{"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/misconceptions","name":"Misconceptions","slug":"misconceptions","description_markdown":"Measures whether a model can discern popular misconceptions from the truth.\r\n\r\nExample:\r\n\r\n```\r\n        input: The daddy longlegs spider is the most venomous spider in the world.\r\n        choice: T\r\n        choice: F\r\n        answer: F\r\n\r\n        input: Karl Benz is correctly credited with the invention of the first modern automobile.\r\n        choice: T\r\n        choice: F\r\n        answer: T\r\n```\r\n\r\nSource: [BIG-bench](https://github.com/google/BIG-bench/tree/main/bigbench/benchmark_tasks/misconceptions)","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":161,"papers_with_code":54,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/misconceptions-on-big-bench","slug":"misconceptions-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla-70B (few-shot, k=5)","paper_title":"Training Compute-Optimal Large Language Models","paper_url":"/paper/training-compute-optimal-large-language","paper_date":"2022-03-29","arxiv_id":"2203.15556","code_links":[{"title":"karpathy/llama2.c","url":"https://github.com/karpathy/llama2.c"},{"title":"nkluge-correa/teenytinyllama","url":"https://github.com/nkluge-correa/teenytinyllama"}],"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349}],"subtasks":[],"parent_tasks":[{"url":"/task/fact-checking","name":"Fact Checking"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":161,"of_with_code":54,"tagged_in_all":161,"counts":{"archive_papers_tagged":161,"with_a_code_link":54,"where_syntology_ran_a_sample":13,"not_listed_spam_title":0,"listed":161,"listed_where_code_ran":13,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":3,"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"},"items":[{"url":"/paper/community-detection-in-networks-a-user-guide","slug":"community-detection-in-networks-a-user-guide","title":"Community detection in networks: A user guide","date":"2016-07-30","arxiv_id":"1608.00163","repositories_listed":18,"syntology":null},{"url":"/paper/laplace-redux-effortless-bayesian-deep","slug":"laplace-redux-effortless-bayesian-deep","title":"Laplace Redux -- Effortless Bayesian Deep Learning","date":"2021-06-28","arxiv_id":"2106.14806","repositories_listed":6,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/laplace-redux-effortless-bayesian-deep#ran","syntology_url":"https://syntology.ai/paper/2106.14806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14806"}},"official":{"repos":["AlexImmer/Laplace","runame/laplace-redux"],"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/factuality-enhanced-language-models-for-open","slug":"factuality-enhanced-language-models-for-open","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","date":"2022-06-09","arxiv_id":"2206.04624","repositories_listed":5,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"9 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/factuality-enhanced-language-models-for-open#ran","syntology_url":"https://syntology.ai/paper/2206.04624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04624"}},"official":{"repos":["nayeon7lee/factualityprompt"],"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":["listed","official"]}}},{"url":"/paper/parting-with-misconceptions-about-learning","slug":"parting-with-misconceptions-about-learning","title":"Parting with Misconceptions about Learning-based Vehicle Motion Planning","date":"2023-06-13","arxiv_id":"2306.07962","repositories_listed":3,"syntology":null},{"url":"/paper/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/truthfulqa-measuring-how-models-mimic-human","slug":"truthfulqa-measuring-how-models-mimic-human","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","date":"2021-09-08","arxiv_id":"2109.07958","repositories_listed":3,"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":0,"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/truthfulqa-measuring-how-models-mimic-human#ran","syntology_url":"https://syntology.ai/paper/2109.07958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07958"}},"official":{"repos":["sylinrl/truthfulqa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unveiling-contrastive-learning-s-capability","slug":"unveiling-contrastive-learning-s-capability","title":"Unveiling Contrastive Learning's Capability of Neighborhood Aggregation for Collaborative Filtering","date":"2025-04-14","arxiv_id":"2504.10113","repositories_listed":2,"syntology":null},{"url":"/paper/reliability-check-an-analysis-of-gpt-3-s","slug":"reliability-check-an-analysis-of-gpt-3-s","title":"Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording","date":"2023-06-09","arxiv_id":"2306.06199","repositories_listed":2,"syntology":null},{"url":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}},{"url":"/paper/on-the-stability-of-fine-tuning-bert","slug":"on-the-stability-of-fine-tuning-bert","title":"On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines","date":"2020-06-08","arxiv_id":"2006.04884","repositories_listed":2,"syntology":{"n":20,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":7,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/on-the-stability-of-fine-tuning-bert#ran","syntology_url":"https://syntology.ai/paper/2006.04884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04884"}},"official":{"repos":["uds-lsv/bert-stable-fine-tuning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/design-challenges-and-misconceptions-in","slug":"design-challenges-and-misconceptions-in","title":"Design Challenges and Misconceptions in Neural Sequence Labeling","date":"2018-06-12","arxiv_id":"1806.04470","repositories_listed":2,"syntology":null},{"url":"/paper/a-structured-unplugged-approach-for","slug":"a-structured-unplugged-approach-for","title":"A Structured Unplugged Approach for Foundational AI Literacy in Primary Education","date":"2025-05-27","arxiv_id":"2505.21398","repositories_listed":1,"syntology":null},{"url":"/paper/when-ai-co-scientists-fail-spot-a-benchmark","slug":"when-ai-co-scientists-fail-spot-a-benchmark","title":"When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research","date":"2025-05-17","arxiv_id":"2505.11855","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-structured-knowledge-a-concept-map","slug":"harnessing-structured-knowledge-a-concept-map","title":"Harnessing Structured Knowledge: A Concept Map-Based Approach for High-Quality Multiple Choice Question Generation with Effective Distractors","date":"2025-05-02","arxiv_id":"2505.02850","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-protect-yourself-from-5g-radiation","slug":"how-to-protect-yourself-from-5g-radiation","title":"How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation","date":"2025-03-12","arxiv_id":"2503.09598","repositories_listed":1,"syntology":null},{"url":"/paper/paths-and-ambient-spaces-in-neural-loss","slug":"paths-and-ambient-spaces-in-neural-loss","title":"Paths and Ambient Spaces in Neural Loss Landscapes","date":"2025-03-05","arxiv_id":"2503.03382","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-correction-explainable-feedback","slug":"learning-to-correction-explainable-feedback","title":"Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor","date":"2024-12-08","arxiv_id":"2412.07801","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-knowledge-tracing-in-tutor-student","slug":"exploring-knowledge-tracing-in-tutor-student","title":"Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs","date":"2024-09-24","arxiv_id":"2409.16490","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-knowledge-tracing-with-concept-map","slug":"enhancing-knowledge-tracing-with-concept-map","title":"Enhancing Knowledge Tracing with Concept Map and Response Disentanglement","date":"2024-08-23","arxiv_id":"2408.12996","repositories_listed":1,"syntology":null},{"url":"/paper/when-big-data-actually-are-low-rank-or","slug":"when-big-data-actually-are-low-rank-or","title":"When big data actually are low-rank, or entrywise approximation of certain function-generated matrices","date":"2024-07-03","arxiv_id":"2407.03250","repositories_listed":1,"syntology":null},{"url":"/paper/malalgoqa-a-pedagogical-approach-for","slug":"malalgoqa-a-pedagogical-approach-for","title":"MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in Education","date":"2024-07-01","arxiv_id":"2407.00938","repositories_listed":1,"syntology":null},{"url":"/paper/divert-distractor-generation-with-variational","slug":"divert-distractor-generation-with-variational","title":"DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questions","date":"2024-06-27","arxiv_id":"2406.19356","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/divert-distractor-generation-with-variational#ran","syntology_url":"https://syntology.ai/paper/2406.19356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19356"}},"official":{"repos":["umass-ml4ed/divert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/student-answer-forecasting-transformer-driven","slug":"student-answer-forecasting-transformer-driven","title":"Student Answer Forecasting: Transformer-Driven Answer Choice Prediction for Language Learning","date":"2024-05-30","arxiv_id":"2405.20079","repositories_listed":1,"syntology":null},{"url":"/paper/a-closer-look-at-classification-evaluation","slug":"a-closer-look-at-classification-evaluation","title":"A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice","date":"2024-04-25","arxiv_id":"2404.16958","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-automated-distractor-generation-for","slug":"exploring-automated-distractor-generation-for","title":"Exploring Automated Distractor Generation for Math Multiple-choice Questions via Large Language Models","date":"2024-04-02","arxiv_id":"2404.02124","repositories_listed":1,"syntology":null},{"url":"/paper/the-pitfalls-of-next-token-prediction","slug":"the-pitfalls-of-next-token-prediction","title":"The pitfalls of next-token prediction","date":"2024-03-11","arxiv_id":"2403.06963","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-pitfalls-of-next-token-prediction#ran","syntology_url":"https://syntology.ai/paper/2403.06963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06963"}},"official":{"repos":["gregorbachmann/next-token-failures"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-power-of-noise-toward-a-unified-multi","slug":"the-power-of-noise-toward-a-unified-multi","title":"Noise-powered Multi-modal Knowledge Graph Representation Framework","date":"2024-03-11","arxiv_id":"2403.06832","repositories_listed":1,"syntology":null},{"url":"/paper/watchat-explaining-perplexing-programs-by","slug":"watchat-explaining-perplexing-programs-by","title":"WatChat: Explaining perplexing programs by debugging mental models","date":"2024-03-08","arxiv_id":"2403.05334","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-validity-of-automatically","slug":"improving-the-validity-of-automatically","title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01304","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":0,"n_instrument":9,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":13,"phrase":"9 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; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/improving-the-validity-of-automatically#ran","syntology_url":"https://syntology.ai/paper/2403.01304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01304"}},"official":{"repos":["umass-ml4ed/feedback-gen-dpo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/clarify-improving-model-robustness-with","slug":"clarify-improving-model-robustness-with","title":"Clarify: Improving Model Robustness With Natural Language Corrections","date":"2024-02-06","arxiv_id":"2402.03715","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/clarify-improving-model-robustness-with#ran","syntology_url":"https://syntology.ai/paper/2402.03715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03715"}},"official":{"repos":["yoonholee/clarify"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-for-in-context-student","slug":"large-language-models-for-in-context-student","title":"Large Language Models for In-Context Student Modeling: Synthesizing Student's Behavior in Visual Programming","date":"2023-10-15","arxiv_id":"2310.10690","repositories_listed":1,"syntology":null},{"url":"/paper/can-large-language-models-provide-security","slug":"can-large-language-models-provide-security","title":"Can Large Language Models Provide Security & Privacy Advice? Measuring the Ability of LLMs to Refute Misconceptions","date":"2023-10-03","arxiv_id":"2310.02431","repositories_listed":1,"syntology":null},{"url":"/paper/echoprompt-instructing-the-model-to-rephrase","slug":"echoprompt-instructing-the-model-to-rephrase","title":"EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning","date":"2023-09-16","arxiv_id":"2309.10687","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-automated-distractor-and-feedback","slug":"exploring-automated-distractor-and-feedback","title":"Automated Distractor and Feedback Generation for Math Multiple-choice Questions via In-context Learning","date":"2023-08-07","arxiv_id":"2308.03234","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-and-equitable-math-problem-solving","slug":"scalable-and-equitable-math-problem-solving","title":"Scalable and Equitable Math Problem Solving Strategy Prediction in Big Educational Data","date":"2023-08-07","arxiv_id":"2308.03892","repositories_listed":1,"syntology":null},{"url":"/paper/towards-democratizing-joint-embedding-self","slug":"towards-democratizing-joint-embedding-self","title":"Towards Democratizing Joint-Embedding Self-Supervised Learning","date":"2023-03-03","arxiv_id":"2303.01986","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-democratizing-joint-embedding-self#ran","syntology_url":"https://syntology.ai/paper/2303.01986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01986"}},"official":{"repos":["facebookresearch/ffcv-ssl"],"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/inability-of-a-graph-neural-network-heuristic","slug":"inability-of-a-graph-neural-network-heuristic","title":"Inability of a graph neural network heuristic to outperform greedy algorithms in solving combinatorial optimization problems like Max-Cut","date":"2022-10-02","arxiv_id":"2210.00623","repositories_listed":1,"syntology":null},{"url":"/paper/a-weakly-supervised-iterative-graph-based","slug":"a-weakly-supervised-iterative-graph-based","title":"A Weakly-Supervised Iterative Graph-Based Approach to Retrieve COVID-19 Misinformation Topics","date":"2022-05-19","arxiv_id":"2205.09416","repositories_listed":1,"syntology":null},{"url":"/paper/from-solution-synthesis-to-student-attempt","slug":"from-solution-synthesis-to-student-attempt","title":"From {Solution Synthesis} to {Student Attempt Synthesis} for Block-Based Visual Programming Tasks","date":"2022-05-03","arxiv_id":"2205.01265","repositories_listed":1,"syntology":null},{"url":"/paper/towards-process-oriented-modular-and","slug":"towards-process-oriented-modular-and","title":"Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needs","date":"2022-04-30","arxiv_id":"2205.00355","repositories_listed":1,"syntology":null},{"url":"/paper/resolving-conceptual-issues-in-modern","slug":"resolving-conceptual-issues-in-modern","title":"Resolving conceptual issues in Modern Coexistence Theory","date":"2022-01-20","arxiv_id":"2201.07926","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-annotator-bias-approximation-on","slug":"end-to-end-annotator-bias-approximation-on","title":"End-to-End Annotator Bias Approximation on Crowdsourced Single-Label Sentiment Analysis","date":"2021-11-03","arxiv_id":"2111.02326","repositories_listed":1,"syntology":null},{"url":"/paper/back-to-the-drawing-board-a-critical","slug":"back-to-the-drawing-board-a-critical","title":"Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning","date":"2021-08-23","arxiv_id":"2108.10241","repositories_listed":1,"syntology":null},{"url":"/paper/the-many-faces-of-1-lipschitz-neural-networks","slug":"the-many-faces-of-1-lipschitz-neural-networks","title":"Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks","date":"2021-04-11","arxiv_id":"2104.05097","repositories_listed":1,"syntology":null},{"url":"/paper/emergent-communication-under-competition","slug":"emergent-communication-under-competition","title":"Emergent Communication under Competition","date":"2021-01-25","arxiv_id":"2101.10276","repositories_listed":1,"syntology":null},{"url":"/paper/hindsight-and-sequential-rationality-of","slug":"hindsight-and-sequential-rationality-of","title":"Hindsight and Sequential Rationality of Correlated Play","date":"2020-12-10","arxiv_id":"2012.05874","repositories_listed":1,"syntology":null},{"url":"/paper/collecting-the-public-perception-of-ai-and","slug":"collecting-the-public-perception-of-ai-and","title":"Collecting the Public Perception of AI and Robot Rights","date":"2020-08-04","arxiv_id":"2008.01339","repositories_listed":1,"syntology":null},{"url":"/paper/a-tutorial-on-vaes-from-bayes-rule-to","slug":"a-tutorial-on-vaes-from-bayes-rule-to","title":"A Tutorial on VAEs: From Bayes' Rule to Lossless Compression","date":"2020-06-18","arxiv_id":"2006.10273","repositories_listed":1,"syntology":null},{"url":"/paper/re-examining-linear-embeddings-for-high-1","slug":"re-examining-linear-embeddings-for-high-1","title":"Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization","date":"2020-01-31","arxiv_id":"2001.11659","repositories_listed":1,"syntology":null},{"url":"/paper/mlrg-deep-curvature","slug":"mlrg-deep-curvature","title":"Deep Curvature Suite","date":"2019-12-20","arxiv_id":"1912.09656","repositories_listed":1,"syntology":null},{"url":"/paper/not-all-claims-are-created-equal-choosing-the","slug":"not-all-claims-are-created-equal-choosing-the","title":"Not All Claims are Created Equal: Choosing the Right Statistical Approach to Assess Hypotheses","date":"2019-11-10","arxiv_id":"1911.03850","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-properly-evaluate-cross-lingual-word","slug":"how-to-properly-evaluate-cross-lingual-word","title":"How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions","date":"2019-02-01","arxiv_id":"1902.00508","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-learning-for-code-education-rubric","slug":"zero-shot-learning-for-code-education-rubric","title":"Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference","date":"2018-09-05","arxiv_id":"1809.01357","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/zero-shot-learning-for-code-education-rubric#ran","syntology_url":"https://syntology.ai/paper/1809.01357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.01357"}},"official":{"repos":["mhw32/rubric-sampling-public"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-variational-inequality-perspective-on","slug":"a-variational-inequality-perspective-on","title":"A Variational Inequality Perspective on Generative Adversarial Networks","date":"2018-02-28","arxiv_id":"1802.10551","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":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-variational-inequality-perspective-on#ran","syntology_url":"https://syntology.ai/paper/1802.10551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.10551"}},"official":{"repos":["GauthierGidel/Variational-Inequality-GAN"],"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":null,"slug":"the-oversmoothing-fallacy-a-misguided","title":"The Oversmoothing Fallacy: A Misguided Narrative in GNN Research","date":"2025-06-05","arxiv_id":"2506.04653","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-10913","title":"Automated Identification of Logical Errors in Programs: Advancing Scalable Analysis of Student Misconceptions","date":"2025-05-16","arxiv_id":"2505.10913","repositories_listed":0,"syntology":null},{"url":null,"slug":"humans-can-learn-to-detect-ai-generated-texts","title":"Humans can learn to detect AI-generated texts, or at least learn when they can't","date":"2025-05-03","arxiv_id":"2505.01877","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-library-learning-fails-a-lego-prover-case","title":"LLM Library Learning Fails: A LEGO-Prover Case Study","date":"2025-04-03","arxiv_id":"2504.03048","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-ai-what-is-it-not-how-we-use-it-in","title":"What is AI, what is it not, how we use it in physics and how it impacts... you","date":"2025-04-02","arxiv_id":"2504.01827","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-intuition-to-understanding-using-ai","title":"From Intuition to Understanding: Using AI Peers to Overcome Physics Misconceptions","date":"2025-04-01","arxiv_id":"2504.00408","repositories_listed":0,"syntology":null},{"url":null,"slug":"clarifying-misconceptions-in-covid-19-vaccine","title":"Clarifying Misconceptions in COVID-19 Vaccine Sentiment and Stance Analysis and Their Implications for Vaccine Hesitancy Mitigation: A Systematic Review","date":"2025-03-23","arxiv_id":"2503.18095","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergent-abilities-in-large-language-models-a","title":"Emergent Abilities in Large Language Models: A Survey","date":"2025-02-28","arxiv_id":"2503.05788","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-factors-influencing-driver","title":"Analyzing Factors Influencing Driver Willingness to Accept Advanced Driver Assistance Systems","date":"2025-02-23","arxiv_id":"2502.16688","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-imitation-game-for-educational-ai","title":"The Imitation Game for Educational AI","date":"2025-02-21","arxiv_id":"2502.15127","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-systems-can-be-dangerous","title":"Retrieval-augmented systems can be dangerous medical communicators","date":"2025-02-18","arxiv_id":"2502.14898","repositories_listed":0,"syntology":null},{"url":null,"slug":"foundation-models-in-computational-pathology","title":"Foundation Models in Computational Pathology: A Review of Challenges, Opportunities, and Impact","date":"2025-02-12","arxiv_id":"2502.08333","repositories_listed":0,"syntology":null},{"url":"/paper/knowledge-tracing-in-programming-education","slug":"knowledge-tracing-in-programming-education","title":"Knowledge Tracing in Programming Education Integrating Students' Questions","date":"2025-01-22","arxiv_id":"2502.10408","repositories_listed":0,"syntology":{"n":5,"n_ran":5,"n_constructed":2,"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 2 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/knowledge-tracing-in-programming-education#ran","syntology_url":"https://syntology.ai/paper/2502.10408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.10408"}},"official":null}},{"url":null,"slug":"generating-plausible-distractors-for-multiple","title":"Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction","date":"2025-01-21","arxiv_id":"2501.13125","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-ai-in-education-from-foundational","title":"Generative AI in Education: From Foundational Insights to the Socratic Playground for Learning","date":"2025-01-12","arxiv_id":"2501.06682","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoding-knowledge-in-large-language-models-a","title":"Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension","date":"2025-01-02","arxiv_id":"2501.01332","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graphical-approach-to-state-variable","title":"A Graphical Approach to State Variable Selection in Off-policy Learning","date":"2025-01-01","arxiv_id":"2501.00854","repositories_listed":0,"syntology":null},{"url":null,"slug":"chasing-progress-not-perfection-revisiting","title":"Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation","date":"2024-12-14","arxiv_id":"2412.10675","repositories_listed":0,"syntology":null},{"url":null,"slug":"developer-perspectives-on-licensing-and","title":"Developer Perspectives on Licensing and Copyright Issues Arising from Generative AI for Software Development","date":"2024-11-16","arxiv_id":"2411.10877","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-generation-of-question-hints-for","title":"Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology","date":"2024-11-05","arxiv_id":"2411.03495","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-on-characterization-of-near-field-sub","title":"A Study on Characterization of Near-Field Sub-Regions For Phased-Array Antennas","date":"2024-10-23","arxiv_id":"2411.02425","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-llm-based-cognitive-models-of","title":"LLM-based Cognitive Models of Students with Misconceptions","date":"2024-10-16","arxiv_id":"2410.12294","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-future-of-learning-in-the-age-of","title":"The Future of Learning in the Age of Generative AI: Automated Question Generation and Assessment with Large Language Models","date":"2024-10-12","arxiv_id":"2410.09576","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmark-inflation-revealing-llm-performance","title":"Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts","date":"2024-10-11","arxiv_id":"2410.09247","repositories_listed":0,"syntology":null},{"url":null,"slug":"listen-to-the-patient-enhancing-medical","title":"Listening to Patients: A Framework of Detecting and Mitigating Patient Misreport for Medical Dialogue Generation","date":"2024-10-08","arxiv_id":"2410.06094","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-explanations-that-anticipate","title":"Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills","date":"2024-10-05","arxiv_id":"2410.04253","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-thematic-framework-for-analyzing-large","title":"A Thematic Framework for Analyzing Large-scale Self-reported Social Media Data on Opioid Use Disorder Treatment Using Buprenorphine Product","date":"2024-10-02","arxiv_id":"2410.01633","repositories_listed":0,"syntology":null},{"url":null,"slug":"classifier-free-guidance-is-a-predictor","title":"Classifier-Free Guidance is a Predictor-Corrector","date":"2024-08-16","arxiv_id":"2408.09000","repositories_listed":0,"syntology":null},{"url":null,"slug":"problems-in-ai-their-roots-in-philosophy-and","title":"Problems in AI, their roots in philosophy, and implications for science and society","date":"2024-07-22","arxiv_id":"2407.15671","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-topology-optimization-the-good-the-bad","title":"Neural topology optimization: the good, the bad, and the ugly","date":"2024-07-19","arxiv_id":"2407.13954","repositories_listed":0,"syntology":null},{"url":null,"slug":"formalising-anti-discrimination-law-in","title":"Formalising Anti-Discrimination Law in Automated Decision Systems","date":"2024-06-29","arxiv_id":"2407.00400","repositories_listed":0,"syntology":null},{"url":null,"slug":"refining-skewed-perceptions-in-vision","title":"Refining Skewed Perceptions in Vision-Language Models through Visual Representations","date":"2024-05-22","arxiv_id":"2405.14030","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-partial-survey-of-decentralized-cooperative","title":"An Initial Introduction to Cooperative Multi-Agent Reinforcement Learning","date":"2024-05-10","arxiv_id":"2405.06161","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-in-context-teaching-adapting-examples","title":"Toward In-Context Teaching: Adapting Examples to Students' Misconceptions","date":"2024-05-07","arxiv_id":"2405.04495","repositories_listed":0,"syntology":null},{"url":null,"slug":"common-pitfalls-to-avoid-while-using","title":"Common pitfalls to avoid while using multiobjective optimization in machine learning","date":"2024-05-02","arxiv_id":"2405.01480","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-a-hallucinating-model-help-in-reducing","title":"Can a Hallucinating Model help in Reducing Human \"Hallucination\"?","date":"2024-05-01","arxiv_id":"2405.00843","repositories_listed":0,"syntology":null},{"url":null,"slug":"math-multiple-choice-question-generation-via","title":"Math Multiple Choice Question Generation via Human-Large Language Model Collaboration","date":"2024-05-01","arxiv_id":"2405.00864","repositories_listed":0,"syntology":null},{"url":null,"slug":"regressive-side-effects-of-training-language","title":"Student Data Paradox and Curious Case of Single Student-Tutor Model: Regressive Side Effects of Training LLMs for Personalized Learning","date":"2024-04-23","arxiv_id":"2404.15156","repositories_listed":0,"syntology":null},{"url":null,"slug":"differential-contributions-of-machine","title":"Differential contributions of machine learning and statistical analysis to language and cognitive sciences","date":"2024-04-22","arxiv_id":"2404.14052","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-automated-distractor-generation-for","title":"Improving Automated Distractor Generation for Math Multiple-choice Questions with Overgenerate-and-rank","date":"2024-04-19","arxiv_id":"2405.05144","repositories_listed":0,"syntology":null},{"url":null,"slug":"axiomatic-modeling-of-fixed-proportion","title":"Axiomatic modeling of fixed proportion technologies","date":"2024-04-18","arxiv_id":"2404.12462","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-boundaries-a-chronology-with-future","title":"Breaking Boundaries: A Chronology with Future Directions of Women in Exercise Physiology Research, Centred on Pregnancy","date":"2024-04-12","arxiv_id":"2404.08833","repositories_listed":0,"syntology":null},{"url":null,"slug":"sok-gradient-leakage-in-federated-learning","title":"SoK: On Gradient Leakage in Federated Learning","date":"2024-04-08","arxiv_id":"2404.05403","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-the-e-brushes-users-as-authors-in","title":"Prompting the E-Brushes: Users as Authors in Generative AI","date":"2024-03-25","arxiv_id":"2406.11844","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-essential-role-of-causality-in-foundation","title":"The Essential Role of Causality in Foundation World Models for Embodied AI","date":"2024-02-06","arxiv_id":"2402.06665","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-diagnostic-accuracy-through-multi","title":"Enhancing Diagnostic Accuracy through Multi-Agent Conversations: Using Large Language Models to Mitigate Cognitive Bias","date":"2024-01-26","arxiv_id":"2401.14589","repositories_listed":0,"syntology":null}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":13,"papers_where_code_ran_first_page":"/task/misconceptions/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/misconceptions/papers/2","json":"/task/misconceptions/papers/2.json","rows":61},{"order":"ran","page":1,"of":1,"url":"/task/misconceptions/papers/ran/1","json":"/task/misconceptions/papers/ran/1.json","rows":13}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"9a491bea219364b4216676569a3f54d03ee59ebd63579f28f0fde6dabc38f104","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}