{"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/ran/4","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":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":4,"pages_in_order":7,"rows_per_page":100,"rows":[301,400],"of":678,"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/papers/ran/1","prev":"/task/decision-making/papers/ran/3","next":"/task/decision-making/papers/ran/5","papers":[{"url":"/paper/rladapter-bridging-large-language-models-to","slug":"rladapter-bridging-large-language-models-to","title":"AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback","date":"2023-09-29","arxiv_id":"2309.17176","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rladapter-bridging-large-language-models-to#ran","syntology_url":"https://syntology.ai/paper/2309.17176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17176"}},"official":{"repos":["pku-rl/adarefiner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/alphazero-like-tree-search-can-guide-large","slug":"alphazero-like-tree-search-can-guide-large","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","date":"2023-09-29","arxiv_id":"2309.17179","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"8 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/alphazero-like-tree-search-can-guide-large#ran","syntology_url":"https://syntology.ai/paper/2309.17179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17179"}},"official":{"repos":["waterhorse1/llm_tree_search"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/memory-gym-partially-observable-challenges-to","slug":"memory-gym-partially-observable-challenges-to","title":"Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents","date":"2023-09-29","arxiv_id":"2309.17207","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/memory-gym-partially-observable-challenges-to#ran","syntology_url":"https://syntology.ai/paper/2309.17207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17207"}},"official":{"repos":["marcometer/endless-memory-gym"],"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/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/suspicion-agent-playing-imperfect-information","slug":"suspicion-agent-playing-imperfect-information","title":"Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4","date":"2023-09-29","arxiv_id":"2309.17277","repositories_listed":1,"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":4,"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/suspicion-agent-playing-imperfect-information#ran","syntology_url":"https://syntology.ai/paper/2309.17277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17277"}},"official":{"repos":["cr-gjx/suspicion-agent"],"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/motif-intrinsic-motivation-from-artificial","slug":"motif-intrinsic-motivation-from-artificial","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","date":"2023-09-29","arxiv_id":"2310.00166","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/motif-intrinsic-motivation-from-artificial#ran","syntology_url":"https://syntology.ai/paper/2310.00166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00166"}},"official":{"repos":["facebookresearch/motif"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/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/trace-trajectory-counterfactual-explanation","slug":"trace-trajectory-counterfactual-explanation","title":"TraCE: Trajectory Counterfactual Explanation Scores","date":"2023-09-27","arxiv_id":"2309.15965","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/trace-trajectory-counterfactual-explanation#ran","syntology_url":"https://syntology.ai/paper/2309.15965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15965"}},"official":{"repos":["jeffnclark/trace"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/are-human-generated-demonstrations-necessary","slug":"are-human-generated-demonstrations-necessary","title":"Are Human-generated Demonstrations Necessary for In-context Learning?","date":"2023-09-26","arxiv_id":"2309.14681","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/are-human-generated-demonstrations-necessary#ran","syntology_url":"https://syntology.ai/paper/2309.14681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14681"}},"official":{"repos":["ruili33/sec"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/estimating-treatment-effects-under","slug":"estimating-treatment-effects-under","title":"Estimating Treatment Effects Under Heterogeneous Interference","date":"2023-09-25","arxiv_id":"2309.13884","repositories_listed":1,"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/estimating-treatment-effects-under#ran","syntology_url":"https://syntology.ai/paper/2309.13884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13884"}},"official":{"repos":["linxf208/hinite"],"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/graph-enhanced-optimizers-for-structure-aware","slug":"graph-enhanced-optimizers-for-structure-aware","title":"Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution","date":"2023-09-24","arxiv_id":"2310.03032","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/graph-enhanced-optimizers-for-structure-aware#ran","syntology_url":"https://syntology.ai/paper/2310.03032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03032"}},"official":{"repos":["mtandhj/sevo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mmst-vit-climate-change-aware-crop-yield","slug":"mmst-vit-climate-change-aware-crop-yield","title":"MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer","date":"2023-09-16","arxiv_id":"2309.09067","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/mmst-vit-climate-change-aware-crop-yield#ran","syntology_url":"https://syntology.ai/paper/2309.09067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09067"}},"official":{"repos":["fudong03/mmst-vit"],"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/laser-llm-agent-with-state-space-exploration","slug":"laser-llm-agent-with-state-space-exploration","title":"LASER: LLM Agent with State-Space Exploration for Web Navigation","date":"2023-09-15","arxiv_id":"2309.08172","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/laser-llm-agent-with-state-space-exploration#ran","syntology_url":"https://syntology.ai/paper/2309.08172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.08172"}},"official":{"repos":["mayer123/laser"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/trafficgpt-viewing-processing-and-interacting","slug":"trafficgpt-viewing-processing-and-interacting","title":"TrafficGPT: Viewing, Processing and Interacting with Traffic Foundation Models","date":"2023-09-13","arxiv_id":"2309.06719","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":5,"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/trafficgpt-viewing-processing-and-interacting#ran","syntology_url":"https://syntology.ai/paper/2309.06719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06719"}},"official":{"repos":["lijlansg/trafficgpt"],"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/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/devil-decoding-vision-features-into-language","slug":"devil-decoding-vision-features-into-language","title":"DeViL: Decoding Vision features into Language","date":"2023-09-04","arxiv_id":"2309.01617","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"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) · 2 unverified","sample_list":"/paper/devil-decoding-vision-features-into-language#ran","syntology_url":"https://syntology.ai/paper/2309.01617","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01617"}},"official":{"repos":["ExplainableML/DeViL"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/everything-everywhere-all-in-one-evaluation","slug":"everything-everywhere-all-in-one-evaluation","title":"One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions","date":"2023-08-31","arxiv_id":"2308.16681","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/everything-everywhere-all-in-one-evaluation#ran","syntology_url":"https://syntology.ai/paper/2308.16681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16681"}},"official":{"repos":["reliable-ai/fairml-multiverse"],"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/gnfactor-multi-task-real-robot-learning-with","slug":"gnfactor-multi-task-real-robot-learning-with","title":"GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields","date":"2023-08-31","arxiv_id":"2308.16891","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"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) · 3 unverified","sample_list":"/paper/gnfactor-multi-task-real-robot-learning-with#ran","syntology_url":"https://syntology.ai/paper/2308.16891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16891"}},"official":{"repos":["YanjieZe/GNFactor"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-reinforcement-learning-training","slug":"improving-reinforcement-learning-training","title":"Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation","date":"2023-08-29","arxiv_id":"2308.14947","repositories_listed":1,"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":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) · 0 unverified","sample_list":"/paper/improving-reinforcement-learning-training#ran","syntology_url":"https://syntology.ai/paper/2308.14947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14947"}},"official":{"repos":["raise-lab/soc-nav-training"],"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/large-language-model-as-autonomous-decision","slug":"large-language-model-as-autonomous-decision","title":"Rational Decision-Making Agent with Internalized Utility Judgment","date":"2023-08-24","arxiv_id":"2308.12519","repositories_listed":0,"syntology":{"n":15,"n_ran":11,"n_constructed":2,"n_ran_checked":8,"n_instrument":3,"n_unverified":4,"n_honours":4,"n_violates":1,"n_no_contract":3,"n_pointer_only":15,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/large-language-model-as-autonomous-decision#ran","syntology_url":"https://syntology.ai/paper/2308.12519","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12519"}},"official":null}},{"url":"/paper/out-of-the-cage-how-stochastic-parrots-win-in","slug":"out-of-the-cage-how-stochastic-parrots-win-in","title":"Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments","date":"2023-08-23","arxiv_id":"2308.12086","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"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) · 1 unverified","sample_list":"/paper/out-of-the-cage-how-stochastic-parrots-win-in#ran","syntology_url":"https://syntology.ai/paper/2308.12086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12086"}},"official":{"repos":["stratosphereips/netsecgame"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/domain-generalization-via-rationale","slug":"domain-generalization-via-rationale","title":"Domain Generalization via Rationale Invariance","date":"2023-08-22","arxiv_id":"2308.11158","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":15,"phrase":"11 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; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/domain-generalization-via-rationale#ran","syntology_url":"https://syntology.ai/paper/2308.11158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11158"}},"official":{"repos":["liangchen527/ridg"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"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/ted-spad-temporal-distinctiveness-for-self","slug":"ted-spad-temporal-distinctiveness-for-self","title":"TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection","date":"2023-08-21","arxiv_id":"2308.11072","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ted-spad-temporal-distinctiveness-for-self#ran","syntology_url":"https://syntology.ai/paper/2308.11072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11072"}},"official":{"repos":["ucf-crcv/ted-spad"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"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/scaled-up-discovery-of-latent-concepts-in","slug":"scaled-up-discovery-of-latent-concepts-in","title":"Scaling up Discovery of Latent Concepts in Deep NLP Models","date":"2023-08-20","arxiv_id":"2308.10263","repositories_listed":1,"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/scaled-up-discovery-of-latent-concepts-in#ran","syntology_url":"https://syntology.ai/paper/2308.10263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10263"}},"official":{"repos":["qcri/latent_concept_analysis"],"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/mindmap-knowledge-graph-prompting-sparks","slug":"mindmap-knowledge-graph-prompting-sparks","title":"MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models","date":"2023-08-17","arxiv_id":"2308.09729","repositories_listed":1,"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":8,"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/mindmap-knowledge-graph-prompting-sparks#ran","syntology_url":"https://syntology.ai/paper/2308.09729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09729"}},"official":{"repos":["wyl-willing/MindMap"],"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/autogen-enabling-next-gen-llm-applications","slug":"autogen-enabling-next-gen-llm-applications","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","date":"2023-08-16","arxiv_id":"2308.08155","repositories_listed":3,"syntology":{"n":8,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"1 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; 0 where Syntology's instrument failed) · 7 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/autogen-enabling-next-gen-llm-applications#ran","syntology_url":"https://syntology.ai/paper/2308.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08155"}},"official":null}},{"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/cumulative-reasoning-with-large-language","slug":"cumulative-reasoning-with-large-language","title":"Cumulative Reasoning with Large Language Models","date":"2023-08-08","arxiv_id":"2308.04371","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cumulative-reasoning-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2308.04371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04371"}},"official":{"repos":["iiis-ai/cumulative-reasoning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/agentbench-evaluating-llms-as-agents","slug":"agentbench-evaluating-llms-as-agents","title":"AgentBench: Evaluating LLMs as Agents","date":"2023-08-07","arxiv_id":"2308.03688","repositories_listed":1,"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/agentbench-evaluating-llms-as-agents#ran","syntology_url":"https://syntology.ai/paper/2308.03688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03688"}},"official":{"repos":["thudm/agentbench"],"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/instructed-to-bias-instruction-tuned-language","slug":"instructed-to-bias-instruction-tuned-language","title":"Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias","date":"2023-08-01","arxiv_id":"2308.00225","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/instructed-to-bias-instruction-tuned-language#ran","syntology_url":"https://syntology.ai/paper/2308.00225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.00225"}},"official":{"repos":["itay1itzhak/instructedtobias"],"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"]}}},{"url":"/paper/decision-focused-learning-foundations-state","slug":"decision-focused-learning-foundations-state","title":"Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities","date":"2023-07-25","arxiv_id":"2307.13565","repositories_listed":1,"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":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) · 0 unverified","sample_list":"/paper/decision-focused-learning-foundations-state#ran","syntology_url":"https://syntology.ai/paper/2307.13565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.13565"}},"official":{"repos":["predopt/predopt-benchmarks"],"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/continuation-path-learning-for-homotopy","slug":"continuation-path-learning-for-homotopy","title":"Continuation Path Learning for Homotopy Optimization","date":"2023-07-24","arxiv_id":"2307.12551","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/continuation-path-learning-for-homotopy#ran","syntology_url":"https://syntology.ai/paper/2307.12551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12551"}},"official":{"repos":["xi-l/cpl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/decoding-the-enigma-benchmarking-humans-and","slug":"decoding-the-enigma-benchmarking-humans-and","title":"Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory","date":"2023-07-20","arxiv_id":"2307.10768","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/decoding-the-enigma-benchmarking-humans-and#ran","syntology_url":"https://syntology.ai/paper/2307.10768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10768"}},"official":{"repos":["zhanglab-deepneurocoglab/worm"],"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/interpreting-and-correcting-medical-image","slug":"interpreting-and-correcting-medical-image","title":"Interpreting and Correcting Medical Image Classification with PIP-Net","date":"2023-07-19","arxiv_id":"2307.10404","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":13,"phrase":"9 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/interpreting-and-correcting-medical-image#ran","syntology_url":"https://syntology.ai/paper/2307.10404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10404"}},"official":{"repos":["m-nauta/pipnet"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"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/is-imitation-all-you-need-generalized","slug":"is-imitation-all-you-need-generalized","title":"Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training","date":"2023-07-16","arxiv_id":"2307.07909","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"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) · 2 unverified","sample_list":"/paper/is-imitation-all-you-need-generalized#ran","syntology_url":"https://syntology.ai/paper/2307.07909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07909"}},"official":{"repos":["yunyikristy/dualmind"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/communicative-agents-for-software-development","slug":"communicative-agents-for-software-development","title":"ChatDev: Communicative Agents for Software Development","date":"2023-07-16","arxiv_id":"2307.07924","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":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/communicative-agents-for-software-development#ran","syntology_url":"https://syntology.ai/paper/2307.07924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07924"}},"official":{"repos":["openbmb/chatdev"],"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/velma-verbalization-embodiment-of-llm-agents","slug":"velma-verbalization-embodiment-of-llm-agents","title":"VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View","date":"2023-07-12","arxiv_id":"2307.06082","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":6,"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/velma-verbalization-embodiment-of-llm-agents#ran","syntology_url":"https://syntology.ai/paper/2307.06082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06082"}},"official":{"repos":["raphael-sch/velma"],"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/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/epidemic-modeling-with-generative-agents","slug":"epidemic-modeling-with-generative-agents","title":"Epidemic Modeling with Generative Agents","date":"2023-07-11","arxiv_id":"2307.04986","repositories_listed":1,"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":4,"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/epidemic-modeling-with-generative-agents#ran","syntology_url":"https://syntology.ai/paper/2307.04986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.04986"}},"official":{"repos":["bear96/gabm-epidemic"],"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/learning-to-generate-equitable-text-in","slug":"learning-to-generate-equitable-text-in","title":"Learning to Generate Equitable Text in Dialogue from Biased Training Data","date":"2023-07-10","arxiv_id":"2307.04303","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"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: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-generate-equitable-text-in#ran","syntology_url":"https://syntology.ai/paper/2307.04303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.04303"}},"official":{"repos":["anthonysicilia/equitable-dialogue-acl2023"],"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/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/causal-discovery-with-language-models-as","slug":"causal-discovery-with-language-models-as","title":"Causal Discovery with Language Models as Imperfect Experts","date":"2023-07-05","arxiv_id":"2307.02390","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/causal-discovery-with-language-models-as#ran","syntology_url":"https://syntology.ai/paper/2307.02390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02390"}},"official":{"repos":["stephlong614/causal-disco"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/analyzing-intentional-behavior-in-autonomous","slug":"analyzing-intentional-behavior-in-autonomous","title":"Analyzing Intentional Behavior in Autonomous Agents under Uncertainty","date":"2023-07-04","arxiv_id":"2307.01532","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/analyzing-intentional-behavior-in-autonomous#ran","syntology_url":"https://syntology.ai/paper/2307.01532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01532"}},"official":{"repos":["filipcano/intentional-autonomous-agents"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-synthetic-electrocardiogram-ecg-image","slug":"a-synthetic-electrocardiogram-ecg-image","title":"ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization","date":"2023-07-04","arxiv_id":"2307.01946","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-synthetic-electrocardiogram-ecg-image#ran","syntology_url":"https://syntology.ai/paper/2307.01946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01946"}},"official":{"repos":["alphanumericslab/ecg-image-kit"],"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/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/can-llms-express-their-uncertainty-an","slug":"can-llms-express-their-uncertainty-an","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","date":"2023-06-22","arxiv_id":"2306.13063","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/can-llms-express-their-uncertainty-an#ran","syntology_url":"https://syntology.ai/paper/2306.13063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.13063"}},"official":{"repos":["miaoxiong2320/llm-uncertainty"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/jumanji-a-diverse-suite-of-scalable","slug":"jumanji-a-diverse-suite-of-scalable","title":"Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX","date":"2023-06-16","arxiv_id":"2306.09884","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/jumanji-a-diverse-suite-of-scalable#ran","syntology_url":"https://syntology.ai/paper/2306.09884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09884"}},"official":{"repos":["instadeepai/jumanji"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/chessgpt-bridging-policy-learning-and-1","slug":"chessgpt-bridging-policy-learning-and-1","title":"ChessGPT: Bridging Policy Learning and Language Modeling","date":"2023-06-15","arxiv_id":"2306.09200","repositories_listed":1,"syntology":{"n":20,"n_ran":14,"n_constructed":8,"n_ran_checked":10,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/chessgpt-bridging-policy-learning-and-1#ran","syntology_url":"https://syntology.ai/paper/2306.09200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09200"}},"official":{"repos":["waterhorse1/chessgpt"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":8,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/arbitrariness-lies-beyond-the-fairness","slug":"arbitrariness-lies-beyond-the-fairness","title":"Arbitrariness Lies Beyond the Fairness-Accuracy Frontier","date":"2023-06-15","arxiv_id":"2306.09425","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/arbitrariness-lies-beyond-the-fairness#ran","syntology_url":"https://syntology.ai/paper/2306.09425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09425"}},"official":null}},{"url":"/paper/the-importance-of-time-in-causal-algorithmic","slug":"the-importance-of-time-in-causal-algorithmic","title":"The Importance of Time in Causal Algorithmic Recourse","date":"2023-06-08","arxiv_id":"2306.05082","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/the-importance-of-time-in-causal-algorithmic#ran","syntology_url":"https://syntology.ai/paper/2306.05082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05082"}},"official":{"repos":["marti5ini/time-car"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/finding-counterfactually-optimal-action","slug":"finding-counterfactually-optimal-action","title":"Finding Counterfactually Optimal Action Sequences in Continuous State Spaces","date":"2023-06-06","arxiv_id":"2306.03929","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"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) · 4 unverified","sample_list":"/paper/finding-counterfactually-optimal-action#ran","syntology_url":"https://syntology.ai/paper/2306.03929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03929"}},"official":{"repos":["networks-learning/counterfactual-continuous-mdp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-study-of-situational-reasoning-for-traffic","slug":"a-study-of-situational-reasoning-for-traffic","title":"A Study of Situational Reasoning for Traffic Understanding","date":"2023-06-05","arxiv_id":"2306.02520","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-study-of-situational-reasoning-for-traffic#ran","syntology_url":"https://syntology.ai/paper/2306.02520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02520"}},"official":{"repos":["saccharomycetes/text-based-traffic-understanding"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"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"]}}},{"url":"/paper/a-large-scale-study-of-probabilistic","slug":"a-large-scale-study-of-probabilistic","title":"A Large-Scale Study of Probabilistic Calibration in Neural Network Regression","date":"2023-06-05","arxiv_id":"2306.02738","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 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; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-large-scale-study-of-probabilistic#ran","syntology_url":"https://syntology.ai/paper/2306.02738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02738"}},"official":{"repos":["vekteur/probabilistic-calibration-study"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"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/auto-gpt-for-online-decision-making","slug":"auto-gpt-for-online-decision-making","title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","date":"2023-06-04","arxiv_id":"2306.02224","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"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) · 5 unverified","sample_list":"/paper/auto-gpt-for-online-decision-making#ran","syntology_url":"https://syntology.ai/paper/2306.02224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02224"}},"official":{"repos":["younghuman/llmagent"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/torchrl-a-data-driven-decision-making-library","slug":"torchrl-a-data-driven-decision-making-library","title":"TorchRL: A data-driven decision-making library for PyTorch","date":"2023-06-01","arxiv_id":"2306.00577","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"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) · 1 unverified","sample_list":"/paper/torchrl-a-data-driven-decision-making-library#ran","syntology_url":"https://syntology.ai/paper/2306.00577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00577"}},"official":null}},{"url":"/paper/extracting-reward-functions-from-diffusion","slug":"extracting-reward-functions-from-diffusion","title":"Extracting Reward Functions from Diffusion Models","date":"2023-06-01","arxiv_id":"2306.01804","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/extracting-reward-functions-from-diffusion#ran","syntology_url":"https://syntology.ai/paper/2306.01804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01804"}},"official":{"repos":["FelipeNuti/diffusion-relative-rewards"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/explanations-as-features-llm-based-features","slug":"explanations-as-features-llm-based-features","title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","date":"2023-05-31","arxiv_id":"2305.19523","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/explanations-as-features-llm-based-features#ran","syntology_url":"https://syntology.ai/paper/2305.19523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19523"}},"official":{"repos":["XiaoxinHe/TAPE","xiaoxinhe/tape_arxiv_2023"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/signal-is-harder-to-learn-than-bias-debiasing","slug":"signal-is-harder-to-learn-than-bias-debiasing","title":"Signal Is Harder To Learn Than Bias: Debiasing with Focal Loss","date":"2023-05-31","arxiv_id":"2305.19671","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"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 4 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; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/signal-is-harder-to-learn-than-bias-debiasing#ran","syntology_url":"https://syntology.ai/paper/2305.19671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19671"}},"official":{"repos":["mvandenhi/signal-is-harder"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/faithfulness-tests-for-natural-language","slug":"faithfulness-tests-for-natural-language","title":"Faithfulness Tests for Natural Language Explanations","date":"2023-05-29","arxiv_id":"2305.18029","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/faithfulness-tests-for-natural-language#ran","syntology_url":"https://syntology.ai/paper/2305.18029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18029"}},"official":{"repos":["copenlu/nle_faithfulness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/chatgpt-powered-conversational-drug-editing","slug":"chatgpt-powered-conversational-drug-editing","title":"ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback","date":"2023-05-29","arxiv_id":"2305.18090","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/chatgpt-powered-conversational-drug-editing#ran","syntology_url":"https://syntology.ai/paper/2305.18090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18090"}},"official":{"repos":["chao1224/chatdrug"],"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/adaplanner-adaptive-planning-from-feedback-1","slug":"adaplanner-adaptive-planning-from-feedback-1","title":"AdaPlanner: Adaptive Planning from Feedback with Language Models","date":"2023-05-26","arxiv_id":"2305.16653","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/adaplanner-adaptive-planning-from-feedback-1#ran","syntology_url":"https://syntology.ai/paper/2305.16653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16653"}},"official":{"repos":["haotiansun14/adaplanner"],"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/future-conditioned-unsupervised-pretraining","slug":"future-conditioned-unsupervised-pretraining","title":"Future-conditioned Unsupervised Pretraining for Decision Transformer","date":"2023-05-26","arxiv_id":"2305.16683","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/future-conditioned-unsupervised-pretraining#ran","syntology_url":"https://syntology.ai/paper/2305.16683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16683"}},"official":{"repos":["fffffarmer/pdt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/better-batch-for-deep-probabilistic-time","slug":"better-batch-for-deep-probabilistic-time","title":"Better Batch for Deep Probabilistic Time Series Forecasting","date":"2023-05-26","arxiv_id":"2305.17028","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/better-batch-for-deep-probabilistic-time#ran","syntology_url":"https://syntology.ai/paper/2305.17028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17028"}},"official":{"repos":["rottenivy/betterbatch"],"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/koopman-kernel-regression-1","slug":"koopman-kernel-regression-1","title":"Koopman Kernel Regression","date":"2023-05-25","arxiv_id":"2305.16215","repositories_listed":1,"syntology":{"n":39,"n_ran":30,"n_constructed":0,"n_ran_checked":30,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":30,"n_pointer_only":0,"phrase":"30 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 0 violated, 30 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/koopman-kernel-regression-1#ran","syntology_url":"https://syntology.ai/paper/2305.16215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16215"}},"official":{"repos":["TUM-ITR/koopcore"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":0,"n_ran_no_instrument_failure":23,"n_unverified":4,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/prompt-optimization-of-large-language-model","slug":"prompt-optimization-of-large-language-model","title":"AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models","date":"2023-05-24","arxiv_id":"2305.15064","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/prompt-optimization-of-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2305.15064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15064"}},"official":{"repos":["owaski/autoplan"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/think-before-you-act-decision-transformers","slug":"think-before-you-act-decision-transformers","title":"Think Before You Act: Decision Transformers with Working Memory","date":"2023-05-24","arxiv_id":"2305.16338","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":3,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/think-before-you-act-decision-transformers#ran","syntology_url":"https://syntology.ai/paper/2305.16338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16338"}},"official":{"repos":["luciferkonn/dt_mem"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-prompting-assists-large-language","slug":"hierarchical-prompting-assists-large-language","title":"Hierarchical Prompting Assists Large Language Model on Web Navigation","date":"2023-05-23","arxiv_id":"2305.14257","repositories_listed":3,"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/hierarchical-prompting-assists-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.14257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14257"}},"official":{"repos":["robert1003/ash-prompting"],"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/class-meet-spock-an-education-tutoring","slug":"class-meet-spock-an-education-tutoring","title":"CLASS: A Design Framework for building Intelligent Tutoring Systems based on Learning Science principles","date":"2023-05-22","arxiv_id":"2305.13272","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/class-meet-spock-an-education-tutoring#ran","syntology_url":"https://syntology.ai/paper/2305.13272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13272"}},"official":{"repos":["luffycodes/tutorbot-spock"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/training-diffusion-models-with-reinforcement","slug":"training-diffusion-models-with-reinforcement","title":"Training Diffusion Models with Reinforcement Learning","date":"2023-05-22","arxiv_id":"2305.13301","repositories_listed":3,"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/training-diffusion-models-with-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2305.13301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13301"}},"official":{"repos":["kvablack/ddpo-pytorch"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/diving-into-the-inter-consistency-of-large","slug":"diving-into-the-inter-consistency-of-large","title":"Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate","date":"2023-05-19","arxiv_id":"2305.11595","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/diving-into-the-inter-consistency-of-large#ran","syntology_url":"https://syntology.ai/paper/2305.11595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11595"}},"official":{"repos":["waste-wood/ford"],"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/counterfactually-comparing-abstaining-1","slug":"counterfactually-comparing-abstaining-1","title":"Counterfactually Comparing Abstaining Classifiers","date":"2023-05-17","arxiv_id":"2305.10564","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/counterfactually-comparing-abstaining-1#ran","syntology_url":"https://syntology.ai/paper/2305.10564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10564"}},"official":{"repos":["yjchoe/comparingabstainingclassifiers"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tree-of-thoughts-deliberate-problem-solving-1","slug":"tree-of-thoughts-deliberate-problem-solving-1","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","date":"2023-05-17","arxiv_id":"2305.10601","repositories_listed":6,"syntology":{"n":24,"n_ran":19,"n_constructed":6,"n_ran_checked":18,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":18,"n_pointer_only":1,"phrase":"19 ran (of which 6 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/tree-of-thoughts-deliberate-problem-solving-1#ran","syntology_url":"https://syntology.ai/paper/2305.10601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10601"}},"official":{"repos":["princeton-nlp/tree-of-thought-llm","ysymyth/tree-of-thought-llm"],"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":["community","listed","official"]}}},{"url":"/paper/cuts-high-dimensional-causal-discovery-from","slug":"cuts-high-dimensional-causal-discovery-from","title":"CUTS+: High-dimensional Causal Discovery from Irregular Time-series","date":"2023-05-10","arxiv_id":"2305.05890","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cuts-high-dimensional-causal-discovery-from#ran","syntology_url":"https://syntology.ai/paper/2305.05890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05890"}},"official":{"repos":["jarrycyx/unn"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-classification-of-feedback-loops-and-their","slug":"a-classification-of-feedback-loops-and-their","title":"A Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systems","date":"2023-05-10","arxiv_id":"2305.06055","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/a-classification-of-feedback-loops-and-their#ran","syntology_url":"https://syntology.ai/paper/2305.06055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06055"}},"official":{"repos":["paganick/feedback-loops-and-biases"],"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/dexart-benchmarking-generalizable-dexterous","slug":"dexart-benchmarking-generalizable-dexterous","title":"DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects","date":"2023-05-09","arxiv_id":"2305.05706","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/dexart-benchmarking-generalizable-dexterous#ran","syntology_url":"https://syntology.ai/paper/2305.05706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05706"}},"official":{"repos":["Kami-code/dexart-release"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-quantification-in-machine","slug":"uncertainty-quantification-in-machine","title":"Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial","date":"2023-05-07","arxiv_id":"2305.04933","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/uncertainty-quantification-in-machine#ran","syntology_url":"https://syntology.ai/paper/2305.04933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04933"}},"official":{"repos":["vnemani14/uq_ml_review"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/explaining-rl-decisions-with-trajectories","slug":"explaining-rl-decisions-with-trajectories","title":"Explaining RL Decisions with Trajectories","date":"2023-05-06","arxiv_id":"2305.04073","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 1 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/explaining-rl-decisions-with-trajectories#ran","syntology_url":"https://syntology.ai/paper/2305.04073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04073"}},"official":{"repos":["shripaddeshmukh/xrl_with_trajectories"],"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/faithful-question-answering-with-monte-carlo","slug":"faithful-question-answering-with-monte-carlo","title":"Faithful Question Answering with Monte-Carlo Planning","date":"2023-05-04","arxiv_id":"2305.02556","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":3,"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 3 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; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/faithful-question-answering-with-monte-carlo#ran","syntology_url":"https://syntology.ai/paper/2305.02556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02556"}},"official":{"repos":["Raising-hrx/FAME"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/masked-trajectory-models-for-prediction","slug":"masked-trajectory-models-for-prediction","title":"Masked Trajectory Models for Prediction, Representation, and Control","date":"2023-05-04","arxiv_id":"2305.02968","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/masked-trajectory-models-for-prediction#ran","syntology_url":"https://syntology.ai/paper/2305.02968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02968"}},"official":{"repos":["facebookresearch/mtm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-pareto-efficient-decision-making-via","slug":"scaling-pareto-efficient-decision-making-via","title":"Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL","date":"2023-04-30","arxiv_id":"2305.00567","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-pareto-efficient-decision-making-via#ran","syntology_url":"https://syntology.ai/paper/2305.00567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00567"}},"official":{"repos":["baitingzbt/peda"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/distance-weighted-supervised-learning-for","slug":"distance-weighted-supervised-learning-for","title":"Distance Weighted Supervised Learning for Offline Interaction Data","date":"2023-04-26","arxiv_id":"2304.13774","repositories_listed":1,"syntology":{"n":27,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":13,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/distance-weighted-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2304.13774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13774"}},"official":null}},{"url":"/paper/hierarchical-state-abstraction-based-on","slug":"hierarchical-state-abstraction-based-on","title":"Hierarchical State Abstraction Based on Structural Information Principles","date":"2023-04-24","arxiv_id":"2304.12000","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hierarchical-state-abstraction-based-on#ran","syntology_url":"https://syntology.ai/paper/2304.12000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.12000"}},"official":{"repos":["ringbdstack/sisa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pcpnet-an-efficient-and-semantic-enhanced","slug":"pcpnet-an-efficient-and-semantic-enhanced","title":"PCPNet: An Efficient and Semantic-Enhanced Transformer Network for Point Cloud Prediction","date":"2023-04-16","arxiv_id":"2304.07773","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/pcpnet-an-efficient-and-semantic-enhanced#ran","syntology_url":"https://syntology.ai/paper/2304.07773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.07773"}},"official":{"repos":["blurryface0814/pcpnet"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/agieval-a-human-centric-benchmark-for","slug":"agieval-a-human-centric-benchmark-for","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","date":"2023-04-13","arxiv_id":"2304.06364","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/agieval-a-human-centric-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2304.06364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06364"}},"official":{"repos":["ruixiangcui/agieval"],"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/do-the-rewards-justify-the-means-measuring","slug":"do-the-rewards-justify-the-means-measuring","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","date":"2023-04-06","arxiv_id":"2304.03279","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/do-the-rewards-justify-the-means-measuring#ran","syntology_url":"https://syntology.ai/paper/2304.03279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03279"}},"official":{"repos":["aypan17/machiavelli"],"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/interpretable-statistical-representations-of","slug":"interpretable-statistical-representations-of","title":"Interpretable statistical representations of neural population dynamics and geometry","date":"2023-04-06","arxiv_id":"2304.03376","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/interpretable-statistical-representations-of#ran","syntology_url":"https://syntology.ai/paper/2304.03376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03376"}},"official":{"repos":["Dynamics-of-Neural-Systems-Lab/MARBLE"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mahalo-unifying-offline-reinforcement","slug":"mahalo-unifying-offline-reinforcement","title":"MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations","date":"2023-03-30","arxiv_id":"2303.17156","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/mahalo-unifying-offline-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2303.17156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17156"}},"official":{"repos":["anqili/mahalo"],"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/a-view-from-somewhere-human-centric-face","slug":"a-view-from-somewhere-human-centric-face","title":"A View From Somewhere: Human-Centric Face Representations","date":"2023-03-30","arxiv_id":"2303.17176","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":3,"phrase":"9 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/a-view-from-somewhere-human-centric-face#ran","syntology_url":"https://syntology.ai/paper/2303.17176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17176"}},"official":{"repos":["sonyai/a_view_from_somewhere"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/optimal-transport-for-offline-imitation","slug":"optimal-transport-for-offline-imitation","title":"Optimal Transport for Offline Imitation Learning","date":"2023-03-24","arxiv_id":"2303.13971","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/optimal-transport-for-offline-imitation#ran","syntology_url":"https://syntology.ai/paper/2303.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13971"}},"official":{"repos":["ethanluoyc/optimal_transport_reward"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reflexion-language-agents-with-verbal","slug":"reflexion-language-agents-with-verbal","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","date":"2023-03-20","arxiv_id":"2303.11366","repositories_listed":5,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/reflexion-language-agents-with-verbal#ran","syntology_url":"https://syntology.ai/paper/2303.11366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11366"}},"official":{"repos":["noahshinn024/reflexion"],"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/hospital-length-of-stay-prediction-based-on","slug":"hospital-length-of-stay-prediction-based-on","title":"Interpretable machine learning for time-to-event prediction in medicine and healthcare","date":"2023-03-17","arxiv_id":"2303.09817","repositories_listed":3,"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/hospital-length-of-stay-prediction-based-on#ran","syntology_url":"https://syntology.ai/paper/2303.09817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09817"}},"official":{"repos":["mi2datalab/xlungs-trustworthy-los-prediction","modeloriented/survex","mi2datalab/interpret-time-to-event"],"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/jump-to-conclusions-short-cutting","slug":"jump-to-conclusions-short-cutting","title":"Jump to Conclusions: Short-Cutting Transformers With Linear Transformations","date":"2023-03-16","arxiv_id":"2303.09435","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/jump-to-conclusions-short-cutting#ran","syntology_url":"https://syntology.ai/paper/2303.09435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09435"}},"official":{"repos":["sashayd/mat"],"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"]}}}],"record_sha256":"d97682582e691c645f3aa4609a1ffc1b9904b27cef0b205d28ad6360d4267f47","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}