{"total":29,"rows":[{"id":"2508.16671","title":"Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2608.13331","title":"Training AI Scientists to Replicate Research","created":"2026-08-13","cited_by_count":9,"area":null},{"id":"2508.00033","title":"GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries","created":"2025-07-30","cited_by_count":8,"area":null},{"id":"2512.22991","title":"Fusion or Confusion? Multimodal Complexity Is Not All You Need","created":"2025-12-28","cited_by_count":5,"area":null},{"id":"2506.08274","title":"The Impact of Feature Scaling In Machine Learning: Effects on Regression and Classification Tasks","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2508.09878","title":"A Survey of Cognitive Distortion Detection and Classification in NLP","created":"2025-08-13","cited_by_count":3,"area":null},{"id":"2505.15469","title":"A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2511.00052","title":"Feature-Guided Analysis of Neural Networks: A Replication Study","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2510.01744","title":"Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGD","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2603.06552","title":"KCLarity at SemEval-2026 Task 6: Encoder and Zero-Shot Approaches to Political Evasion Detection","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2608.26236","title":"6.5% of the Neuro-Symbolic Literature Can Be Reproduced from Its Published Artifacts, a Six-Stage Audit Framework and First Instantiation","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2502.10398","title":"Practical Application and Limitations of AI Certification Catalogues in the Light of the AI Act","created":"2025-01-20","cited_by_count":0,"area":null},{"id":"2504.17655","title":"Aerial Image Classification in Scarce and Unconstrained Environments via Conformal Prediction","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2508.00880","title":"Reproducibility of Machine Learning-Based Fault Detection and Diagnosis for HVAC Systems in Buildings: An Empirical Study","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2508.20275","title":"A Systematic Review on the Generative AI Applications in Human Medical Genomics","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2510.25692","title":"A Configuration-First Framework for Reproducible, Low-Code Machine Learning: a Localization Use Case","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2512.16715","title":"Towards Reproducibility in Predictive Process Mining: SPICE -- A Deep Learning Library","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2601.17684","title":"A Model-Driven Lossless Compression Algorithm Resistant to Mismatch","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2603.28040","title":"Bit-Identical Medical Deep Learning via Structured Orthogonal Initialization","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.12772","title":"Just Ask for a Table: A Thirty-Token User Prompt Defeats Sponsored Recommendations in Twelve LLMs","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.13801","title":"Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.14164","title":"Unsteady Metrics and Benchmarking Cultures of AI Model Builders","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.19258","title":"ExECG: An Explainable AI Framework for ECG models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.24213","title":"Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.29786","title":"Croissant Tasks: A Metadata Format for Reproducible Machine Learning Evaluations","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.03019","title":"Reproducibility is the New Copyleft: Defining AGI-oriented Reproducible Builds","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.16113","title":"RecourseBench: A Modular Framework for Reproducible Algorithmic Recourse Evaluation","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.10420","title":"Is Model Instability just Noise to be Tolerated or a Property that can be Managed?","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.29677","title":"MedSegBenchmarker: A Raw-Count-First Framework for Controlled 2D Medical Image Segmentation Benchmarks","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}