{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":155,"tagged_in_all":554,"items":[{"url":"/paper/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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":5}},{"url":"/paper/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","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","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","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","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":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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","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","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","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":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/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","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","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","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":3,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/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","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","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","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_unverified":0,"n_pointer_only":2}}],"syntology_records":9,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}