarking-knowledge-transfer-for#ran","syntology_url":"https://syntology.ai/paper/2306.03310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03310"}},"official":null}},{"url":"/paper/solving-np-hard-min-max-routing-problems-as","slug":"solving-np-hard-min-max-routing-problems-as","title":"Equity-Transformer: Solving NP-hard Min-Max Routing Problems as Sequential Generation with Equity Context","date":"2023-06-05","arxiv_id":"2306.02689","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/solving-np-hard-min-max-routing-problems-as#ran","syntology_url":"https://syntology.ai/paper/2306.02689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02689"}},"official":{"repos":["kaist-silab/equity-transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"6ad3d01d437af4cf4c98c0b200621c599ddd9bd061b4ad1ee73b5ef0eaa8a674","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}