{"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/12","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":12,"pages_in_order":124,"rows_per_page":100,"rows":[1101,1200],"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/11","next":"/task/decision-making/papers/13","papers":[{"url":"/paper/icln-input-convex-loss-network-for-decision","slug":"icln-input-convex-loss-network-for-decision","title":"Locally Convex Global Loss Network for Decision-Focused Learning","date":"2024-03-04","arxiv_id":"2403.01875","repositories_listed":1,"syntology":null},{"url":"/paper/comtraq-mpc-meta-trained-dqn-mpc-integration","slug":"comtraq-mpc-meta-trained-dqn-mpc-integration","title":"ComTraQ-MPC: Meta-Trained DQN-MPC Integration for Trajectory Tracking with Limited Active Localization Updates","date":"2024-03-03","arxiv_id":"2403.01564","repositories_listed":1,"syntology":null},{"url":"/paper/playing-nethack-with-llms-potential","slug":"playing-nethack-with-llms-potential","title":"Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents","date":"2024-03-01","arxiv_id":"2403.00690","repositories_listed":1,"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/playing-nethack-with-llms-potential#ran","syntology_url":"https://syntology.ai/paper/2403.00690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00690"}},"official":{"repos":["commandercero/netplay"],"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/a-cognitive-based-trajectory-prediction","slug":"a-cognitive-based-trajectory-prediction","title":"A Cognitive-Based Trajectory Prediction Approach for Autonomous Driving","date":"2024-02-29","arxiv_id":"2402.19251","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-long-term-recommendation-with-bi","slug":"enhancing-long-term-recommendation-with-bi","title":"Large Language Models are Learnable Planners for Long-Term Recommendation","date":"2024-02-29","arxiv_id":"2403.00843","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/enhancing-long-term-recommendation-with-bi#ran","syntology_url":"https://syntology.ai/paper/2403.00843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00843"}},"official":{"repos":["jizhi-zhang/billp"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/memonav-working-memory-model-for-visual","slug":"memonav-working-memory-model-for-visual","title":"MemoNav: Working Memory Model for Visual Navigation","date":"2024-02-29","arxiv_id":"2402.19161","repositories_listed":1,"syntology":null},{"url":"/paper/approaching-human-level-forecasting-with","slug":"approaching-human-level-forecasting-with","title":"Approaching Human-Level Forecasting with Language Models","date":"2024-02-28","arxiv_id":"2402.18563","repositories_listed":1,"syntology":null},{"url":"/paper/decisionnce-embodied-multimodal","slug":"decisionnce-embodied-multimodal","title":"DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning","date":"2024-02-28","arxiv_id":"2402.18137","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/decisionnce-embodied-multimodal#ran","syntology_url":"https://syntology.ai/paper/2402.18137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18137"}},"official":{"repos":["2toinf/DecisionNCE"],"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/rora-robust-free-text-rationale-evaluation","slug":"rora-robust-free-text-rationale-evaluation","title":"RORA: Robust Free-Text Rationale Evaluation","date":"2024-02-28","arxiv_id":"2402.18678","repositories_listed":1,"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":1,"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/rora-robust-free-text-rationale-evaluation#ran","syntology_url":"https://syntology.ai/paper/2402.18678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18678"}},"official":{"repos":["zipjiang/rora"],"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/unveiling-the-potential-of-robustness-in","slug":"unveiling-the-potential-of-robustness-in","title":"Unveiling the Potential of Robustness in Selecting Conditional Average Treatment Effect Estimators","date":"2024-02-28","arxiv_id":"2402.18392","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"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) · 3 unverified","sample_list":"/paper/unveiling-the-potential-of-robustness-in#ran","syntology_url":"https://syntology.ai/paper/2402.18392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18392"}},"official":{"repos":["yiyhuang3/cate_estimator_selection"],"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":["official"]}}},{"url":"/paper/benchmarking-data-science-agents","slug":"benchmarking-data-science-agents","title":"Benchmarking Data Science Agents","date":"2024-02-27","arxiv_id":"2402.17168","repositories_listed":1,"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/benchmarking-data-science-agents#ran","syntology_url":"https://syntology.ai/paper/2402.17168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17168"}},"official":{"repos":["metacopilot/dseval"],"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/contingency-planning-using-bi-level-markov","slug":"contingency-planning-using-bi-level-markov","title":"Contingency Planning Using Bi-level Markov Decision Processes for Space Missions","date":"2024-02-26","arxiv_id":"2402.16342","repositories_listed":1,"syntology":null},{"url":"/paper/ehrnoteqa-a-patient-specific-question","slug":"ehrnoteqa-a-patient-specific-question","title":"EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries","date":"2024-02-25","arxiv_id":"2402.16040","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/ehrnoteqa-a-patient-specific-question#ran","syntology_url":"https://syntology.ai/paper/2402.16040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16040"}},"official":{"repos":["ji-youn-kim/ehrnoteqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-can-llm-guide-rl-a-value-based-approach","slug":"how-can-llm-guide-rl-a-value-based-approach","title":"How Can LLM Guide RL? A Value-Based Approach","date":"2024-02-25","arxiv_id":"2402.16181","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/how-can-llm-guide-rl-a-value-based-approach#ran","syntology_url":"https://syntology.ai/paper/2402.16181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16181"}},"official":{"repos":["agentification/language-integrated-vi"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/predicting-outcomes-in-video-games-with-long","slug":"predicting-outcomes-in-video-games-with-long","title":"Predicting Outcomes in Video Games with Long Short Term Memory Networks","date":"2024-02-24","arxiv_id":"2402.15923","repositories_listed":1,"syntology":null},{"url":"/paper/reward-design-for-justifiable-sequential","slug":"reward-design-for-justifiable-sequential","title":"Reward Design for Justifiable Sequential Decision-Making","date":"2024-02-24","arxiv_id":"2402.15826","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-a-better-planning-with-transformers","slug":"beyond-a-better-planning-with-transformers","title":"Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping","date":"2024-02-21","arxiv_id":"2402.14083","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/beyond-a-better-planning-with-transformers#ran","syntology_url":"https://syntology.ai/paper/2402.14083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14083"}},"official":{"repos":["facebookresearch/searchformer"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-generative-models-for-offline-policy","slug":"deep-generative-models-for-offline-policy","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","date":"2024-02-21","arxiv_id":"2402.13777","repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-reasoning-based-on-large-language","slug":"hybrid-reasoning-based-on-large-language","title":"Hybrid Reasoning Based on Large Language Models for Autonomous Car Driving","date":"2024-02-21","arxiv_id":"2402.13602","repositories_listed":1,"syntology":null},{"url":"/paper/pca-bench-evaluating-multimodal-large","slug":"pca-bench-evaluating-multimodal-large","title":"PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain","date":"2024-02-21","arxiv_id":"2402.15527","repositories_listed":1,"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/pca-bench-evaluating-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2402.15527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15527"}},"official":{"repos":["pkunlp-icler/pca-eval"],"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/sage-evaluating-moral-consistency-in-large","slug":"sage-evaluating-moral-consistency-in-large","title":"SaGE: Evaluating Moral Consistency in Large Language Models","date":"2024-02-21","arxiv_id":"2402.13709","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/sage-evaluating-moral-consistency-in-large#ran","syntology_url":"https://syntology.ai/paper/2402.13709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13709"}},"official":{"repos":["vnnm404/SaGE"],"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/social-environment-design","slug":"social-environment-design","title":"Social Environment Design","date":"2024-02-21","arxiv_id":"2402.14090","repositories_listed":1,"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":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) · 0 unverified","sample_list":"/paper/social-environment-design#ran","syntology_url":"https://syntology.ai/paper/2402.14090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14090"}},"official":{"repos":["ezhang7423/social-environment-design"],"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/analyzing-operator-states-and-the-impact-of","slug":"analyzing-operator-states-and-the-impact-of","title":"Analyzing Operator States and the Impact of AI-Enhanced Decision Support in Control Rooms: A Human-in-the-Loop Specialized Reinforcement Learning Framework for Intervention Strategies","date":"2024-02-20","arxiv_id":"2402.13219","repositories_listed":1,"syntology":null},{"url":"/paper/more-3s-multimodal-based-offline","slug":"more-3s-multimodal-based-offline","title":"MORE-3S:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces","date":"2024-02-20","arxiv_id":"2402.12845","repositories_listed":1,"syntology":null},{"url":"/paper/reflect-rl-two-player-online-rl-fine-tuning","slug":"reflect-rl-two-player-online-rl-fine-tuning","title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","date":"2024-02-20","arxiv_id":"2402.12621","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 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) · 4 unverified","sample_list":"/paper/reflect-rl-two-player-online-rl-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2402.12621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12621"}},"official":{"repos":["zhourunlong/reflect-rl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/what-if-llms-have-different-world-views","slug":"what-if-llms-have-different-world-views","title":"What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents","date":"2024-02-20","arxiv_id":"2402.13184","repositories_listed":1,"syntology":null},{"url":"/paper/xrl-bench-a-benchmark-for-evaluating-and","slug":"xrl-bench-a-benchmark-for-evaluating-and","title":"XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques","date":"2024-02-20","arxiv_id":"2402.12685","repositories_listed":1,"syntology":null},{"url":"/paper/artifacts-or-abduction-how-do-llms-answer","slug":"artifacts-or-abduction-how-do-llms-answer","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","date":"2024-02-19","arxiv_id":"2402.12483","repositories_listed":1,"syntology":{"n":10,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"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) · 6 unverified","sample_list":"/paper/artifacts-or-abduction-how-do-llms-answer#ran","syntology_url":"https://syntology.ai/paper/2402.12483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12483"}},"official":{"repos":["nbalepur/mcqa-artifacts"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-view-conformal-learning-for","slug":"multi-view-conformal-learning-for","title":"Multi-View Conformal Learning for Heterogeneous Sensor Fusion","date":"2024-02-19","arxiv_id":"2402.12307","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-location-trajectory-generation","slug":"synthetic-location-trajectory-generation","title":"Synthetic location trajectory generation using categorical diffusion models","date":"2024-02-19","arxiv_id":"2402.12242","repositories_listed":1,"syntology":null},{"url":"/paper/unist-a-prompt-empowered-universal-model-for","slug":"unist-a-prompt-empowered-universal-model-for","title":"UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction","date":"2024-02-19","arxiv_id":"2402.11838","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"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) · 5 unverified","sample_list":"/paper/unist-a-prompt-empowered-universal-model-for#ran","syntology_url":"https://syntology.ai/paper/2402.11838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11838"}},"official":{"repos":["tsinghua-fib-lab/unist"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-planning-in-hierarchical-active","slug":"dynamic-planning-in-hierarchical-active","title":"Dynamic planning in hierarchical active inference","date":"2024-02-18","arxiv_id":"2402.11658","repositories_listed":1,"syntology":null},{"url":"/paper/are-you-struggling-dataset-and-baselines-for","slug":"are-you-struggling-dataset-and-baselines-for","title":"Are you Struggling? Dataset and Baselines for Struggle Determination in Assembly Videos","date":"2024-02-16","arxiv_id":"2402.11057","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-generative-diffusion-models-via","slug":"explaining-generative-diffusion-models-via","title":"Explaining generative diffusion models via visual analysis for interpretable decision-making process","date":"2024-02-16","arxiv_id":"2402.10404","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/explaining-generative-diffusion-models-via#ran","syntology_url":"https://syntology.ai/paper/2402.10404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10404"}},"official":{"repos":["ian-jihoonpark/X-Diffusion"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/network-formation-and-dynamics-among-multi","slug":"network-formation-and-dynamics-among-multi","title":"Network Formation and Dynamics Among Multi-LLMs","date":"2024-02-16","arxiv_id":"2402.10659","repositories_listed":1,"syntology":null},{"url":"/paper/prise-learning-temporal-action-abstractions","slug":"prise-learning-temporal-action-abstractions","title":"PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control","date":"2024-02-16","arxiv_id":"2402.10450","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/prise-learning-temporal-action-abstractions#ran","syntology_url":"https://syntology.ai/paper/2402.10450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10450"}},"official":{"repos":["frankzheng2022/prise"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rag-driver-generalisable-driving-explanations","slug":"rag-driver-generalisable-driving-explanations","title":"RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model","date":"2024-02-16","arxiv_id":"2402.10828","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/rag-driver-generalisable-driving-explanations#ran","syntology_url":"https://syntology.ai/paper/2402.10828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10828"}},"official":null}},{"url":"/paper/jack-of-all-trades-master-of-some-a-multi","slug":"jack-of-all-trades-master-of-some-a-multi","title":"Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent","date":"2024-02-15","arxiv_id":"2402.09844","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/jack-of-all-trades-master-of-some-a-multi#ran","syntology_url":"https://syntology.ai/paper/2402.09844","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09844"}},"official":{"repos":["huggingface/jat"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/dataset-clustering-for-improved-offline","slug":"dataset-clustering-for-improved-offline","title":"Dataset Clustering for Improved Offline Policy Learning","date":"2024-02-14","arxiv_id":"2402.09550","repositories_listed":1,"syntology":null},{"url":"/paper/logicprpbank-a-corpus-for-logical-implication","slug":"logicprpbank-a-corpus-for-logical-implication","title":"LogicPrpBank: A Corpus for Logical Implication and Equivalence","date":"2024-02-14","arxiv_id":"2402.09609","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-reasoning-in-generative-large","slug":"probabilistic-reasoning-in-generative-large","title":"Reasoning over Uncertain Text by Generative Large Language Models","date":"2024-02-14","arxiv_id":"2402.09614","repositories_listed":1,"syntology":null},{"url":"/paper/cma-r-causal-mediation-analysis-for","slug":"cma-r-causal-mediation-analysis-for","title":"CMA-R:Causal Mediation Analysis for Explaining Rumour Detection","date":"2024-02-13","arxiv_id":"2402.08155","repositories_listed":1,"syntology":null},{"url":"/paper/epistemic-exploration-for-generalizable","slug":"epistemic-exploration-for-generalizable","title":"Epistemic Exploration for Generalizable Planning and Learning in Non-Stationary Settings","date":"2024-02-13","arxiv_id":"2402.08145","repositories_listed":1,"syntology":null},{"url":"/paper/fairness-auditing-with-multi-agent","slug":"fairness-auditing-with-multi-agent","title":"Fairness Auditing with Multi-Agent Collaboration","date":"2024-02-13","arxiv_id":"2402.08522","repositories_listed":1,"syntology":null},{"url":"/paper/group-decision-making-among-privacy-aware","slug":"group-decision-making-among-privacy-aware","title":"Differentially Private Distributed Inference","date":"2024-02-13","arxiv_id":"2402.08156","repositories_listed":1,"syntology":null},{"url":"/paper/addressing-cognitive-bias-in-medical-language","slug":"addressing-cognitive-bias-in-medical-language","title":"Addressing cognitive bias in medical language models","date":"2024-02-12","arxiv_id":"2402.08113","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":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) · 1 unverified","sample_list":"/paper/addressing-cognitive-bias-in-medical-language#ran","syntology_url":"https://syntology.ai/paper/2402.08113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08113"}},"official":{"repos":["carlwharris/cog-bias-med-llms"],"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/fairness-evaluation-for-uplift-modeling-in","slug":"fairness-evaluation-for-uplift-modeling-in","title":"Fairness Evaluation for Uplift Modeling in the Absence of Ground Truth","date":"2024-02-12","arxiv_id":"2403.12069","repositories_listed":1,"syntology":null},{"url":"/paper/from-uncertainty-to-precision-enhancing","slug":"from-uncertainty-to-precision-enhancing","title":"From Uncertainty to Precision: Enhancing Binary Classifier Performance through Calibration","date":"2024-02-12","arxiv_id":"2402.07790","repositories_listed":1,"syntology":null},{"url":"/paper/noise-adaptive-confidence-sets-for-linear","slug":"noise-adaptive-confidence-sets-for-linear","title":"Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization","date":"2024-02-12","arxiv_id":"2402.07341","repositories_listed":1,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/noise-adaptive-confidence-sets-for-linear#ran","syntology_url":"https://syntology.ai/paper/2402.07341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07341"}},"official":{"repos":["jungtaekkim/losan-lofav"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/re-diffinet-modeling-discrepancies-in-tumor","slug":"re-diffinet-modeling-discrepancies-in-tumor","title":"Re-DiffiNet: Modeling discrepancies in tumor segmentation using diffusion models","date":"2024-02-12","arxiv_id":"2402.07354","repositories_listed":1,"syntology":null},{"url":"/paper/smx-sequential-monte-carlo-planning-for","slug":"smx-sequential-monte-carlo-planning-for","title":"SPO: Sequential Monte Carlo Policy Optimisation","date":"2024-02-12","arxiv_id":"2402.07963","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/smx-sequential-monte-carlo-planning-for#ran","syntology_url":"https://syntology.ai/paper/2402.07963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07963"}},"official":null}},{"url":"/paper/teller-a-trustworthy-framework-for","slug":"teller-a-trustworthy-framework-for","title":"TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection","date":"2024-02-12","arxiv_id":"2402.07776","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-group-specific-distributed-concept","slug":"unveiling-group-specific-distributed-concept","title":"Unveiling Group-Specific Distributed Concept Drift: A Fairness Imperative in Federated Learning","date":"2024-02-12","arxiv_id":"2402.07586","repositories_listed":1,"syntology":null},{"url":"/paper/wildfiregpt-tailored-large-language-model-for","slug":"wildfiregpt-tailored-large-language-model-for","title":"A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation","date":"2024-02-12","arxiv_id":"2402.07877","repositories_listed":1,"syntology":null},{"url":"/paper/self-consistent-conformal-prediction","slug":"self-consistent-conformal-prediction","title":"Self-Calibrating Conformal Prediction","date":"2024-02-11","arxiv_id":"2402.07307","repositories_listed":1,"syntology":{"n":25,"n_ran":23,"n_constructed":4,"n_ran_checked":9,"n_instrument":14,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"23 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 14 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/self-consistent-conformal-prediction#ran","syntology_url":"https://syntology.ai/paper/2402.07307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07307"}},"official":{"repos":["larsvanderlaan/selfcalibratingconformal"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/deepcover-advancing-rnn-test-coverage-and","slug":"deepcover-advancing-rnn-test-coverage-and","title":"DeepCover: Advancing RNN Test Coverage and Online Error Prediction using State Machine Extraction","date":"2024-02-10","arxiv_id":"2402.06966","repositories_listed":1,"syntology":null},{"url":"/paper/entropy-regularized-token-level-policy","slug":"entropy-regularized-token-level-policy","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","date":"2024-02-09","arxiv_id":"2402.06700","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/entropy-regularized-token-level-policy#ran","syntology_url":"https://syntology.ai/paper/2402.06700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06700"}},"official":{"repos":["morning9393/etpo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/premier-taco-pretraining-multitask","slug":"premier-taco-pretraining-multitask","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","date":"2024-02-09","arxiv_id":"2402.06187","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"6 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/premier-taco-pretraining-multitask#ran","syntology_url":"https://syntology.ai/paper/2402.06187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06187"}},"official":{"repos":["premiertaco/premier-taco"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/the-uk-universities-superannuation-scheme","slug":"the-uk-universities-superannuation-scheme","title":"The UK Universities Superannuation Scheme valuations 2014-2023: gilt yield dependence, self-sufficiency and metrics","date":"2024-02-08","arxiv_id":"2403.08811","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-hypergraph-network-for-trust","slug":"adaptive-hypergraph-network-for-trust","title":"Adaptive Hypergraph Network for Trust Prediction","date":"2024-02-07","arxiv_id":"2402.05154","repositories_listed":1,"syntology":null},{"url":"/paper/flowpg-action-constrained-policy-gradient-1","slug":"flowpg-action-constrained-policy-gradient-1","title":"FlowPG: Action-constrained Policy Gradient with Normalizing Flows","date":"2024-02-07","arxiv_id":"2402.05149","repositories_listed":1,"syntology":null},{"url":"/paper/oil-ad-an-anomaly-detection-framework-for","slug":"oil-ad-an-anomaly-detection-framework-for","title":"OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences","date":"2024-02-07","arxiv_id":"2402.04567","repositories_listed":1,"syntology":null},{"url":"/paper/teranga-go-carpooling-collaborative","slug":"teranga-go-carpooling-collaborative","title":"Teranga Go!: Carpooling Collaborative Consumption Community with multi-criteria hesitant fuzzy linguistic term set opinions to build confidence and trust","date":"2024-02-07","arxiv_id":"2403.05550","repositories_listed":1,"syntology":null},{"url":"/paper/adaflow-imitation-learning-with-variance","slug":"adaflow-imitation-learning-with-variance","title":"AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies","date":"2024-02-06","arxiv_id":"2402.04292","repositories_listed":1,"syntology":null},{"url":"/paper/learning-metrics-that-maximise-power-for","slug":"learning-metrics-that-maximise-power-for","title":"Learning Metrics that Maximise Power for Accelerated A/B-Tests","date":"2024-02-06","arxiv_id":"2402.03915","repositories_listed":1,"syntology":null},{"url":"/paper/logical-specifications-guided-dynamic-task","slug":"logical-specifications-guided-dynamic-task","title":"Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents","date":"2024-02-06","arxiv_id":"2402.03678","repositories_listed":1,"syntology":null},{"url":"/paper/skill-set-optimization-reinforcing-language","slug":"skill-set-optimization-reinforcing-language","title":"Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills","date":"2024-02-05","arxiv_id":"2402.03244","repositories_listed":1,"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/skill-set-optimization-reinforcing-language#ran","syntology_url":"https://syntology.ai/paper/2402.03244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03244"}},"official":{"repos":["allenai/sso"],"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/v-irl-grounding-virtual-intelligence-in-real","slug":"v-irl-grounding-virtual-intelligence-in-real","title":"V-IRL: Grounding Virtual Intelligence in Real Life","date":"2024-02-05","arxiv_id":"2402.03310","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":5,"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/v-irl-grounding-virtual-intelligence-in-real#ran","syntology_url":"https://syntology.ai/paper/2402.03310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03310"}},"official":{"repos":["VIRL-Platform/VIRL"],"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/interpreting-graph-neural-networks-with-in","slug":"interpreting-graph-neural-networks-with-in","title":"Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks","date":"2024-02-03","arxiv_id":"2402.02036","repositories_listed":1,"syntology":null},{"url":"/paper/query-decision-regression-between-shortest","slug":"query-decision-regression-between-shortest","title":"Query-decision Regression between Shortest Path and Minimum Steiner Tree","date":"2024-02-03","arxiv_id":"2402.02211","repositories_listed":1,"syntology":null},{"url":"/paper/approximate-control-for-continuous-time","slug":"approximate-control-for-continuous-time","title":"Approximate Control for Continuous-Time POMDPs","date":"2024-02-02","arxiv_id":"2402.01431","repositories_listed":1,"syntology":null},{"url":"/paper/climbing-the-ladder-of-interpretability-with","slug":"climbing-the-ladder-of-interpretability-with","title":"Counterfactual Concept Bottleneck Models","date":"2024-02-02","arxiv_id":"2402.01408","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":16,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/climbing-the-ladder-of-interpretability-with#ran","syntology_url":"https://syntology.ai/paper/2402.01408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01408"}},"official":{"repos":["gabriele-dominici/counterfactual-cbm"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/pokellmon-a-human-parity-agent-for-pokemon","slug":"pokellmon-a-human-parity-agent-for-pokemon","title":"PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models","date":"2024-02-02","arxiv_id":"2402.01118","repositories_listed":1,"syntology":null},{"url":"/paper/the-effect-of-diversity-on-group-decision","slug":"the-effect-of-diversity-on-group-decision","title":"The effect of diversity on group decision-making","date":"2024-02-02","arxiv_id":"2402.01427","repositories_listed":1,"syntology":null},{"url":"/paper/towards-the-new-xai-a-hypothesis-driven","slug":"towards-the-new-xai-a-hypothesis-driven","title":"Towards the New XAI: A Hypothesis-Driven Approach to Decision Support Using Evidence","date":"2024-02-02","arxiv_id":"2402.01292","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-hybrid-modeling-for-flexible","slug":"hierarchical-hybrid-modeling-for-flexible","title":"Deep hybrid models: infer and plan in a dynamic world","date":"2024-02-01","arxiv_id":"2402.10088","repositories_listed":1,"syntology":null},{"url":"/paper/raddqn-a-deep-q-learning-based-architecture","slug":"raddqn-a-deep-q-learning-based-architecture","title":"RadDQN: a Deep Q Learning-based Architecture for Finding Time-efficient Minimum Radiation Exposure Pathway","date":"2024-02-01","arxiv_id":"2402.00468","repositories_listed":1,"syntology":null},{"url":"/paper/vertical-symbolic-regression-via-deep-policy","slug":"vertical-symbolic-regression-via-deep-policy","title":"Vertical Symbolic Regression via Deep Policy Gradient","date":"2024-02-01","arxiv_id":"2402.00254","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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) · 0 unverified","sample_list":"/paper/vertical-symbolic-regression-via-deep-policy#ran","syntology_url":"https://syntology.ai/paper/2402.00254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00254"}},"official":{"repos":["jiangnanhugo/vsr-dpg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/x-cba-explainability-aided-catboosted-anomal","slug":"x-cba-explainability-aided-catboosted-anomal","title":"X-CBA: Explainability Aided CatBoosted Anomal-E for Intrusion Detection System","date":"2024-02-01","arxiv_id":"2402.00839","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-bias-driven-stratification-for","slug":"hierarchical-bias-driven-stratification-for","title":"Hierarchical Bias-Driven Stratification for Interpretable Causal Effect Estimation","date":"2024-01-31","arxiv_id":"2401.17737","repositories_listed":1,"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":3,"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/hierarchical-bias-driven-stratification-for#ran","syntology_url":"https://syntology.ai/paper/2401.17737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17737"}},"official":{"repos":["ibm-hrl-mlhls/bicause-trees"],"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/llm-voting-human-choices-and-ai-collective","slug":"llm-voting-human-choices-and-ai-collective","title":"LLM Voting: Human Choices and AI Collective Decision Making","date":"2024-01-31","arxiv_id":"2402.01766","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/llm-voting-human-choices-and-ai-collective#ran","syntology_url":"https://syntology.ai/paper/2402.01766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01766"}},"official":{"repos":["ethz-coss/LLM_voting"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/the-heterogeneous-aggregate-valence-analysis","slug":"the-heterogeneous-aggregate-valence-analysis","title":"The Mixed Aggregate Preference Logit Model: A Machine Learning Approach to Modeling Unobserved Heterogeneity in Discrete Choice Analysis","date":"2024-01-31","arxiv_id":"2402.00184","repositories_listed":1,"syntology":null},{"url":"/paper/layered-and-staged-monte-carlo-tree-search","slug":"layered-and-staged-monte-carlo-tree-search","title":"Layered and Staged Monte Carlo Tree Search for SMT Strategy Synthesis","date":"2024-01-30","arxiv_id":"2401.17159","repositories_listed":1,"syntology":null},{"url":"/paper/neuro-fuzzy-random-vector-functional-link","slug":"neuro-fuzzy-random-vector-functional-link","title":"Neuro-Fuzzy Random Vector Functional Link Neural Network for Classification and Regression Problems","date":"2024-01-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/goat-explaining-graph-neural-networks-via","slug":"goat-explaining-graph-neural-networks-via","title":"GOAt: Explaining Graph Neural Networks via Graph Output Attribution","date":"2024-01-26","arxiv_id":"2401.14578","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"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) · 6 unverified","sample_list":"/paper/goat-explaining-graph-neural-networks-via#ran","syntology_url":"https://syntology.ai/paper/2401.14578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14578"}},"official":{"repos":["sluxsr/goat"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/high-dimensional-forecasting-with-known","slug":"high-dimensional-forecasting-with-known","title":"High-dimensional forecasting with known knowns and known unknowns","date":"2024-01-26","arxiv_id":"2401.14582","repositories_listed":1,"syntology":null},{"url":"/paper/interpreting-time-series-transformer-models","slug":"interpreting-time-series-transformer-models","title":"Interpreting Time Series Transformer Models and Sensitivity Analysis of Population Age Groups to COVID-19 Infections","date":"2024-01-26","arxiv_id":"2401.15119","repositories_listed":1,"syntology":null},{"url":"/paper/neighbor-aware-calibration-of-segmentation","slug":"neighbor-aware-calibration-of-segmentation","title":"Neighbor-Aware Calibration of Segmentation Networks with Penalty-Based Constraints","date":"2024-01-25","arxiv_id":"2401.14487","repositories_listed":1,"syntology":null},{"url":"/paper/prompting-large-language-models-for-zero-shot-1","slug":"prompting-large-language-models-for-zero-shot-1","title":"Prompting Large Language Models for Zero-Shot Clinical Prediction with Structured Longitudinal Electronic Health Record Data","date":"2024-01-25","arxiv_id":"2402.01713","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"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, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prompting-large-language-models-for-zero-shot-1#ran","syntology_url":"https://syntology.ai/paper/2402.01713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01713"}},"official":{"repos":["yhzhu99/llm4healthcare"],"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/reinforcement-learning-with-hidden-markov","slug":"reinforcement-learning-with-hidden-markov","title":"HMM for Discovering Decision-Making Dynamics Using Reinforcement Learning Experiments","date":"2024-01-25","arxiv_id":"2401.13929","repositories_listed":1,"syntology":null},{"url":"/paper/respect-the-model-fine-grained-and-robust-1","slug":"respect-the-model-fine-grained-and-robust-1","title":"Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition","date":"2024-01-25","arxiv_id":"2402.03348","repositories_listed":1,"syntology":{"n":11,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/respect-the-model-fine-grained-and-robust-1#ran","syntology_url":"https://syntology.ai/paper/2402.03348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03348"}},"official":null}},{"url":"/paper/true-knowledge-comes-from-practice-aligning","slug":"true-knowledge-comes-from-practice-aligning","title":"True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning","date":"2024-01-25","arxiv_id":"2401.14151","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/true-knowledge-comes-from-practice-aligning#ran","syntology_url":"https://syntology.ai/paper/2401.14151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14151"}},"official":{"repos":["weihaotan/twosome"],"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/a-v2x-based-privacy-preserving-federated","slug":"a-v2x-based-privacy-preserving-federated","title":"A V2X-based Privacy Preserving Federated Measuring and Learning System","date":"2024-01-24","arxiv_id":"2401.13848","repositories_listed":1,"syntology":null},{"url":"/paper/conformal-prediction-sets-improve-human","slug":"conformal-prediction-sets-improve-human","title":"Conformal Prediction Sets Improve Human Decision Making","date":"2024-01-24","arxiv_id":"2401.13744","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conformal-prediction-sets-improve-human#ran","syntology_url":"https://syntology.ai/paper/2401.13744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.13744"}},"official":{"repos":["layer6ai-labs/hitl-conformal-prediction"],"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","unlocated"]}}},{"url":"/paper/discount-distributional-counterfactual","slug":"discount-distributional-counterfactual","title":"Distributional Counterfactual Explanations With Optimal Transport","date":"2024-01-23","arxiv_id":"2401.13112","repositories_listed":1,"syntology":null},{"url":"/paper/edge-computing-enabled-deep-learning-approach","slug":"edge-computing-enabled-deep-learning-approach","title":"Edge-Computing-Enabled Deep Learning Approach for Low-Light Satellite Image Enhancement","date":"2024-01-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hazard-challenge-embodied-decision-making-in","slug":"hazard-challenge-embodied-decision-making-in","title":"HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments","date":"2024-01-23","arxiv_id":"2401.12975","repositories_listed":1,"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/hazard-challenge-embodied-decision-making-in#ran","syntology_url":"https://syntology.ai/paper/2401.12975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12975"}},"official":{"repos":["umass-foundation-model/hazard"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/differentiable-tree-search-in-latent-state","slug":"differentiable-tree-search-in-latent-state","title":"Differentiable Tree Search Network","date":"2024-01-22","arxiv_id":"2401.11660","repositories_listed":1,"syntology":null},{"url":"/paper/improve-robustness-of-eye-disease-detection","slug":"improve-robustness-of-eye-disease-detection","title":"Enhance Eye Disease Detection using Learnable Probabilistic Discrete Latents in Machine Learning Architectures","date":"2024-01-21","arxiv_id":"2402.16865","repositories_listed":1,"syntology":null},{"url":"/paper/information-theoretic-state-variable","slug":"information-theoretic-state-variable","title":"Information-Theoretic State Variable Selection for Reinforcement Learning","date":"2024-01-21","arxiv_id":"2401.11512","repositories_listed":1,"syntology":null}],"record_sha256":"8105dd56d52a8f22016abd4b0a031bc0da4a416e259640d85e27b01566a3743a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}