{"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/arc","name":"ARC","slug":"arc","description_markdown":null,"categories":[{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":554,"papers_with_code":155,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"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":6,"rows_per_page":100,"shown":100,"of":554,"of_with_code":155,"tagged_in_all":554,"counts":{"archive_papers_tagged":554,"with_a_code_link":155,"where_syntology_ran_a_sample":48,"not_listed_spam_title":0,"listed":554,"listed_where_code_ran":48,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":40,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":40,"listed_every_run_a_failure_of_syntologys_instrument":8,"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/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","repositories_listed":8,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}},"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/the-measure-of-intelligence","slug":"the-measure-of-intelligence","title":"On the Measure of Intelligence","date":"2019-11-05","arxiv_id":"1911.01547","repositories_listed":6,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-measure-of-intelligence#ran","syntology_url":"https://syntology.ai/paper/1911.01547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01547"}},"official":{"repos":["fchollet/ARC"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/factgraph-evaluating-factuality-in","slug":"factgraph-evaluating-factuality-in","title":"FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations","date":"2022-04-13","arxiv_id":"2204.06508","repositories_listed":3,"syntology":null},{"url":"/paper/self-consistency-improves-chain-of-thought","slug":"self-consistency-improves-chain-of-thought","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","date":"2022-03-21","arxiv_id":"2203.11171","repositories_listed":3,"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/self-consistency-improves-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2203.11171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11171"}},"official":null}},{"url":"/paper/designing-effective-sparse-expert-models","slug":"designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/designing-effective-sparse-expert-models#ran","syntology_url":"https://syntology.ai/paper/2202.08906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08906"}},"official":{"repos":["tensorflow/mesh"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/arc-support-line-segments-revisited-an","slug":"arc-support-line-segments-revisited-an","title":"Arc-support Line Segments Revisited: An Efficient and High-quality Ellipse Detection","date":"2018-10-08","arxiv_id":"1810.03243","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-attend-on-essential-terms-an","slug":"learning-to-attend-on-essential-terms-an","title":"Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering","date":"2018-08-28","arxiv_id":"1808.09492","repositories_listed":3,"syntology":null},{"url":"/paper/the-jumping-reasoning-curve-tracking-the","slug":"the-jumping-reasoning-curve-tracking-the","title":"The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles","date":"2025-02-03","arxiv_id":"2502.01081","repositories_listed":2,"syntology":null},{"url":"/paper/capturing-sparks-of-abstraction-for-the-arc","slug":"capturing-sparks-of-abstraction-for-the-arc","title":"Capturing Sparks of Abstraction for the ARC Challenge","date":"2024-11-17","arxiv_id":"2411.11206","repositories_listed":2,"syntology":null},{"url":"/paper/monte-carlo-tree-search-boosts-reasoning-via","slug":"monte-carlo-tree-search-boosts-reasoning-via","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","date":"2024-05-01","arxiv_id":"2405.00451","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/monte-carlo-tree-search-boosts-reasoning-via#ran","syntology_url":"https://syntology.ai/paper/2405.00451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00451"}},"official":{"repos":["YuxiXie/MCTS-DPO"],"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/neural-networks-for-abstraction-and-reasoning","slug":"neural-networks-for-abstraction-and-reasoning","title":"Neural networks for abstraction and reasoning: Towards broad generalization in machines","date":"2024-02-05","arxiv_id":"2402.03507","repositories_listed":2,"syntology":null},{"url":"/paper/communicating-natural-programs-to-humans-and","slug":"communicating-natural-programs-to-humans-and","title":"Communicating Natural Programs to Humans and Machines","date":"2021-06-15","arxiv_id":"2106.07824","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-second-order-treecrf-for-neural","slug":"efficient-second-order-treecrf-for-neural","title":"Efficient Second-Order TreeCRF for Neural Dependency Parsing","date":"2020-05-03","arxiv_id":"2005.00975","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/efficient-second-order-treecrf-for-neural#ran","syntology_url":"https://syntology.ai/paper/2005.00975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00975"}},"official":{"repos":["yzhangcs/crfpar"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/freelb-enhanced-adversarial-training-for","slug":"freelb-enhanced-adversarial-training-for","title":"FreeLB: Enhanced Adversarial Training for Natural Language Understanding","date":"2019-09-25","arxiv_id":"1909.11764","repositories_listed":2,"syntology":null},{"url":"/paper/more-about-covariance-descriptors-for-image","slug":"more-about-covariance-descriptors-for-image","title":"More About Covariance Descriptors for Image Set Coding: Log-Euclidean Framework based Kernel Matrix Representation","date":"2019-09-16","arxiv_id":"1909.07273","repositories_listed":2,"syntology":null},{"url":"/paper/yara-parser-a-fast-and-accurate-dependency","slug":"yara-parser-a-fast-and-accurate-dependency","title":"Yara Parser: A Fast and Accurate Dependency Parser","date":"2015-03-23","arxiv_id":"1503.06733","repositories_listed":2,"syntology":null},{"url":"/paper/ds-gt-at-checkthat-2025-detecting","slug":"ds-gt-at-checkthat-2025-detecting","title":"DS@GT at CheckThat! 2025: Detecting Subjectivity via Transfer-Learning and Corrective Data Augmentation","date":"2025-07-08","arxiv_id":"2507.06189","repositories_listed":1,"syntology":null},{"url":"/paper/ds-gt-at-checkthat-2025-ensemble-methods-for","slug":"ds-gt-at-checkthat-2025-ensemble-methods-for","title":"DS@GT at CheckThat! 2025: Ensemble Methods for Detection of Scientific Discourse on Social Media","date":"2025-07-08","arxiv_id":"2507.06205","repositories_listed":1,"syntology":null},{"url":"/paper/ds-gt-at-checkthat-2025-evaluating-context","slug":"ds-gt-at-checkthat-2025-evaluating-context","title":"DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification","date":"2025-07-08","arxiv_id":"2507.06195","repositories_listed":1,"syntology":null},{"url":"/paper/tile-based-vit-inference-with-visual-cluster","slug":"tile-based-vit-inference-with-visual-cluster","title":"Tile-Based ViT Inference with Visual-Cluster Priors for Zero-Shot Multi-Species Plant Identification","date":"2025-07-08","arxiv_id":"2507.06093","repositories_listed":1,"syntology":null},{"url":"/paper/con-instruction-universal-jailbreaking-of","slug":"con-instruction-universal-jailbreaking-of","title":"Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities","date":"2025-05-31","arxiv_id":"2506.00548","repositories_listed":1,"syntology":null},{"url":"/paper/helm-hyperbolic-large-language-models-via","slug":"helm-hyperbolic-large-language-models-via","title":"HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts","date":"2025-05-30","arxiv_id":"2505.24722","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/helm-hyperbolic-large-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2505.24722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.24722"}},"official":{"repos":["graph-and-geometric-learning/helm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/apr-transformer-initial-pose-estimation-for","slug":"apr-transformer-initial-pose-estimation-for","title":"APR-Transformer: Initial Pose Estimation for Localization in Complex Environments through Absolute Pose Regression","date":"2025-05-14","arxiv_id":"2505.09356","repositories_listed":1,"syntology":null},{"url":"/paper/fast-text-to-audio-generation-with","slug":"fast-text-to-audio-generation-with","title":"Fast Text-to-Audio Generation with Adversarial Post-Training","date":"2025-05-13","arxiv_id":"2505.08175","repositories_listed":1,"syntology":null},{"url":"/paper/optiks-optimized-gradient-properties-through","slug":"optiks-optimized-gradient-properties-through","title":"OPTIKS: Optimized Gradient Properties Through Timing in K-Space","date":"2025-05-11","arxiv_id":"2505.07117","repositories_listed":1,"syntology":null},{"url":"/paper/datadecide-how-to-predict-best-pretraining","slug":"datadecide-how-to-predict-best-pretraining","title":"DataDecide: How to Predict Best Pretraining Data with Small Experiments","date":"2025-04-15","arxiv_id":"2504.11393","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/datadecide-how-to-predict-best-pretraining#ran","syntology_url":"https://syntology.ai/paper/2504.11393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11393"}},"official":null}},{"url":"/paper/improving-in-context-learning-with-reasoning","slug":"improving-in-context-learning-with-reasoning","title":"Improving In-Context Learning with Reasoning Distillation","date":"2025-04-14","arxiv_id":"2504.10647","repositories_listed":1,"syntology":null},{"url":"/paper/when-astronomy-meets-ai-manazel-for-crescent","slug":"when-astronomy-meets-ai-manazel-for-crescent","title":"When Astronomy Meets AI: Manazel For Crescent Visibility Prediction in Morocco","date":"2025-03-27","arxiv_id":"2503.21634","repositories_listed":1,"syntology":null},{"url":"/paper/pht-cad-efficient-cad-parametric-primitive","slug":"pht-cad-efficient-cad-parametric-primitive","title":"PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuning","date":"2025-03-23","arxiv_id":"2503.18147","repositories_listed":1,"syntology":null},{"url":"/paper/arc-anchored-representation-clouds-for-high","slug":"arc-anchored-representation-clouds-for-high","title":"ARC: Anchored Representation Clouds for High-Resolution INR Classification","date":"2025-03-19","arxiv_id":"2503.15156","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/arc-anchored-representation-clouds-for-high#ran","syntology_url":"https://syntology.ai/paper/2503.15156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.15156"}},"official":{"repos":["jluij/anchored_representation_clouds"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/can-llms-predict-citation-intent-an","slug":"can-llms-predict-citation-intent-an","title":"Can LLMs Predict Citation Intent? An Experimental Analysis of In-context Learning and Fine-tuning on Open LLMs","date":"2025-02-20","arxiv_id":"2502.14561","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-llms-fluid-intelligence","slug":"understanding-llms-fluid-intelligence","title":"Understanding LLMs' Fluid Intelligence Deficiency: An Analysis of the ARC Task","date":"2025-02-11","arxiv_id":"2502.07190","repositories_listed":1,"syntology":null},{"url":"/paper/unified-3d-mri-representations-via-sequence","slug":"unified-3d-mri-representations-via-sequence","title":"Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning","date":"2025-01-21","arxiv_id":"2501.12057","repositories_listed":1,"syntology":null},{"url":"/paper/the-utility-of-hyperplane-angle-metric-in","slug":"the-utility-of-hyperplane-angle-metric-in","title":"The Utility of Hyperplane Angle Metric in Detecting Financial Concept Drift","date":"2025-01-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nsa-neuro-symbolic-arc-challenge","slug":"nsa-neuro-symbolic-arc-challenge","title":"NSA: Neuro-symbolic ARC Challenge","date":"2025-01-08","arxiv_id":"2501.04424","repositories_listed":1,"syntology":null},{"url":"/paper/hybridising-reinforcement-learning-and","slug":"hybridising-reinforcement-learning-and","title":"Hybridising Reinforcement Learning and Heuristics for Hierarchical Directed Arc Routing Problems","date":"2025-01-01","arxiv_id":"2501.00852","repositories_listed":1,"syntology":null},{"url":"/paper/conceptsearch-towards-efficient-program","slug":"conceptsearch-towards-efficient-program","title":"ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)","date":"2024-12-10","arxiv_id":"2412.07322","repositories_listed":1,"syntology":null},{"url":"/paper/minimum-weighted-feedback-arc-sets-for","slug":"minimum-weighted-feedback-arc-sets-for","title":"Minimum Weighted Feedback Arc Sets for Ranking from Pairwise Comparisons","date":"2024-12-10","arxiv_id":"2412.16181","repositories_listed":1,"syntology":null},{"url":"/paper/arc-prize-2024-technical-report","slug":"arc-prize-2024-technical-report","title":"ARC Prize 2024: Technical Report","date":"2024-12-05","arxiv_id":"2412.04604","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/arc-prize-2024-technical-report#ran","syntology_url":"https://syntology.ai/paper/2412.04604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04604"}},"official":{"repos":["michaelhodel/re-arc"],"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/searching-latent-program-spaces","slug":"searching-latent-program-spaces","title":"Searching Latent Program Spaces","date":"2024-11-13","arxiv_id":"2411.08706","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":3,"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 3 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/searching-latent-program-spaces#ran","syntology_url":"https://syntology.ai/paper/2411.08706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.08706"}},"official":{"repos":["clement-bonnet/lpn"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/the-surprising-effectiveness-of-test-time","slug":"the-surprising-effectiveness-of-test-time","title":"The Surprising Effectiveness of Test-Time Training for Few-Shot Learning","date":"2024-11-11","arxiv_id":"2411.07279","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/the-surprising-effectiveness-of-test-time#ran","syntology_url":"https://syntology.ai/paper/2411.07279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07279"}},"official":{"repos":["ekinakyurek/marc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/language-models-are-hidden-reasoners","slug":"language-models-are-hidden-reasoners","title":"Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding","date":"2024-11-06","arxiv_id":"2411.04282","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/language-models-are-hidden-reasoners#ran","syntology_url":"https://syntology.ai/paper/2411.04282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04282"}},"official":{"repos":["salesforceairesearch/latro"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/combining-induction-and-transduction-for","slug":"combining-induction-and-transduction-for","title":"Combining Induction and Transduction for Abstract Reasoning","date":"2024-11-04","arxiv_id":"2411.02272","repositories_listed":1,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":12,"n_instrument":5,"n_unverified":2,"n_honours":3,"n_violates":2,"n_no_contract":7,"n_pointer_only":19,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 2 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/combining-induction-and-transduction-for#ran","syntology_url":"https://syntology.ai/paper/2411.02272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02272"}},"official":{"repos":["xu3kev/barc"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/digitizing-touch-with-an-artificial","slug":"digitizing-touch-with-an-artificial","title":"Digitizing Touch with an Artificial Multimodal Fingertip","date":"2024-11-04","arxiv_id":"2411.02479","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/digitizing-touch-with-an-artificial#ran","syntology_url":"https://syntology.ai/paper/2411.02479","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02479"}},"official":{"repos":["facebookresearch/digit360"],"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/todo-enhancing-llm-alignment-with-ternary","slug":"todo-enhancing-llm-alignment-with-ternary","title":"TODO: Enhancing LLM Alignment with Ternary Preferences","date":"2024-11-02","arxiv_id":"2411.02442","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/todo-enhancing-llm-alignment-with-ternary#ran","syntology_url":"https://syntology.ai/paper/2411.02442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02442"}},"official":{"repos":["xxares/todo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/conformal-prediction-of-circular-data","slug":"conformal-prediction-of-circular-data","title":"Projected random forests and conformal prediction of circular data","date":"2024-10-31","arxiv_id":"2410.24145","repositories_listed":1,"syntology":null},{"url":"/paper/draco-differentiable-reconstruction-for","slug":"draco-differentiable-reconstruction-for","title":"DRACO: Differentiable Reconstruction for Arbitrary CBCT Orbits","date":"2024-10-18","arxiv_id":"2410.14900","repositories_listed":1,"syntology":null},{"url":"/paper/image-based-backbone-reconstruction-for-non","slug":"image-based-backbone-reconstruction-for-non","title":"Image-based backbone reconstruction for non-slender soft robots","date":"2024-10-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/itergen-iterative-structured-llm-generation","slug":"itergen-iterative-structured-llm-generation","title":"IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking","date":"2024-10-09","arxiv_id":"2410.07295","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/itergen-iterative-structured-llm-generation#ran","syntology_url":"https://syntology.ai/paper/2410.07295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07295"}},"official":{"repos":["uiuc-arc/itergen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mexa-multilingual-evaluation-of-english","slug":"mexa-multilingual-evaluation-of-english","title":"MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment","date":"2024-10-08","arxiv_id":"2410.05873","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mexa-multilingual-evaluation-of-english#ran","syntology_url":"https://syntology.ai/paper/2410.05873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05873"}},"official":{"repos":["cisnlp/mexa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tackling-the-abstraction-and-reasoning-corpus-1","slug":"tackling-the-abstraction-and-reasoning-corpus-1","title":"Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects","date":"2024-10-08","arxiv_id":"2410.06405","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":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tackling-the-abstraction-and-reasoning-corpus-1#ran","syntology_url":"https://syntology.ai/paper/2410.06405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06405"}},"official":{"repos":["khalil-research/ViTARC"],"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/rationale-aware-answer-verification-by","slug":"rationale-aware-answer-verification-by","title":"Rationale-Aware Answer Verification by Pairwise Self-Evaluation","date":"2024-10-07","arxiv_id":"2410.04838","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rationale-aware-answer-verification-by#ran","syntology_url":"https://syntology.ai/paper/2410.04838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04838"}},"official":{"repos":["akirakawabata/reps"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cax-cellular-automata-accelerated-in-jax","slug":"cax-cellular-automata-accelerated-in-jax","title":"CAX: Cellular Automata Accelerated in JAX","date":"2024-10-03","arxiv_id":"2410.02651","repositories_listed":1,"syntology":null},{"url":"/paper/data-augmentation-for-sparse-multidimensional","slug":"data-augmentation-for-sparse-multidimensional","title":"Data Augmentation for Sparse Multidimensional Learning Performance Data Using Generative AI","date":"2024-09-24","arxiv_id":"2409.15631","repositories_listed":1,"syntology":null},{"url":"/paper/decouplenet-a-lightweight-backbone-network","slug":"decouplenet-a-lightweight-backbone-network","title":"DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks","date":"2024-09-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/matern-kernels-for-tunable-implicit-surface","slug":"matern-kernels-for-tunable-implicit-surface","title":"Matérn Kernels for Tunable Implicit Surface Reconstruction","date":"2024-09-23","arxiv_id":"2409.15466","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/matern-kernels-for-tunable-implicit-surface#ran","syntology_url":"https://syntology.ai/paper/2409.15466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.15466"}},"official":{"repos":["mweiherer/matern-surface-reconstruction"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-symbolic-collaborative-distillation","slug":"neural-symbolic-collaborative-distillation","title":"Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks","date":"2024-09-20","arxiv_id":"2409.13203","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neural-symbolic-collaborative-distillation#ran","syntology_url":"https://syntology.ai/paper/2409.13203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13203"}},"official":{"repos":["xnhyacinth/nesycd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/h-arc-a-robust-estimate-of-human-performance","slug":"h-arc-a-robust-estimate-of-human-performance","title":"H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark","date":"2024-09-02","arxiv_id":"2409.01374","repositories_listed":1,"syntology":null},{"url":"/paper/arcle-the-abstraction-and-reasoning-corpus","slug":"arcle-the-abstraction-and-reasoning-corpus","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","date":"2024-07-30","arxiv_id":"2407.20806","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/arcle-the-abstraction-and-reasoning-corpus#ran","syntology_url":"https://syntology.ai/paper/2407.20806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20806"}},"official":{"repos":["confeitohs/arcle"],"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/dependency-transformer-grammars-integrating","slug":"dependency-transformer-grammars-integrating","title":"Dependency Transformer Grammars: Integrating Dependency Structures into Transformer Language Models","date":"2024-07-24","arxiv_id":"2407.17406","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-laws-with-vocabulary-larger-models","slug":"scaling-laws-with-vocabulary-larger-models","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","date":"2024-07-18","arxiv_id":"2407.13623","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":2,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scaling-laws-with-vocabulary-larger-models#ran","syntology_url":"https://syntology.ai/paper/2407.13623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13623"}},"official":{"repos":["sail-sg/scaling-with-vocab"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/texttt-metabench-a-sparse-benchmark-to","slug":"texttt-metabench-a-sparse-benchmark-to","title":"$\\texttt{metabench}$ -- A Sparse Benchmark to Measure General Ability in Large Language Models","date":"2024-07-04","arxiv_id":"2407.12844","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"8 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/texttt-metabench-a-sparse-benchmark-to#ran","syntology_url":"https://syntology.ai/paper/2407.12844","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12844"}},"official":{"repos":["adkipnis/metabench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-fineweb-datasets-decanting-the-web-for","slug":"the-fineweb-datasets-decanting-the-web-for","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","date":"2024-06-25","arxiv_id":"2406.17557","repositories_listed":1,"syntology":null},{"url":"/paper/varbench-robust-language-model-benchmarking","slug":"varbench-robust-language-model-benchmarking","title":"VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation","date":"2024-06-25","arxiv_id":"2406.17681","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"6 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/varbench-robust-language-model-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2406.17681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17681"}},"official":{"repos":["qbetterk/VarBench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adamoe-token-adaptive-routing-with-null","slug":"adamoe-token-adaptive-routing-with-null","title":"AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models","date":"2024-06-19","arxiv_id":"2406.13233","repositories_listed":1,"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/adamoe-token-adaptive-routing-with-null#ran","syntology_url":"https://syntology.ai/paper/2406.13233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13233"}},"official":{"repos":["cengzihao/adamoe"],"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/cross-modal-learning-for-anomaly-detection-in","slug":"cross-modal-learning-for-anomaly-detection-in","title":"Cross-Modal Learning for Anomaly Detection in Complex Industrial Process: Methodology and Benchmark","date":"2024-06-13","arxiv_id":"2406.09016","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/cross-modal-learning-for-anomaly-detection-in#ran","syntology_url":"https://syntology.ai/paper/2406.09016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09016"}},"official":{"repos":["gaochangwu/fmf-benchmark"],"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/flow-of-reasoning-efficient-training-of-llm","slug":"flow-of-reasoning-efficient-training-of-llm","title":"Flow of Reasoning:Training LLMs for Divergent Problem Solving with Minimal Examples","date":"2024-06-09","arxiv_id":"2406.05673","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/flow-of-reasoning-efficient-training-of-llm#ran","syntology_url":"https://syntology.ai/paper/2406.05673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05673"}},"official":{"repos":["yu-fangxu/for"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/yuan-2-0-m32-mixture-of-experts-with","slug":"yuan-2-0-m32-mixture-of-experts-with","title":"Yuan 2.0-M32: Mixture of Experts with Attention Router","date":"2024-05-28","arxiv_id":"2405.17976","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/yuan-2-0-m32-mixture-of-experts-with#ran","syntology_url":"https://syntology.ai/paper/2405.17976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17976"}},"official":{"repos":["ieit-yuan/yuan2.0-m32"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/arc-a-generalist-graph-anomaly-detector-with","slug":"arc-a-generalist-graph-anomaly-detector-with","title":"ARC: A Generalist Graph Anomaly Detector with In-Context Learning","date":"2024-05-27","arxiv_id":"2405.16771","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/arc-a-generalist-graph-anomaly-detector-with#ran","syntology_url":"https://syntology.ai/paper/2405.16771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16771"}},"official":{"repos":["yixinliu233/arc"],"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/modeling-citation-worthiness-by-using","slug":"modeling-citation-worthiness-by-using","title":"Modeling citation worthiness by using attention-based bidirectional long short-term memory networks and interpretable models","date":"2024-05-20","arxiv_id":"2405.12206","repositories_listed":1,"syntology":null},{"url":"/paper/localized-adaptive-risk-control","slug":"localized-adaptive-risk-control","title":"Localized Adaptive Risk Control","date":"2024-05-13","arxiv_id":"2405.07976","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/localized-adaptive-risk-control#ran","syntology_url":"https://syntology.ai/paper/2405.07976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07976"}},"official":{"repos":["kclip/localized-adaptive-risk-control"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/freseg-frenet-frame-based-part-segmentation","slug":"freseg-frenet-frame-based-part-segmentation","title":"Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear Structures","date":"2024-04-19","arxiv_id":"2404.14435","repositories_listed":1,"syntology":null},{"url":"/paper/addressing-the-abstraction-and-reasoning","slug":"addressing-the-abstraction-and-reasoning","title":"Addressing the Abstraction and Reasoning Corpus via Procedural Example Generation","date":"2024-04-10","arxiv_id":"2404.07353","repositories_listed":1,"syntology":null},{"url":"/paper/is-watermarking-llm-generated-code-robust","slug":"is-watermarking-llm-generated-code-robust","title":"Is The Watermarking Of LLM-Generated Code Robust?","date":"2024-03-24","arxiv_id":"2403.17983","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":7,"n_instrument":7,"n_unverified":2,"n_honours":1,"n_violates":3,"n_no_contract":3,"n_pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 3 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/is-watermarking-llm-generated-code-robust#ran","syntology_url":"https://syntology.ai/paper/2403.17983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17983"}},"official":{"repos":["uiuc-arc/llm-code-watermark"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reasoning-abilities-of-large-language-models","slug":"reasoning-abilities-of-large-language-models","title":"Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus","date":"2024-03-18","arxiv_id":"2403.11793","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/reasoning-abilities-of-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2403.11793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11793"}},"official":{"repos":["GIST-DSLab/ARC_Prompt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/do-large-language-models-solve-arc-visual","slug":"do-large-language-models-solve-arc-visual","title":"Do Large Language Models Solve ARC Visual Analogies Like People Do?","date":"2024-03-13","arxiv_id":"2403.09734","repositories_listed":1,"syntology":null},{"url":"/paper/the-emotion-dynamics-of-literary-novels","slug":"the-emotion-dynamics-of-literary-novels","title":"The Emotion Dynamics of Literary Novels","date":"2024-03-04","arxiv_id":"2403.02474","repositories_listed":1,"syntology":null},{"url":"/paper/codeit-self-improving-language-models-with","slug":"codeit-self-improving-language-models-with","title":"CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay","date":"2024-02-07","arxiv_id":"2402.04858","repositories_listed":1,"syntology":{"n":41,"n_ran":32,"n_constructed":4,"n_ran_checked":10,"n_instrument":22,"n_unverified":9,"n_honours":4,"n_violates":2,"n_no_contract":4,"n_pointer_only":41,"phrase":"32 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 2 violated, 4 with no contract checked; 22 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/codeit-self-improving-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2402.04858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04858"}},"official":{"repos":["Qualcomm-AI-research/codeit"],"state":"official (archive's flag): 32 ran","n_ran":32,"n_constructed":4,"n_ran_no_instrument_failure":10,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/speak-it-out-solving-symbol-related-problems","slug":"speak-it-out-solving-symbol-related-problems","title":"Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models","date":"2024-01-22","arxiv_id":"2401.11725","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-planning-for-the-abstraction-and","slug":"generalized-planning-for-the-abstraction-and","title":"Generalized Planning for the Abstraction and Reasoning Corpus","date":"2024-01-15","arxiv_id":"2401.07426","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/generalized-planning-for-the-abstraction-and#ran","syntology_url":"https://syntology.ai/paper/2401.07426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.07426"}},"official":{"repos":["you68681/gpar"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/robot-assisted-deep-venous-thrombosis","slug":"robot-assisted-deep-venous-thrombosis","title":"Robot-Assisted Deep Venous Thrombosis Ultrasound Examination using Virtual Fixture","date":"2024-01-04","arxiv_id":"2401.02539","repositories_listed":1,"syntology":null},{"url":"/paper/rotated-multi-scale-interaction-network-for","slug":"rotated-multi-scale-interaction-network-for","title":"Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation","date":"2023-12-19","arxiv_id":"2312.12470","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":14,"phrase":"11 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; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rotated-multi-scale-interaction-network-for#ran","syntology_url":"https://syntology.ai/paper/2312.12470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12470"}},"official":{"repos":["lsan2401/rmsin"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/token-level-adaptation-of-lora-adapters-for","slug":"token-level-adaptation-of-lora-adapters-for","title":"Token-Level Adaptation of LoRA Adapters for Downstream Task Generalization","date":"2023-11-17","arxiv_id":"2311.10847","repositories_listed":1,"syntology":null},{"url":"/paper/solving-arc-visual-analogies-with-neural","slug":"solving-arc-visual-analogies-with-neural","title":"Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized method","date":"2023-11-14","arxiv_id":"2311.08083","repositories_listed":1,"syntology":null},{"url":"/paper/tackling-the-abstraction-and-reasoning-corpus","slug":"tackling-the-abstraction-and-reasoning-corpus","title":"Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle","date":"2023-11-01","arxiv_id":"2311.00545","repositories_listed":1,"syntology":null},{"url":"/paper/graph-attention-based-deep-reinforcement","slug":"graph-attention-based-deep-reinforcement","title":"Graph Attention-based Deep Reinforcement Learning for solving the Chinese Postman Problem with Load-dependent costs","date":"2023-10-24","arxiv_id":"2310.15516","repositories_listed":1,"syntology":null},{"url":"/paper/instruction-tuning-with-human-curriculum","slug":"instruction-tuning-with-human-curriculum","title":"Instruction Tuning with Human Curriculum","date":"2023-10-14","arxiv_id":"2310.09518","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-adaptation-of-large-vision-1","slug":"efficient-adaptation-of-large-vision-1","title":"Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing","date":"2023-10-10","arxiv_id":"2310.06234","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"6 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-adaptation-of-large-vision-1#ran","syntology_url":"https://syntology.ai/paper/2310.06234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06234"}},"official":{"repos":["davidyanande/arc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-llm-as-a-system-of","slug":"large-language-model-llm-as-a-system-of","title":"Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) Challenge","date":"2023-10-08","arxiv_id":"2310.05146","repositories_listed":1,"syntology":null},{"url":"/paper/hypothesis-search-inductive-reasoning-with","slug":"hypothesis-search-inductive-reasoning-with","title":"Hypothesis Search: Inductive Reasoning with Language Models","date":"2023-09-11","arxiv_id":"2309.05660","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hypothesis-search-inductive-reasoning-with#ran","syntology_url":"https://syntology.ai/paper/2309.05660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05660"}},"official":{"repos":["relento/hypothesis_search"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/teaching-smaller-language-models-to","slug":"teaching-smaller-language-models-to","title":"Teaching Smaller Language Models To Generalise To Unseen Compositional Questions","date":"2023-08-02","arxiv_id":"2308.00946","repositories_listed":1,"syntology":null},{"url":"/paper/deep-image-prior-inpainting-of-ancient","slug":"deep-image-prior-inpainting-of-ancient","title":"Deep image prior inpainting of ancient frescoes in the Mediterranean Alpine arc","date":"2023-06-25","arxiv_id":"2306.14209","repositories_listed":1,"syntology":null},{"url":"/paper/an-approach-to-solving-the-abstraction-and","slug":"an-approach-to-solving-the-abstraction-and","title":"An Approach to Solving the Abstraction and Reasoning Corpus (ARC) Challenge","date":"2023-06-06","arxiv_id":"2306.03553","repositories_listed":1,"syntology":null},{"url":"/paper/generating-high-quality-emotion-arcs-for-low","slug":"generating-high-quality-emotion-arcs-for-low","title":"Evaluating Emotion Arcs Across Languages: Bridging the Global Divide in Sentiment Analysis","date":"2023-06-03","arxiv_id":"2306.02213","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":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generating-high-quality-emotion-arcs-for-low#ran","syntology_url":"https://syntology.ai/paper/2306.02213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02213"}},"official":{"repos":["dteodore/emotionarcs"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/anpl-compiling-natural-programs-with","slug":"anpl-compiling-natural-programs-with","title":"ANPL: Towards Natural Programming with Interactive Decomposition","date":"2023-05-29","arxiv_id":"2305.18498","repositories_listed":1,"syntology":null},{"url":"/paper/llms-and-the-abstraction-and-reasoning-corpus","slug":"llms-and-the-abstraction-and-reasoning-corpus","title":"LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations","date":"2023-05-26","arxiv_id":"2305.18354","repositories_listed":1,"syntology":null},{"url":"/paper/approximating-a-rum-from-distributions-on-k","slug":"approximating-a-rum-from-distributions-on-k","title":"Approximating a RUM from Distributions on k-Slates","date":"2023-05-22","arxiv_id":"2305.13283","repositories_listed":1,"syntology":null},{"url":"/paper/the-conceptarc-benchmark-evaluating","slug":"the-conceptarc-benchmark-evaluating","title":"The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain","date":"2023-05-11","arxiv_id":"2305.07141","repositories_listed":1,"syntology":null},{"url":"/paper/affective-reasoning-at-utterance-level-in","slug":"affective-reasoning-at-utterance-level-in","title":"How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoning","date":"2023-05-04","arxiv_id":"2305.02615","repositories_listed":1,"syntology":null},{"url":"/paper/citeprompt-using-prompts-to-identify-citation","slug":"citeprompt-using-prompts-to-identify-citation","title":"CitePrompt: Using Prompts to Identify Citation Intent in Scientific Papers","date":"2023-04-25","arxiv_id":"2304.12730","repositories_listed":1,"syntology":null}],"syntology_records":40,"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":48,"papers_where_code_ran_first_page":"/task/arc/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":6,"url":"/task/arc/papers/2","json":"/task/arc/papers/2.json","rows":100},{"order":"archive","page":3,"of":6,"url":"/task/arc/papers/3","json":"/task/arc/papers/3.json","rows":100},{"order":"archive","page":4,"of":6,"url":"/task/arc/papers/4","json":"/task/arc/papers/4.json","rows":100},{"order":"archive","page":5,"of":6,"url":"/task/arc/papers/5","json":"/task/arc/papers/5.json","rows":100},{"order":"archive","page":6,"of":6,"url":"/task/arc/papers/6","json":"/task/arc/papers/6.json","rows":54},{"order":"ran","page":1,"of":1,"url":"/task/arc/papers/ran/1","json":"/task/arc/papers/ran/1.json","rows":48}],"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":"630efb70951ee7a102a3c37afe7de5b8b106e86699194d14ad425e5fb99c3ffe","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}