{"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/diagnostic/papers/ran/1","list_of":"/task/diagnostic","task":"Diagnostic","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":1,"pages_in_order":2,"rows_per_page":100,"rows":[1,100],"of":157,"counts":{"archive_papers_tagged":4513,"with_a_code_link":1213,"where_syntology_ran_a_sample":157,"not_listed_spam_title":0,"listed":4513,"listed_where_code_ran":157,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":132,"every_run_a_failure_of_syntologys_instrument":25,"listed_with_a_run_with_no_instrument_failure":132,"listed_every_run_a_failure_of_syntologys_instrument":25,"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/diagnostic/papers/ran/1","prev":null,"next":"/task/diagnostic/papers/ran/2","papers":[{"url":"/paper/mam-modular-multi-agent-framework-for-multi","slug":"mam-modular-multi-agent-framework-for-multi","title":"MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration","date":"2025-06-24","arxiv_id":"2506.19835","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mam-modular-multi-agent-framework-for-multi#ran","syntology_url":"https://syntology.ai/paper/2506.19835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.19835"}},"official":{"repos":["yczhou001/mam"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/when-meaning-stays-the-same-but-models-drift","slug":"when-meaning-stays-the-same-but-models-drift","title":"When Meaning Stays the Same, but Models Drift: Evaluating Quality of Service under Token-Level Behavioral Instability in LLMs","date":"2025-06-11","arxiv_id":"2506.10095","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":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/when-meaning-stays-the-same-but-models-drift#ran","syntology_url":"https://syntology.ai/paper/2506.10095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.10095"}},"official":{"repos":["Xiao-Vandy/LLM-Prompt-Variance-Diagnostic-Analysis"],"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/are-vision-language-models-ready-for-clinical","slug":"are-vision-language-models-ready-for-clinical","title":"Are Vision Language Models Ready for Clinical Diagnosis? A 3D Medical Benchmark for Tumor-centric Visual Question Answering","date":"2025-05-25","arxiv_id":"2505.18915","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/are-vision-language-models-ready-for-clinical#ran","syntology_url":"https://syntology.ai/paper/2505.18915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18915"}},"official":{"repos":["schuture/deeptumorvqa"],"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/cxreasonbench-a-benchmark-for-evaluating","slug":"cxreasonbench-a-benchmark-for-evaluating","title":"CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays","date":"2025-05-23","arxiv_id":"2505.18087","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/cxreasonbench-a-benchmark-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2505.18087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18087"}},"official":{"repos":["ttumyche/cxreasonbench"],"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/better-safe-than-sorry-overreaction-problem","slug":"better-safe-than-sorry-overreaction-problem","title":"Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition","date":"2025-05-21","arxiv_id":"2505.15367","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/better-safe-than-sorry-overreaction-problem#ran","syntology_url":"https://syntology.ai/paper/2505.15367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15367"}},"official":null}},{"url":"/paper/fhbench-towards-efficient-and-personalized","slug":"fhbench-towards-efficient-and-personalized","title":"FHBench: Towards Efficient and Personalized Federated Learning for Multimodal Healthcare","date":"2025-04-15","arxiv_id":"2504.10817","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fhbench-towards-efficient-and-personalized#ran","syntology_url":"https://syntology.ai/paper/2504.10817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.10817"}},"official":{"repos":["wph6/fhbench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/3mdbench-medical-multimodal-multi-agent","slug":"3mdbench-medical-multimodal-multi-agent","title":"3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark","date":"2025-03-26","arxiv_id":"2504.13861","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/3mdbench-medical-multimodal-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2504.13861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13861"}},"official":{"repos":["univanxx/3mdbench"],"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/pisa-experiments-exploring-physics-post","slug":"pisa-experiments-exploring-physics-post","title":"PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop","date":"2025-03-12","arxiv_id":"2503.09595","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/pisa-experiments-exploring-physics-post#ran","syntology_url":"https://syntology.ai/paper/2503.09595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09595"}},"official":{"repos":["vision-x-nyu/pisa-experiments"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gem-empowering-mllm-for-grounded-ecg","slug":"gem-empowering-mllm-for-grounded-ecg","title":"GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images","date":"2025-03-08","arxiv_id":"2503.06073","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gem-empowering-mllm-for-grounded-ecg#ran","syntology_url":"https://syntology.ai/paper/2503.06073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06073"}},"official":{"repos":["lanxiang1017/gem"],"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/enhanced-contrastive-learning-with-multi-view","slug":"enhanced-contrastive-learning-with-multi-view","title":"Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation","date":"2025-02-27","arxiv_id":"2502.20056","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":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) · 4 unverified","sample_list":"/paper/enhanced-contrastive-learning-with-multi-view#ran","syntology_url":"https://syntology.ai/paper/2502.20056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20056"}},"official":{"repos":["mk-runner/MLRG"],"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/citrus-leveraging-expert-cognitive-pathways","slug":"citrus-leveraging-expert-cognitive-pathways","title":"Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Support","date":"2025-02-25","arxiv_id":"2502.18274","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":4,"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, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/citrus-leveraging-expert-cognitive-pathways#ran","syntology_url":"https://syntology.ai/paper/2502.18274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18274"}},"official":{"repos":["jdh-algo/Citrus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/medcot-medical-chain-of-thought-via","slug":"medcot-medical-chain-of-thought-via","title":"MedCoT: Medical Chain of Thought via Hierarchical Expert","date":"2024-12-18","arxiv_id":"2412.13736","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/medcot-medical-chain-of-thought-via#ran","syntology_url":"https://syntology.ai/paper/2412.13736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13736"}},"official":{"repos":["jxliu-ai/medcot"],"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/llms-can-simulate-standardized-patients-via","slug":"llms-can-simulate-standardized-patients-via","title":"LLMs Can Simulate Standardized Patients via Agent Coevolution","date":"2024-12-16","arxiv_id":"2412.11716","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llms-can-simulate-standardized-patients-via#ran","syntology_url":"https://syntology.ai/paper/2412.11716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11716"}},"official":{"repos":["zjumai/evopatient"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/explainable-machine-learning-for-neoplasms","slug":"explainable-machine-learning-for-neoplasms","title":"Explainable machine learning for neoplasms diagnosis via electrocardiograms: an externally validated study","date":"2024-12-10","arxiv_id":"2412.07737","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/explainable-machine-learning-for-neoplasms#ran","syntology_url":"https://syntology.ai/paper/2412.07737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07737"}},"official":{"repos":["ai4healthuol/cardiodiag"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/voxel-based-differentiable-x-ray-rendering","slug":"voxel-based-differentiable-x-ray-rendering","title":"Differentiable Voxel-based X-ray Rendering Improves Sparse-View 3D CBCT Reconstruction","date":"2024-11-28","arxiv_id":"2411.19224","repositories_listed":3,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/voxel-based-differentiable-x-ray-rendering#ran","syntology_url":"https://syntology.ai/paper/2411.19224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.19224"}},"official":{"repos":["hossein-momeni/diffvox"],"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":["listed","official"]}}},{"url":"/paper/sbi-reloaded-a-toolkit-for-simulation-based","slug":"sbi-reloaded-a-toolkit-for-simulation-based","title":"sbi reloaded: a toolkit for simulation-based inference workflows","date":"2024-11-26","arxiv_id":"2411.17337","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/sbi-reloaded-a-toolkit-for-simulation-based#ran","syntology_url":"https://syntology.ai/paper/2411.17337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17337"}},"official":{"repos":["sbi-dev/sbi"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-multimodal-approach-combining-structural","slug":"a-multimodal-approach-combining-structural","title":"A Multimodal Approach Combining Structural and Cross-domain Textual Guidance for Weakly Supervised OCT Segmentation","date":"2024-11-19","arxiv_id":"2411.12615","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"7 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-multimodal-approach-combining-structural#ran","syntology_url":"https://syntology.ai/paper/2411.12615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12615"}},"official":{"repos":["yangjiaqidig/WSSS-AGM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/harnessing-machine-learning-for-single-shot","slug":"harnessing-machine-learning-for-single-shot","title":"Harnessing Machine Learning for Single-Shot Measurement of Free Electron Laser Pulse Power","date":"2024-11-14","arxiv_id":"2411.09468","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/harnessing-machine-learning-for-single-shot#ran","syntology_url":"https://syntology.ai/paper/2411.09468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09468"}},"official":{"repos":["thawn/vprd"],"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/disengcd-a-meta-multigraph-assisted","slug":"disengcd-a-meta-multigraph-assisted","title":"DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis","date":"2024-10-23","arxiv_id":"2410.17564","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/disengcd-a-meta-multigraph-assisted#ran","syntology_url":"https://syntology.ai/paper/2410.17564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17564"}},"official":{"repos":["bimk/intelligent-education"],"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/gaze-assisted-medical-image-segmentation","slug":"gaze-assisted-medical-image-segmentation","title":"Gaze-Assisted Medical Image Segmentation","date":"2024-10-23","arxiv_id":"2410.17920","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gaze-assisted-medical-image-segmentation#ran","syntology_url":"https://syntology.ai/paper/2410.17920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17920"}},"official":{"repos":["leiluk1/gaze-based-segmentation"],"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/mmed-rag-versatile-multimodal-rag-system-for","slug":"mmed-rag-versatile-multimodal-rag-system-for","title":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models","date":"2024-10-16","arxiv_id":"2410.13085","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mmed-rag-versatile-multimodal-rag-system-for#ran","syntology_url":"https://syntology.ai/paper/2410.13085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13085"}},"official":{"repos":["richard-peng-xia/mmed-rag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cxpmrg-bench-pre-training-and-benchmarking","slug":"cxpmrg-bench-pre-training-and-benchmarking","title":"CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset","date":"2024-10-01","arxiv_id":"2410.00379","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cxpmrg-bench-pre-training-and-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2410.00379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00379"}},"official":{"repos":["event-ahu/medical_image_analysis"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/do-llms-suffer-from-multi-party-hangover-a","slug":"do-llms-suffer-from-multi-party-hangover-a","title":"Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations","date":"2024-09-27","arxiv_id":"2409.18602","repositories_listed":1,"syntology":{"n":19,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":7,"n_honours":7,"n_violates":1,"n_no_contract":0,"n_pointer_only":19,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 7 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/do-llms-suffer-from-multi-party-hangover-a#ran","syntology_url":"https://syntology.ai/paper/2409.18602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18602"}},"official":{"repos":["dhfbk/MPH"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/evidence-is-all-you-need-ordering-imaging","slug":"evidence-is-all-you-need-ordering-imaging","title":"Evidence Is All You Need: Ordering Imaging Studies via Language Model Alignment with the ACR Appropriateness Criteria","date":"2024-09-27","arxiv_id":"2409.19177","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evidence-is-all-you-need-ordering-imaging#ran","syntology_url":"https://syntology.ai/paper/2409.19177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19177"}},"official":{"repos":["michael-s-yao/radGPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-predicting-temporal-changes-in-a","slug":"towards-predicting-temporal-changes-in-a","title":"Towards Predicting Temporal Changes in a Patient's Chest X-ray Images based on Electronic Health Records","date":"2024-09-11","arxiv_id":"2409.07012","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-predicting-temporal-changes-in-a#ran","syntology_url":"https://syntology.ai/paper/2409.07012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07012"}},"official":{"repos":["dek924/ehrxdiff"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-unreasonable-ineffectiveness-of-nucleus","slug":"the-unreasonable-ineffectiveness-of-nucleus","title":"The Unreasonable Ineffectiveness of Nucleus Sampling on Mitigating Text Memorization","date":"2024-08-29","arxiv_id":"2408.16345","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/the-unreasonable-ineffectiveness-of-nucleus#ran","syntology_url":"https://syntology.ai/paper/2408.16345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16345"}},"official":{"repos":["lukaborec/memorization-nucleus-sampling"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ecg-chat-a-large-ecg-language-model-for","slug":"ecg-chat-a-large-ecg-language-model-for","title":"ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis","date":"2024-08-16","arxiv_id":"2408.08849","repositories_listed":1,"syntology":{"n":14,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":14,"phrase":"6 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; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/ecg-chat-a-large-ecg-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2408.08849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08849"}},"official":{"repos":["YubaoZhao/ECG-Chat"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/ragchecker-a-fine-grained-framework-for","slug":"ragchecker-a-fine-grained-framework-for","title":"RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation","date":"2024-08-15","arxiv_id":"2408.08067","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":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) · 2 unverified","sample_list":"/paper/ragchecker-a-fine-grained-framework-for#ran","syntology_url":"https://syntology.ai/paper/2408.08067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08067"}},"official":{"repos":["amazon-science/ragchecker"],"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/ecg-fm-an-open-electrocardiogram-foundation","slug":"ecg-fm-an-open-electrocardiogram-foundation","title":"ECG-FM: An Open Electrocardiogram Foundation Model","date":"2024-08-09","arxiv_id":"2408.05178","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ecg-fm-an-open-electrocardiogram-foundation#ran","syntology_url":"https://syntology.ai/paper/2408.05178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05178"}},"official":{"repos":["bowang-lab/ecg-fm","jwoo5/fairseq-signals"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-02865","slug":"2408-02865","title":"VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledge","date":"2024-08-05","arxiv_id":"2408.02865","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/2408-02865#ran","syntology_url":"https://syntology.ai/paper/2408.02865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02865"}},"official":{"repos":["HUANGLIZI/VisionUnite"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-01933","slug":"2408-01933","title":"DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models","date":"2024-08-04","arxiv_id":"2408.01933","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-01933#ran","syntology_url":"https://syntology.ai/paper/2408.01933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01933"}},"official":{"repos":["wbw520/direct"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mds-ed-multimodal-decision-support-in-the","slug":"mds-ed-multimodal-decision-support-in-the","title":"Enhancing clinical decision support with physiological waveforms -- a multimodal benchmark in emergency care","date":"2024-07-25","arxiv_id":"2407.17856","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":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) · 0 unverified","sample_list":"/paper/mds-ed-multimodal-decision-support-in-the#ran","syntology_url":"https://syntology.ai/paper/2407.17856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17856"}},"official":{"repos":["ai4healthuol/mds-ed"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-multimodal-knowledge-enhanced-whole-slide","slug":"a-multimodal-knowledge-enhanced-whole-slide","title":"A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model","date":"2024-07-22","arxiv_id":"2407.15362","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"phrase":"9 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-multimodal-knowledge-enhanced-whole-slide#ran","syntology_url":"https://syntology.ai/paper/2407.15362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15362"}},"official":null}},{"url":"/paper/cod-towards-an-interpretable-medical-agent","slug":"cod-towards-an-interpretable-medical-agent","title":"CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis","date":"2024-07-18","arxiv_id":"2407.13301","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":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cod-towards-an-interpretable-medical-agent#ran","syntology_url":"https://syntology.ai/paper/2407.13301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13301"}},"official":{"repos":["freedomintelligence/chain-of-diagnosis"],"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/specialist-vision-language-models-for","slug":"specialist-vision-language-models-for","title":"Specialist vision-language models for clinical ophthalmology","date":"2024-07-11","arxiv_id":"2407.08410","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":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/specialist-vision-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2407.08410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08410"}},"official":{"repos":["robbieholland/specialistvlms"],"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/benchmarking-embedding-aggregation-methods-in","slug":"benchmarking-embedding-aggregation-methods-in","title":"Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data Perspective","date":"2024-07-10","arxiv_id":"2407.07841","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/benchmarking-embedding-aggregation-methods-in#ran","syntology_url":"https://syntology.ai/paper/2407.07841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07841"}},"official":{"repos":["fuchs-lab-public/cpath_sabenchmark"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/wsi-vqa-interpreting-whole-slide-images-by","slug":"wsi-vqa-interpreting-whole-slide-images-by","title":"WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering","date":"2024-07-08","arxiv_id":"2407.05603","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":2,"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/wsi-vqa-interpreting-whole-slide-images-by#ran","syntology_url":"https://syntology.ai/paper/2407.05603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05603"}},"official":{"repos":["cpystan/wsi-vqa"],"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/minigpt-med-large-language-model-as-a-general","slug":"minigpt-med-large-language-model-as-a-general","title":"MiniGPT-Med: Large Language Model as a General Interface for Radiology Diagnosis","date":"2024-07-04","arxiv_id":"2407.04106","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minigpt-med-large-language-model-as-a-general#ran","syntology_url":"https://syntology.ai/paper/2407.04106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04106"}},"official":{"repos":["vision-cair/minigpt-med"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/toolbehonest-a-multi-level-hallucination","slug":"toolbehonest-a-multi-level-hallucination","title":"ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models","date":"2024-06-28","arxiv_id":"2406.20015","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/toolbehonest-a-multi-level-hallucination#ran","syntology_url":"https://syntology.ai/paper/2406.20015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20015"}},"official":{"repos":["toolbehonest/toolbehonest"],"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/from-biased-selective-labels-to-pseudo-labels","slug":"from-biased-selective-labels-to-pseudo-labels","title":"From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions","date":"2024-06-27","arxiv_id":"2406.18865","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/from-biased-selective-labels-to-pseudo-labels#ran","syntology_url":"https://syntology.ai/paper/2406.18865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18865"}},"official":{"repos":["mld3/dcem"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["community","official"]}}},{"url":"/paper/from-majority-to-minority-a-diffusion-based","slug":"from-majority-to-minority-a-diffusion-based","title":"From Majority to Minority: A Diffusion-based Augmentation for Underrepresented Groups in Skin Lesion Analysis","date":"2024-06-26","arxiv_id":"2406.18375","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":2,"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/from-majority-to-minority-a-diffusion-based#ran","syntology_url":"https://syntology.ai/paper/2406.18375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18375"}},"official":{"repos":["janet-sw/skin-diff"],"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/md-tree-a-model-diagnostic-tree-grown-on-loss","slug":"md-tree-a-model-diagnostic-tree-grown-on-loss","title":"MD tree: a model-diagnostic tree grown on loss landscape","date":"2024-06-24","arxiv_id":"2406.16988","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":6,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"15 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; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/md-tree-a-model-diagnostic-tree-grown-on-loss#ran","syntology_url":"https://syntology.ai/paper/2406.16988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16988"}},"official":{"repos":["yefanzhou/modeldiagnosis"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-robustness-of-global-feature-effect","slug":"on-the-robustness-of-global-feature-effect","title":"On the Robustness of Global Feature Effect Explanations","date":"2024-06-13","arxiv_id":"2406.09069","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/on-the-robustness-of-global-feature-effect#ran","syntology_url":"https://syntology.ai/paper/2406.09069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09069"}},"official":{"repos":["hbaniecki/robust-feature-effects"],"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/common-and-rare-fundus-diseases","slug":"common-and-rare-fundus-diseases","title":"Enhancing Diagnostic Accuracy in Rare and Common Fundus Diseases with a Knowledge-Rich Vision-Language Model","date":"2024-06-13","arxiv_id":"2406.09317","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/common-and-rare-fundus-diseases#ran","syntology_url":"https://syntology.ai/paper/2406.09317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09317"}},"official":{"repos":["LooKing9218/RetiZero"],"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/mediq-question-asking-llms-for-adaptive-and","slug":"mediq-question-asking-llms-for-adaptive-and","title":"MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning","date":"2024-06-03","arxiv_id":"2406.00922","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mediq-question-asking-llms-for-adaptive-and#ran","syntology_url":"https://syntology.ai/paper/2406.00922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00922"}},"official":{"repos":["stellali7/mediq","stellalisy/mediq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/websuite-systematically-evaluating-why-web","slug":"websuite-systematically-evaluating-why-web","title":"WebSuite: Systematically Evaluating Why Web Agents Fail","date":"2024-06-01","arxiv_id":"2406.01623","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/websuite-systematically-evaluating-why-web#ran","syntology_url":"https://syntology.ai/paper/2406.01623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01623"}},"official":{"repos":["erichli1/websuite"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/pediatricsgpt-large-language-models-as","slug":"pediatricsgpt-large-language-models-as","title":"PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications","date":"2024-05-29","arxiv_id":"2405.19266","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pediatricsgpt-large-language-models-as#ran","syntology_url":"https://syntology.ai/paper/2405.19266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19266"}},"official":{"repos":["ydk122024/pediatricsgpt"],"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/ret-clip-a-retinal-image-foundation-model-pre","slug":"ret-clip-a-retinal-image-foundation-model-pre","title":"RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports","date":"2024-05-23","arxiv_id":"2405.14137","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ret-clip-a-retinal-image-foundation-model-pre#ran","syntology_url":"https://syntology.ai/paper/2405.14137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14137"}},"official":{"repos":["sstonemason/ret-clip"],"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/unveiling-the-tapestry-of-consistency-in","slug":"unveiling-the-tapestry-of-consistency-in","title":"Unveiling the Tapestry of Consistency in Large Vision-Language Models","date":"2024-05-23","arxiv_id":"2405.14156","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"7 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unveiling-the-tapestry-of-consistency-in#ran","syntology_url":"https://syntology.ai/paper/2405.14156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14156"}},"official":{"repos":["foundation-multimodal-models/conbench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vim4path-self-supervised-vision-mamba-for","slug":"vim4path-self-supervised-vision-mamba-for","title":"Vim4Path: Self-Supervised Vision Mamba for Histopathology Images","date":"2024-04-20","arxiv_id":"2404.13222","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vim4path-self-supervised-vision-mamba-for#ran","syntology_url":"https://syntology.ai/paper/2404.13222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13222"}},"official":{"repos":["atlasanalyticslab/vim4path"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/look-listen-and-answer-overcoming-biases-for","slug":"look-listen-and-answer-overcoming-biases-for","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","date":"2024-04-18","arxiv_id":"2404.12020","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/look-listen-and-answer-overcoming-biases-for#ran","syntology_url":"https://syntology.ai/paper/2404.12020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12020"}},"official":{"repos":["reml-group/music-avqa-r"],"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":["community","official"]}}},{"url":"/paper/mechanisms-of-non-factual-hallucinations-in","slug":"mechanisms-of-non-factual-hallucinations-in","title":"Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations","date":"2024-03-27","arxiv_id":"2403.18167","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mechanisms-of-non-factual-hallucinations-in#ran","syntology_url":"https://syntology.ai/paper/2403.18167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18167"}},"official":{"repos":["jadeleiyu/lm_hallucination_mechanisms"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/eye-gaze-guided-multi-modal-alignment","slug":"eye-gaze-guided-multi-modal-alignment","title":"Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning","date":"2024-03-19","arxiv_id":"2403.12416","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/eye-gaze-guided-multi-modal-alignment#ran","syntology_url":"https://syntology.ai/paper/2403.12416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12416"}},"official":{"repos":["momarky/egma"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/zero-shot-ecg-classification-with-multimodal","slug":"zero-shot-ecg-classification-with-multimodal","title":"Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement","date":"2024-03-11","arxiv_id":"2403.06659","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/zero-shot-ecg-classification-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2403.06659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06659"}},"official":{"repos":["cheliu-computation/merl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/histgen-histopathology-report-generation-via","slug":"histgen-histopathology-report-generation-via","title":"HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interaction","date":"2024-03-08","arxiv_id":"2403.05396","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/histgen-histopathology-report-generation-via#ran","syntology_url":"https://syntology.ai/paper/2403.05396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05396"}},"official":{"repos":["dddavid4real/HistGen"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/electrocardiogram-instruction-tuning-for","slug":"electrocardiogram-instruction-tuning-for","title":"MEIT: Multi-Modal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation","date":"2024-03-07","arxiv_id":"2403.04945","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":17,"phrase":"14 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/electrocardiogram-instruction-tuning-for#ran","syntology_url":"https://syntology.ai/paper/2403.04945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04945"}},"official":{"repos":["aiot-mlsys-lab/meit"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/serval-synergy-learning-between-vertical","slug":"serval-synergy-learning-between-vertical","title":"SERVAL: Synergy Learning between Vertical Models and LLMs towards Oracle-Level Zero-shot Medical Prediction","date":"2024-03-03","arxiv_id":"2403.01570","repositories_listed":0,"syntology":{"n":8,"n_ran":6,"n_constructed":1,"n_ran_checked":1,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 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; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/serval-synergy-learning-between-vertical#ran","syntology_url":"https://syntology.ai/paper/2403.01570","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01570"}},"official":null}},{"url":"/paper/listening-to-the-noise-blind-denoising-with","slug":"listening-to-the-noise-blind-denoising-with","title":"Listening to the Noise: Blind Denoising with Gibbs Diffusion","date":"2024-02-29","arxiv_id":"2402.19455","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/listening-to-the-noise-blind-denoising-with#ran","syntology_url":"https://syntology.ai/paper/2402.19455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19455"}},"official":{"repos":["rubenohana/gibbs-diffusion"],"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/model-x-ray-detect-backdoored-models-via","slug":"model-x-ray-detect-backdoored-models-via","title":"Model X-ray:Detecting Backdoored Models via Decision Boundary","date":"2024-02-27","arxiv_id":"2402.17465","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":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-x-ray-detect-backdoored-models-via#ran","syntology_url":"https://syntology.ai/paper/2402.17465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17465"}},"official":{"repos":["SuYanghao/Model_X-ray"],"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/codes-towards-building-open-source-language","slug":"codes-towards-building-open-source-language","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","date":"2024-02-26","arxiv_id":"2402.16347","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/codes-towards-building-open-source-language#ran","syntology_url":"https://syntology.ai/paper/2402.16347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16347"}},"official":{"repos":["ruckbreasoning/codes"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/measuring-implicit-bias-in-explicitly","slug":"measuring-implicit-bias-in-explicitly","title":"Measuring Implicit Bias in Explicitly Unbiased Large Language Models","date":"2024-02-06","arxiv_id":"2402.04105","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-implicit-bias-in-explicitly#ran","syntology_url":"https://syntology.ai/paper/2402.04105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04105"}},"official":{"repos":["baixuechunzi/llm-implicit-bias"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/guiding-masked-representation-learning-to","slug":"guiding-masked-representation-learning-to","title":"Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram","date":"2024-02-02","arxiv_id":"2402.09450","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":5,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":12,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/guiding-masked-representation-learning-to#ran","syntology_url":"https://syntology.ai/paper/2402.09450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09450"}},"official":{"repos":["bakqui/st-mem"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-practical-probabilistic-benchmark-for-ai","slug":"a-practical-probabilistic-benchmark-for-ai","title":"A Practical Probabilistic Benchmark for AI Weather Models","date":"2024-01-27","arxiv_id":"2401.15305","repositories_listed":1,"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/a-practical-probabilistic-benchmark-for-ai#ran","syntology_url":"https://syntology.ai/paper/2401.15305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15305"}},"official":{"repos":["nvidia/earth2mip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/long-tailed-3d-detection-via-2d-late-fusion","slug":"long-tailed-3d-detection-via-2d-late-fusion","title":"Long-Tailed 3D Detection via Multi-Modal Fusion","date":"2023-12-18","arxiv_id":"2312.10986","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/long-tailed-3d-detection-via-2d-late-fusion#ran","syntology_url":"https://syntology.ai/paper/2312.10986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10986"}},"official":{"repos":["mayechi/lt3d-lf"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/quilt-llava-visual-instruction-tuning-by","slug":"quilt-llava-visual-instruction-tuning-by","title":"Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos","date":"2023-12-07","arxiv_id":"2312.04746","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quilt-llava-visual-instruction-tuning-by#ran","syntology_url":"https://syntology.ai/paper/2312.04746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04746"}},"official":null}},{"url":"/paper/persistent-test-time-adaptation-in-episodic","slug":"persistent-test-time-adaptation-in-episodic","title":"Persistent Test-time Adaptation in Recurring Testing Scenarios","date":"2023-11-30","arxiv_id":"2311.18193","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":6,"n_ran_checked":6,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":17,"phrase":"12 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/persistent-test-time-adaptation-in-episodic#ran","syntology_url":"https://syntology.ai/paper/2311.18193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18193"}},"official":{"repos":["hthieu166/petta"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/radialog-a-large-vision-language-model-for","slug":"radialog-a-large-vision-language-model-for","title":"RaDialog: A Large Vision-Language Model for Radiology Report Generation and Conversational Assistance","date":"2023-11-30","arxiv_id":"2311.18681","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/radialog-a-large-vision-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2311.18681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18681"}},"official":{"repos":["chantalmp/radialog"],"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/mvbench-a-comprehensive-multi-modal-video","slug":"mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","date":"2023-11-28","arxiv_id":"2311.17005","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"7 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mvbench-a-comprehensive-multi-modal-video#ran","syntology_url":"https://syntology.ai/paper/2311.17005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17005"}},"official":{"repos":["opengvlab/ask-anything"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-robustness-of-text-image","slug":"benchmarking-robustness-of-text-image","title":"Benchmarking Robustness of Text-Image Composed Retrieval","date":"2023-11-24","arxiv_id":"2311.14837","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/benchmarking-robustness-of-text-image#ran","syntology_url":"https://syntology.ai/paper/2311.14837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14837"}},"official":{"repos":["suntongtongtong/benchmark-robustness-text-image-compose-retrieval"],"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/attribute-diversity-determines-the","slug":"attribute-diversity-determines-the","title":"Attribute Diversity Determines the Systematicity Gap in VQA","date":"2023-11-15","arxiv_id":"2311.08695","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/attribute-diversity-determines-the#ran","syntology_url":"https://syntology.ai/paper/2311.08695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08695"}},"official":{"repos":["ikb-a/systematicity-gap-in-vqa"],"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/data-factors-for-better-compositional","slug":"data-factors-for-better-compositional","title":"Data Factors for Better Compositional Generalization","date":"2023-11-08","arxiv_id":"2311.04420","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/data-factors-for-better-compositional#ran","syntology_url":"https://syntology.ai/paper/2311.04420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04420"}},"official":{"repos":["owenzx/data4comp"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/recurrent-linear-transformers","slug":"recurrent-linear-transformers","title":"AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning","date":"2023-10-24","arxiv_id":"2310.15719","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/recurrent-linear-transformers#ran","syntology_url":"https://syntology.ai/paper/2310.15719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15719"}},"official":{"repos":["subho406/Recurrent-Linear-Transformers","subho406/agalite"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/hallusionbench-you-see-what-you-think-or-you","slug":"hallusionbench-you-see-what-you-think-or-you","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","date":"2023-10-23","arxiv_id":"2310.14566","repositories_listed":9,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hallusionbench-you-see-what-you-think-or-you#ran","syntology_url":"https://syntology.ai/paper/2310.14566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14566"}},"official":{"repos":["tianyi-lab/hallusionbench"],"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":["listed","official"]}}},{"url":"/paper/cxr-llava-multimodal-large-language-model-for","slug":"cxr-llava-multimodal-large-language-model-for","title":"CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images","date":"2023-10-22","arxiv_id":"2310.18341","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cxr-llava-multimodal-large-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2310.18341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18341"}},"official":{"repos":["ecofri/cxr_llava"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/m3dsynth-a-dataset-of-medical-3d-images-with","slug":"m3dsynth-a-dataset-of-medical-3d-images-with","title":"M3Dsynth: A dataset of medical 3D images with AI-generated local manipulations","date":"2023-09-14","arxiv_id":"2309.07973","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/m3dsynth-a-dataset-of-medical-3d-images-with#ran","syntology_url":"https://syntology.ai/paper/2309.07973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07973"}},"official":null}},{"url":"/paper/a-localization-to-segmentation-framework-for","slug":"a-localization-to-segmentation-framework-for","title":"A Localization-to-Segmentation Framework for Automatic Tumor Segmentation in Whole-Body PET/CT Images","date":"2023-09-11","arxiv_id":"2309.05446","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/a-localization-to-segmentation-framework-for#ran","syntology_url":"https://syntology.ai/paper/2309.05446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05446"}},"official":{"repos":["medcai/l2snet"],"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/learning-diverse-features-in-vision","slug":"learning-diverse-features-in-vision","title":"Learning Diverse Features in Vision Transformers for Improved Generalization","date":"2023-08-30","arxiv_id":"2308.16274","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":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-diverse-features-in-vision#ran","syntology_url":"https://syntology.ai/paper/2308.16274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16274"}},"official":{"repos":["armandnm/diverse-vit"],"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/towards-quantitative-precision-for-ecg","slug":"towards-quantitative-precision-for-ecg","title":"Towards quantitative precision for ECG analysis: Leveraging state space models, self-supervision and patient metadata","date":"2023-08-29","arxiv_id":"2308.15291","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/towards-quantitative-precision-for-ecg#ran","syntology_url":"https://syntology.ai/paper/2308.15291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.15291"}},"official":{"repos":["tmehari/ssm_ecg"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/egoschema-a-diagnostic-benchmark-for-very-1","slug":"egoschema-a-diagnostic-benchmark-for-very-1","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","date":"2023-08-17","arxiv_id":"2308.09126","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/egoschema-a-diagnostic-benchmark-for-very-1#ran","syntology_url":"https://syntology.ai/paper/2308.09126","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09126"}},"official":{"repos":["egoschema/egoschema"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-distill-global-representation-for","slug":"learning-to-distill-global-representation-for","title":"Learning to Distill Global Representation for Sparse-View CT","date":"2023-08-16","arxiv_id":"2308.08463","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"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) · 3 unverified","sample_list":"/paper/learning-to-distill-global-representation-for#ran","syntology_url":"https://syntology.ai/paper/2308.08463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08463"}},"official":{"repos":["longzilicart/gloredi"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/chexfusion-effective-fusion-of-multi-view","slug":"chexfusion-effective-fusion-of-multi-view","title":"CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray Classification","date":"2023-08-08","arxiv_id":"2308.03968","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/chexfusion-effective-fusion-of-multi-view#ran","syntology_url":"https://syntology.ai/paper/2308.03968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03968"}},"official":{"repos":["dongkyuk/CheXFusion"],"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/evaluating-the-ripple-effects-of-knowledge","slug":"evaluating-the-ripple-effects-of-knowledge","title":"Evaluating the Ripple Effects of Knowledge Editing in Language Models","date":"2023-07-24","arxiv_id":"2307.12976","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/evaluating-the-ripple-effects-of-knowledge#ran","syntology_url":"https://syntology.ai/paper/2307.12976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12976"}},"official":{"repos":["edenbiran/rippleedits"],"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/large-language-models-perform-diagnostic","slug":"large-language-models-perform-diagnostic","title":"Large Language Models Perform Diagnostic Reasoning","date":"2023-07-18","arxiv_id":"2307.08922","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-perform-diagnostic#ran","syntology_url":"https://syntology.ai/paper/2307.08922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08922"}},"official":{"repos":["nlplab-best-team/diagnostic-reasoning"],"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/v-lol-a-diagnostic-dataset-for-visual-logical","slug":"v-lol-a-diagnostic-dataset-for-visual-logical","title":"V-LoL: A Diagnostic Dataset for Visual Logical Learning","date":"2023-06-13","arxiv_id":"2306.07743","repositories_listed":1,"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/v-lol-a-diagnostic-dataset-for-visual-logical#ran","syntology_url":"https://syntology.ai/paper/2306.07743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07743"}},"official":{"repos":["ml-research/vlol-dataset-gen"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/monotonic-location-attention-for-length","slug":"monotonic-location-attention-for-length","title":"Monotonic Location Attention for Length Generalization","date":"2023-05-31","arxiv_id":"2305.20019","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/monotonic-location-attention-for-length#ran","syntology_url":"https://syntology.ai/paper/2305.20019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.20019"}},"official":{"repos":["jrc1995/monotoniclocationattention"],"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/echo-event-causality-inference-via-human","slug":"echo-event-causality-inference-via-human","title":"ECHo: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning","date":"2023-05-24","arxiv_id":"2305.14740","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/echo-event-causality-inference-via-human#ran","syntology_url":"https://syntology.ai/paper/2305.14740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14740"}},"official":{"repos":["yuxixie/echo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/paxion-patching-action-knowledge-in-video-1","slug":"paxion-patching-action-knowledge-in-video-1","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","date":"2023-05-18","arxiv_id":"2305.10683","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":2,"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/paxion-patching-action-knowledge-in-video-1#ran","syntology_url":"https://syntology.ai/paper/2305.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10683"}},"official":{"repos":["mikewangwzhl/paxion"],"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/pmc-vqa-visual-instruction-tuning-for-medical","slug":"pmc-vqa-visual-instruction-tuning-for-medical","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","date":"2023-05-17","arxiv_id":"2305.10415","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pmc-vqa-visual-instruction-tuning-for-medical#ran","syntology_url":"https://syntology.ai/paper/2305.10415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10415"}},"official":{"repos":["xiaoman-zhang/PMC-VQA"],"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/text-classification-via-large-language-models","slug":"text-classification-via-large-language-models","title":"Text Classification via Large Language Models","date":"2023-05-15","arxiv_id":"2305.08377","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/text-classification-via-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2305.08377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.08377"}},"official":{"repos":["shannonai/gpt-cls-carp"],"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/segment-anything-in-medical-images","slug":"segment-anything-in-medical-images","title":"Segment Anything in Medical Images","date":"2023-04-24","arxiv_id":"2304.12306","repositories_listed":3,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":7,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/segment-anything-in-medical-images#ran","syntology_url":"https://syntology.ai/paper/2304.12306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.12306"}},"official":{"repos":["bowang-lab/medsam"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/ambiguous-medical-image-segmentation-using","slug":"ambiguous-medical-image-segmentation-using","title":"Ambiguous Medical Image Segmentation using Diffusion Models","date":"2023-04-10","arxiv_id":"2304.04745","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ambiguous-medical-image-segmentation-using#ran","syntology_url":"https://syntology.ai/paper/2304.04745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04745"}},"official":{"repos":["aimansnigdha/ambiguous-medical-image-segmentation-using-diffusion-models"],"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/characterizing-the-optimal-0-1-loss-for-multi","slug":"characterizing-the-optimal-0-1-loss-for-multi","title":"Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker","date":"2023-02-21","arxiv_id":"2302.10722","repositories_listed":0,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/characterizing-the-optimal-0-1-loss-for-multi#ran","syntology_url":"https://syntology.ai/paper/2302.10722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10722"}},"official":null}},{"url":"/paper/jana-jointly-amortized-neural-approximation","slug":"jana-jointly-amortized-neural-approximation","title":"JANA: Jointly Amortized Neural Approximation of Complex Bayesian Models","date":"2023-02-17","arxiv_id":"2302.09125","repositories_listed":4,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/jana-jointly-amortized-neural-approximation#ran","syntology_url":"https://syntology.ai/paper/2302.09125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.09125"}},"official":{"repos":["bayesflow-org/jana-paper","stefanradev93/BayesFlow"],"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":["listed","official"]}}},{"url":"/paper/ctl-evaluating-generalization-on-never-seen","slug":"ctl-evaluating-generalization-on-never-seen","title":"CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations","date":"2022-10-12","arxiv_id":"2210.06350","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/ctl-evaluating-generalization-on-never-seen#ran","syntology_url":"https://syntology.ai/paper/2210.06350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06350"}},"official":{"repos":["robertcsordas/ctlpp"],"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/truncated-proposals-for-scalable-and-hassle","slug":"truncated-proposals-for-scalable-and-hassle","title":"Truncated proposals for scalable and hassle-free simulation-based inference","date":"2022-10-10","arxiv_id":"2210.04815","repositories_listed":1,"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":1,"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/truncated-proposals-for-scalable-and-hassle#ran","syntology_url":"https://syntology.ai/paper/2210.04815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.04815"}},"official":{"repos":["mackelab/tsnpe_neurips"],"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/egotaskqa-understanding-human-tasks-in","slug":"egotaskqa-understanding-human-tasks-in","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","date":"2022-10-08","arxiv_id":"2210.03929","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":2,"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/egotaskqa-understanding-human-tasks-in#ran","syntology_url":"https://syntology.ai/paper/2210.03929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03929"}},"official":{"repos":["Buzz-Beater/EgoTaskQA"],"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/ultra-high-resolution-unpaired-stain","slug":"ultra-high-resolution-unpaired-stain","title":"Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization","date":"2022-08-23","arxiv_id":"2208.10730","repositories_listed":1,"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":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) · 2 unverified","sample_list":"/paper/ultra-high-resolution-unpaired-stain#ran","syntology_url":"https://syntology.ai/paper/2208.10730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.10730"}},"official":{"repos":["kaminyou/urust"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/plm-icd-automatic-icd-coding-with-pretrained-1","slug":"plm-icd-automatic-icd-coding-with-pretrained-1","title":"PLM-ICD: Automatic ICD Coding with Pretrained Language Models","date":"2022-07-12","arxiv_id":"2207.05289","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/plm-icd-automatic-icd-coding-with-pretrained-1#ran","syntology_url":"https://syntology.ai/paper/2207.05289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.05289"}},"official":{"repos":["miulab/plm-icd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/randstainna-learning-stain-agnostic-features","slug":"randstainna-learning-stain-agnostic-features","title":"RandStainNA: Learning Stain-Agnostic Features from Histology Slides by Bridging Stain Augmentation and Normalization","date":"2022-06-25","arxiv_id":"2206.12694","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/randstainna-learning-stain-agnostic-features#ran","syntology_url":"https://syntology.ai/paper/2206.12694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.12694"}},"official":{"repos":["yiqings/randstainna"],"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/classifying-unstructured-clinical-notes-via","slug":"classifying-unstructured-clinical-notes-via","title":"Classifying Unstructured Clinical Notes via Automatic Weak Supervision","date":"2022-06-24","arxiv_id":"2206.12088","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/classifying-unstructured-clinical-notes-via#ran","syntology_url":"https://syntology.ai/paper/2206.12088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.12088"}},"official":{"repos":["autonlab/KeyClass"],"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"]}}}],"record_sha256":"320871694265a7fd1f633d93434b5fb55e5376f43fab78f9aa8e0ccfb0f29d73","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}