{"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/synthetic-data-generation/papers/2","list_of":"/task/synthetic-data-generation","task":"Synthetic Data Generation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":9,"rows_per_page":100,"rows":[101,200],"of":822,"counts":{"archive_papers_tagged":822,"with_a_code_link":325,"where_syntology_ran_a_sample":52,"not_listed_spam_title":0,"listed":822,"listed_where_code_ran":52,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":46,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":46,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/synthetic-data-generation","prev":"/task/synthetic-data-generation","next":"/task/synthetic-data-generation/papers/3","papers":[{"url":"/paper/give-me-some-hard-questions-synthetic-data","slug":"give-me-some-hard-questions-synthetic-data","title":"Give me Some Hard Questions: Synthetic Data Generation for Clinical QA","date":"2024-12-05","arxiv_id":"2412.04573","repositories_listed":1,"syntology":null},{"url":"/paper/domain-agnostic-stroke-lesion-segmentation","slug":"domain-agnostic-stroke-lesion-segmentation","title":"Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Data","date":"2024-12-04","arxiv_id":"2412.03318","repositories_listed":1,"syntology":null},{"url":"/paper/simuscope-realistic-endoscopic-synthetic","slug":"simuscope-realistic-endoscopic-synthetic","title":"SimuScope: Realistic Endoscopic Synthetic Dataset Generation through Surgical Simulation and Diffusion Models","date":"2024-12-03","arxiv_id":"2412.02332","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-amyloid-pet-quantification-mri","slug":"enhancing-amyloid-pet-quantification-mri","title":"Enhancing Amyloid PET Quantification: MRI-Guided Super-Resolution Using Latent Diffusion Models","date":"2024-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/seed-free-synthetic-data-generation-framework","slug":"seed-free-synthetic-data-generation-framework","title":"Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai","date":"2024-11-23","arxiv_id":"2411.15484","repositories_listed":1,"syntology":null},{"url":"/paper/bhasaanuvaad-a-speech-translation-dataset-for","slug":"bhasaanuvaad-a-speech-translation-dataset-for","title":"BhasaAnuvaad: A Speech Translation Dataset for 13 Indian Languages","date":"2024-11-07","arxiv_id":"2411.04699","repositories_listed":1,"syntology":null},{"url":"/paper/improved-multi-task-brain-tumour-segmentation","slug":"improved-multi-task-brain-tumour-segmentation","title":"Improved Multi-Task Brain Tumour Segmentation with Synthetic Data Augmentation","date":"2024-11-07","arxiv_id":"2411.04632","repositories_listed":1,"syntology":null},{"url":"/paper/debiasing-synthetic-data-generated-by-deep","slug":"debiasing-synthetic-data-generated-by-deep","title":"Debiasing Synthetic Data Generated by Deep Generative Models","date":"2024-11-06","arxiv_id":"2411.04216","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"8 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; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/debiasing-synthetic-data-generated-by-deep#ran","syntology_url":"https://syntology.ai/paper/2411.04216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04216"}},"official":{"repos":["syndara-lab/debiased-generation"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/guide-vae-advancing-data-generation-with-user","slug":"guide-vae-advancing-data-generation-with-user","title":"GUIDE-VAE: Advancing Data Generation with User Information and Pattern Dictionaries","date":"2024-11-06","arxiv_id":"2411.03936","repositories_listed":1,"syntology":null},{"url":"/paper/neural-spell-checker-beyond-words-with","slug":"neural-spell-checker-beyond-words-with","title":"Neural spell-checker: Beyond words with synthetic data generation","date":"2024-10-30","arxiv_id":"2410.23514","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-data-generation-with-large-language-1","slug":"synthetic-data-generation-with-large-language-1","title":"Synthetic Data Generation with Large Language Models for Personalized Community Question Answering","date":"2024-10-29","arxiv_id":"2410.22182","repositories_listed":1,"syntology":null},{"url":"/paper/little-giants-synthesizing-high-quality","slug":"little-giants-synthesizing-high-quality","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","date":"2024-10-24","arxiv_id":"2410.18634","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/little-giants-synthesizing-high-quality#ran","syntology_url":"https://syntology.ai/paper/2410.18634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18634"}},"official":{"repos":["haon-chen/SPEED"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rag-confusionqa-a-benchmark-for-evaluating","slug":"rag-confusionqa-a-benchmark-for-evaluating","title":"ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions","date":"2024-10-18","arxiv_id":"2410.14567","repositories_listed":1,"syntology":null},{"url":"/paper/a-little-human-data-goes-a-long-way","slug":"a-little-human-data-goes-a-long-way","title":"A Little Human Data Goes A Long Way","date":"2024-10-17","arxiv_id":"2410.13098","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-little-human-data-goes-a-long-way#ran","syntology_url":"https://syntology.ai/paper/2410.13098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13098"}},"official":{"repos":["dhananjayashok/littlehumandata"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ccup-a-controllable-synthetic-data-generation","slug":"ccup-a-controllable-synthetic-data-generation","title":"CCUP: A Controllable Synthetic Data Generation Pipeline for Pretraining Cloth-Changing Person Re-Identification Models","date":"2024-10-17","arxiv_id":"2410.13567","repositories_listed":1,"syntology":null},{"url":"/paper/tmgbench-a-systematic-game-benchmark-for","slug":"tmgbench-a-systematic-game-benchmark-for","title":"TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs","date":"2024-10-14","arxiv_id":"2410.10479","repositories_listed":1,"syntology":null},{"url":"/paper/dfimat-decoupled-flexible-interactive-matting","slug":"dfimat-decoupled-flexible-interactive-matting","title":"DFIMat: Decoupled Flexible Interactive Matting in Multi-Person Scenarios","date":"2024-10-13","arxiv_id":"2410.09788","repositories_listed":1,"syntology":null},{"url":"/paper/driving-privacy-forward-mitigating","slug":"driving-privacy-forward-mitigating","title":"Driving Privacy Forward: Mitigating Information Leakage within Smart Vehicles through Synthetic Data Generation","date":"2024-10-11","arxiv_id":"2410.08462","repositories_listed":1,"syntology":null},{"url":"/paper/select-a-large-scale-benchmark-of-data","slug":"select-a-large-scale-benchmark-of-data","title":"SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification","date":"2024-10-07","arxiv_id":"2410.05057","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/select-a-large-scale-benchmark-of-data#ran","syntology_url":"https://syntology.ai/paper/2410.05057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05057"}},"official":{"repos":["jimmyxu123/select"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/training-language-models-on-synthetic-edit","slug":"training-language-models-on-synthetic-edit","title":"Training Language Models on Synthetic Edit Sequences Improves Code Synthesis","date":"2024-10-03","arxiv_id":"2410.02749","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/training-language-models-on-synthetic-edit#ran","syntology_url":"https://syntology.ai/paper/2410.02749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02749"}},"official":{"repos":["upiterbarg/lintseq"],"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/towards-a-theoretical-understanding-of-1","slug":"towards-a-theoretical-understanding-of-1","title":"Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective","date":"2024-10-02","arxiv_id":"2410.01720","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-a-theoretical-understanding-of-1#ran","syntology_url":"https://syntology.ai/paper/2410.01720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01720"}},"official":{"repos":["zygan1999/towards-a-theoretical-understanding-of-synthetic-data-in-llm-post-training"],"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/improved-generation-of-synthetic-imaging-data","slug":"improved-generation-of-synthetic-imaging-data","title":"Improved Generation of Synthetic Imaging Data Using Feature-Aligned Diffusion","date":"2024-10-01","arxiv_id":"2410.00731","repositories_listed":1,"syntology":null},{"url":"/paper/targeted-synthetic-data-generation-for","slug":"targeted-synthetic-data-generation-for","title":"Targeted synthetic data generation for tabular data via hardness characterization","date":"2024-10-01","arxiv_id":"2410.00759","repositories_listed":1,"syntology":null},{"url":"/paper/dreamstruct-understanding-slides-and-user","slug":"dreamstruct-understanding-slides-and-user","title":"DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation","date":"2024-09-30","arxiv_id":"2410.00201","repositories_listed":1,"syntology":null},{"url":"/paper/preserving-logical-and-functional","slug":"preserving-logical-and-functional","title":"Preserving logical and functional dependencies in synthetic tabular data","date":"2024-09-26","arxiv_id":"2409.17684","repositories_listed":1,"syntology":null},{"url":"/paper/towards-synthetic-data-generation-for","slug":"towards-synthetic-data-generation-for","title":"Towards Synthetic Data Generation for Improved Pain Recognition in Videos under Patient Constraints","date":"2024-09-24","arxiv_id":"2409.16382","repositories_listed":1,"syntology":null},{"url":"/paper/2409-12993","slug":"2409-12993","title":"CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair","date":"2024-09-19","arxiv_id":"2409.12993","repositories_listed":1,"syntology":null},{"url":"/paper/synsum-synthetic-benchmark-with-structured","slug":"synsum-synthetic-benchmark-with-structured","title":"SynSUM -- Synthetic Benchmark with Structured and Unstructured Medical Records","date":"2024-09-13","arxiv_id":"2409.08936","repositories_listed":1,"syntology":null},{"url":"/paper/boundless-generating-photorealistic-synthetic","slug":"boundless-generating-photorealistic-synthetic","title":"Boundless: Generating Photorealistic Synthetic Data for Object Detection in Urban Streetscapes","date":"2024-09-04","arxiv_id":"2409.03022","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-llm-scheduling-by-learning-to-rank","slug":"efficient-llm-scheduling-by-learning-to-rank","title":"Efficient LLM Scheduling by Learning to Rank","date":"2024-08-28","arxiv_id":"2408.15792","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/efficient-llm-scheduling-by-learning-to-rank#ran","syntology_url":"https://syntology.ai/paper/2408.15792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15792"}},"official":{"repos":["hao-ai-lab/vllm-ltr"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/generating-data-with-text-to-speech-and-large","slug":"generating-data-with-text-to-speech-and-large","title":"Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition","date":"2024-08-17","arxiv_id":"2408.09215","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02253","slug":"2408-02253","title":"Advancing Post-OCR Correction: A Comparative Study of Synthetic Data","date":"2024-08-05","arxiv_id":"2408.02253","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02140","slug":"2408-02140","title":"VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces","date":"2024-08-04","arxiv_id":"2408.02140","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-synthetic-data-for-enhanced","slug":"optimizing-synthetic-data-for-enhanced","title":"Optimizing Synthetic Data for Enhanced Pancreatic Tumor Segmentation","date":"2024-07-27","arxiv_id":"2407.19284","repositories_listed":1,"syntology":null},{"url":"/paper/vggheads-a-large-scale-synthetic-dataset-for","slug":"vggheads-a-large-scale-synthetic-dataset-for","title":"VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset","date":"2024-07-25","arxiv_id":"2407.18245","repositories_listed":1,"syntology":null},{"url":"/paper/convex-space-learning-for-tabular-synthetic","slug":"convex-space-learning-for-tabular-synthetic","title":"Convex space learning for tabular synthetic data generation","date":"2024-07-13","arxiv_id":"2407.09789","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-hallucination-detection-through","slug":"enhancing-hallucination-detection-through","title":"Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses","date":"2024-07-07","arxiv_id":"2407.05474","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-hallucination-detection-through#ran","syntology_url":"https://syntology.ai/paper/2407.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05474"}},"official":{"repos":["asappresearch/halugen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unigen-a-unified-framework-for-textual","slug":"unigen-a-unified-framework-for-textual","title":"UniGen: A Unified Framework for Textual Dataset Generation Using Large Language Models","date":"2024-06-27","arxiv_id":"2406.18966","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/unigen-a-unified-framework-for-textual#ran","syntology_url":"https://syntology.ai/paper/2406.18966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18966"}},"official":{"repos":["howiehwong/unigen"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/synrs3d-a-synthetic-dataset-for-global-3d","slug":"synrs3d-a-synthetic-dataset-for-global-3d","title":"SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery","date":"2024-06-26","arxiv_id":"2406.18151","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/synrs3d-a-synthetic-dataset-for-global-3d#ran","syntology_url":"https://syntology.ai/paper/2406.18151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18151"}},"official":{"repos":["JTRNEO/SynRS3D"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/voice-disorder-analysis-a-transformer-based","slug":"voice-disorder-analysis-a-transformer-based","title":"Voice Disorder Analysis: a Transformer-based Approach","date":"2024-06-20","arxiv_id":"2406.14693","repositories_listed":1,"syntology":null},{"url":"/paper/nemotron-4-340b-technical-report","slug":"nemotron-4-340b-technical-report","title":"Nemotron-4 340B Technical Report","date":"2024-06-17","arxiv_id":"2406.11704","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/nemotron-4-340b-technical-report#ran","syntology_url":"https://syntology.ai/paper/2406.11704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11704"}},"official":{"repos":["nvidia/nemo-aligner"],"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/enhancing-human-action-recognition-with-gan","slug":"enhancing-human-action-recognition-with-gan","title":"Enhancing human action recognition with GAN-based data augmentation","date":"2024-06-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-oversampling-theory-and-a-practical","slug":"synthetic-oversampling-theory-and-a-practical","title":"Synthetic Oversampling: Theory and A Practical Approach Using LLMs to Address Data Imbalance","date":"2024-06-05","arxiv_id":"2406.03628","repositories_listed":1,"syntology":null},{"url":"/paper/tiny-models-from-tiny-data-textual-and-null","slug":"tiny-models-from-tiny-data-textual-and-null","title":"Tiny models from tiny data: Textual and null-text inversion for few-shot distillation","date":"2024-06-05","arxiv_id":"2406.03146","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-data-generation-for-3d-myocardium","slug":"synthetic-data-generation-for-3d-myocardium","title":"Synthetic Data Generation for 3D Myocardium Deformation Analysis","date":"2024-06-03","arxiv_id":"2406.01040","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-differentially-private-synthetic","slug":"adapting-differentially-private-synthetic","title":"Differentially Private Synthetic Data Generation for Relational Databases","date":"2024-05-29","arxiv_id":"2405.18670","repositories_listed":1,"syntology":null},{"url":"/paper/conditioning-on-time-is-all-you-need-for","slug":"conditioning-on-time-is-all-you-need-for","title":"Conditioning on Time is All You Need for Synthetic Survival Data Generation","date":"2024-05-27","arxiv_id":"2405.17333","repositories_listed":1,"syntology":null},{"url":"/paper/sheet-music-transformer-end-to-end-full-page","slug":"sheet-music-transformer-end-to-end-full-page","title":"End-to-End Full-Page Optical Music Recognition for Pianoform Sheet Music","date":"2024-05-20","arxiv_id":"2405.12105","repositories_listed":1,"syntology":null},{"url":"/paper/synthesizrr-generating-diverse-datasets-with","slug":"synthesizrr-generating-diverse-datasets-with","title":"SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation","date":"2024-05-16","arxiv_id":"2405.10040","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/synthesizrr-generating-diverse-datasets-with#ran","syntology_url":"https://syntology.ai/paper/2405.10040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10040"}},"official":{"repos":["amazon-science/synthesizrr"],"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/prompting-based-synthetic-data-generation-for","slug":"prompting-based-synthetic-data-generation-for","title":"Prompting-based Synthetic Data Generation for Few-Shot Question Answering","date":"2024-05-15","arxiv_id":"2405.09335","repositories_listed":1,"syntology":null},{"url":"/paper/comparative-study-of-models-trained-on","slug":"comparative-study-of-models-trained-on","title":"Comparative study of models trained on synthetic data for Ukrainian grammatical error correction","date":"2024-05-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/on-the-fly-data-augmentation-for-forecasting","slug":"on-the-fly-data-augmentation-for-forecasting","title":"Online Data Augmentation for Forecasting with Deep Learning","date":"2024-04-25","arxiv_id":"2404.16918","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-task-oriented-dialogues-with-state","slug":"simulating-task-oriented-dialogues-with-state","title":"Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models","date":"2024-04-23","arxiv_id":"2404.14772","repositories_listed":1,"syntology":null},{"url":"/paper/better-synthetic-data-by-retrieving-and","slug":"better-synthetic-data-by-retrieving-and","title":"Better Synthetic Data by Retrieving and Transforming Existing Datasets","date":"2024-04-22","arxiv_id":"2404.14361","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/better-synthetic-data-by-retrieving-and#ran","syntology_url":"https://syntology.ai/paper/2404.14361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14361"}},"official":{"repos":["neulab/prompt2model"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-multi-faceted-evaluation-framework-for","slug":"a-multi-faceted-evaluation-framework-for","title":"A Multi-Faceted Evaluation Framework for Assessing Synthetic Data Generated by Large Language Models","date":"2024-04-20","arxiv_id":"2404.14445","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-actions-and-walking-to-llm-generated","slug":"aligning-actions-and-walking-to-llm-generated","title":"Aligning Actions and Walking to LLM-Generated Textual Descriptions","date":"2024-04-18","arxiv_id":"2404.12192","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-deep-learning-for-theorem-proving","slug":"a-survey-on-deep-learning-for-theorem-proving","title":"A Survey on Deep Learning for Theorem Proving","date":"2024-04-15","arxiv_id":"2404.09939","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-prompting-methods-for-mitigating","slug":"exploring-prompting-methods-for-mitigating","title":"EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models","date":"2024-04-15","arxiv_id":"2404.12404","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":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) · 0 unverified","sample_list":"/paper/exploring-prompting-methods-for-mitigating#ran","syntology_url":"https://syntology.ai/paper/2404.12404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12404"}},"official":{"repos":["seharanul17/synthetic-tabular-LLM"],"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/an-evaluation-framework-for-synthetic-data","slug":"an-evaluation-framework-for-synthetic-data","title":"An evaluation framework for synthetic data generation models","date":"2024-04-13","arxiv_id":"2404.08866","repositories_listed":1,"syntology":null},{"url":"/paper/towards-algorithmic-fidelity-mental-health","slug":"towards-algorithmic-fidelity-mental-health","title":"Towards Algorithmic Fidelity: Mental Health Representation across Demographics in Synthetic vs. Human-generated Data","date":"2024-03-25","arxiv_id":"2403.16909","repositories_listed":1,"syntology":null},{"url":"/paper/syncs-synthetic-data-and-contrastive-self","slug":"syncs-synthetic-data-and-contrastive-self","title":"SYNCS: Synthetic Data and Contrastive Self-Supervised Training for Central Sulcus Segmentation","date":"2024-03-22","arxiv_id":"2403.15121","repositories_listed":1,"syntology":null},{"url":"/paper/joint-selection-adaptively-incorporating","slug":"joint-selection-adaptively-incorporating","title":"Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data","date":"2024-03-12","arxiv_id":"2403.07797","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/joint-selection-adaptively-incorporating#ran","syntology_url":"https://syntology.ai/paper/2403.07797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07797"}},"official":{"repos":["miguel-fuentes/jam_aistats"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/synth4bench-a-framework-for-generating","slug":"synth4bench-a-framework-for-generating","title":"Synth4bench: a framework for generating synthetic genomics data for the evaluation of tumor-only somatic variant calling algorithms","date":"2024-03-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-data-generation-for-system","slug":"synthetic-data-generation-for-system","title":"Synthetic data generation for system identification: leveraging knowledge transfer from similar systems","date":"2024-03-08","arxiv_id":"2403.05164","repositories_listed":1,"syntology":null},{"url":"/paper/lab-large-scale-alignment-for-chatbots","slug":"lab-large-scale-alignment-for-chatbots","title":"LAB: Large-Scale Alignment for ChatBots","date":"2024-03-02","arxiv_id":"2403.01081","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/lab-large-scale-alignment-for-chatbots#ran","syntology_url":"https://syntology.ai/paper/2403.01081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01081"}},"official":null}},{"url":"/paper/api-blend-a-comprehensive-corpora-for","slug":"api-blend-a-comprehensive-corpora-for","title":"API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs","date":"2024-02-23","arxiv_id":"2402.15491","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/api-blend-a-comprehensive-corpora-for#ran","syntology_url":"https://syntology.ai/paper/2402.15491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15491"}},"official":{"repos":["ibm/api-blend"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/synthetic-location-trajectory-generation","slug":"synthetic-location-trajectory-generation","title":"Synthetic location trajectory generation using categorical diffusion models","date":"2024-02-19","arxiv_id":"2402.12242","repositories_listed":1,"syntology":null},{"url":"/paper/grasping-the-essentials-tailoring-large","slug":"grasping-the-essentials-tailoring-large","title":"Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction","date":"2024-02-17","arxiv_id":"2402.11142","repositories_listed":1,"syntology":null},{"url":"/paper/datadreamer-a-tool-for-synthetic-data","slug":"datadreamer-a-tool-for-synthetic-data","title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows","date":"2024-02-16","arxiv_id":"2402.10379","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/datadreamer-a-tool-for-synthetic-data#ran","syntology_url":"https://syntology.ai/paper/2402.10379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10379"}},"official":{"repos":["datadreamer-dev/datadreamer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/pedagogical-alignment-of-large-language","slug":"pedagogical-alignment-of-large-language","title":"Pedagogical Alignment of Large Language Models","date":"2024-02-07","arxiv_id":"2402.05000","repositories_listed":1,"syntology":null},{"url":"/paper/unconditional-latent-diffusion-models","slug":"unconditional-latent-diffusion-models","title":"Unconditional Latent Diffusion Models Memorize Patient Imaging Data: Implications for Openly Sharing Synthetic Data","date":"2024-02-01","arxiv_id":"2402.01054","repositories_listed":1,"syntology":null},{"url":"/paper/enhanced-sound-event-localization-and","slug":"enhanced-sound-event-localization-and","title":"Enhanced Sound Event Localization and Detection in Real 360-degree audio-visual soundscapes","date":"2024-01-29","arxiv_id":"2401.17129","repositories_listed":1,"syntology":null},{"url":"/paper/subgroup-analysis-methods-for-time-to-event","slug":"subgroup-analysis-methods-for-time-to-event","title":"Subgroup analysis methods for time-to-event outcomes in heterogeneous randomized controlled trials","date":"2024-01-22","arxiv_id":"2401.11842","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-while-privacy-preserving-a","slug":"scaling-while-privacy-preserving-a","title":"Scaling While Privacy Preserving: A Comprehensive Synthetic Tabular Data Generation and Evaluation in Learning Analytics","date":"2024-01-12","arxiv_id":"2401.06883","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-data-generation-framework-dataset","slug":"synthetic-data-generation-framework-dataset","title":"Synthetic Data Generation Framework, Dataset, and Efficient Deep Model for Pedestrian Intention Prediction","date":"2024-01-12","arxiv_id":"2401.06757","repositories_listed":1,"syntology":null},{"url":"/paper/uavd4l-a-large-scale-dataset-for-uav-6-dof","slug":"uavd4l-a-large-scale-dataset-for-uav-6-dof","title":"UAVD4L: A Large-Scale Dataset for UAV 6-DoF Localization","date":"2024-01-11","arxiv_id":"2401.05971","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/uavd4l-a-large-scale-dataset-for-uav-6-dof#ran","syntology_url":"https://syntology.ai/paper/2401.05971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05971"}},"official":{"repos":["ringowrw/uavd4l"],"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/irg-generating-synthetic-relational-databases","slug":"irg-generating-synthetic-relational-databases","title":"IRG: Generating Synthetic Relational Databases using Deep Learning with Insightful Relational Understanding","date":"2023-12-23","arxiv_id":"2312.15187","repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-end-to-end-computer-vision","slug":"a-comprehensive-end-to-end-computer-vision","title":"A Comprehensive End-to-End Computer Vision Framework for Restoration and Recognition of Low-Quality Engineering Drawings","date":"2023-12-21","arxiv_id":"2312.13620","repositories_listed":1,"syntology":null},{"url":"/paper/retailsynth-synthetic-data-generation-for","slug":"retailsynth-synthetic-data-generation-for","title":"RetailSynth: Synthetic Data Generation for Retail AI Systems Evaluation","date":"2023-12-21","arxiv_id":"2312.14095","repositories_listed":1,"syntology":null},{"url":"/paper/view-dependent-octree-based-mesh-extraction","slug":"view-dependent-octree-based-mesh-extraction","title":"View-Dependent Octree-based Mesh Extraction in Unbounded Scenes for Procedural Synthetic Data","date":"2023-12-13","arxiv_id":"2312.08364","repositories_listed":1,"syntology":null},{"url":"/paper/combining-propensity-score-methods-with","slug":"combining-propensity-score-methods-with","title":"Combining propensity score methods with variational autoencoders for generating synthetic data in presence of latent sub-groups","date":"2023-12-12","arxiv_id":"2312.07781","repositories_listed":1,"syntology":null},{"url":"/paper/d3a-ts-denoising-driven-data-augmentation-in","slug":"d3a-ts-denoising-driven-data-augmentation-in","title":"D3A-TS: Denoising-Driven Data Augmentation in Time Series","date":"2023-12-09","arxiv_id":"2312.05550","repositories_listed":1,"syntology":null},{"url":"/paper/tsmorph-generation-of-semi-synthetic-time","slug":"tsmorph-generation-of-semi-synthetic-time","title":"Enhancing Algorithm Performance Understanding through tsMorph: Generating Semi-Synthetic Time Series for Robust Forecasting Evaluation","date":"2023-12-03","arxiv_id":"2312.01344","repositories_listed":1,"syntology":null},{"url":"/paper/privacy-preserving-data-sharing-in","slug":"privacy-preserving-data-sharing-in","title":"Privacy-Preserving Data Sharing in Agriculture: Enforcing Policy Rules for Secure and Confidential Data Synthesis","date":"2023-11-27","arxiv_id":"2311.15460","repositories_listed":1,"syntology":null},{"url":"/paper/safesea-synthetic-data-generation-for-adverse","slug":"safesea-synthetic-data-generation-for-adverse","title":"SafeSea: Synthetic Data Generation for Adverse & Low Probability Maritime Conditions","date":"2023-11-24","arxiv_id":"2311.14764","repositories_listed":1,"syntology":null},{"url":"/paper/survtimesurvival-survival-analysis-on-the","slug":"survtimesurvival-survival-analysis-on-the","title":"SurvTimeSurvival: Survival Analysis On The Patient With Multiple Visits/Records","date":"2023-11-16","arxiv_id":"2311.09854","repositories_listed":1,"syntology":null},{"url":"/paper/gec-depend-non-autoregressive-grammatical","slug":"gec-depend-non-autoregressive-grammatical","title":"GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding","date":"2023-11-14","arxiv_id":"2311.08191","repositories_listed":1,"syntology":null},{"url":"/paper/mmm-and-mmmsynth-clustering-of-heterogeneous","slug":"mmm-and-mmmsynth-clustering-of-heterogeneous","title":"MMM and MMMSynth: Clustering of heterogeneous tabular data, and synthetic data generation","date":"2023-10-30","arxiv_id":"2310.19454","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-data-analytics-with-synthetic-volume","slug":"boosting-data-analytics-with-synthetic-volume","title":"Boosting Data Analytics With Synthetic Volume Expansion","date":"2023-10-27","arxiv_id":"2310.17848","repositories_listed":1,"syntology":null},{"url":"/paper/autodiff-combining-auto-encoder-and-diffusion","slug":"autodiff-combining-auto-encoder-and-diffusion","title":"AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing","date":"2023-10-24","arxiv_id":"2310.15479","repositories_listed":1,"syntology":null},{"url":"/paper/winsyn-a-high-resolution-testbed-for","slug":"winsyn-a-high-resolution-testbed-for","title":"WinSyn: A High Resolution Testbed for Synthetic Data","date":"2023-10-09","arxiv_id":"2310.08471","repositories_listed":1,"syntology":null},{"url":"/paper/flaim-aim-based-synthetic-data-generation-in","slug":"flaim-aim-based-synthetic-data-generation-in","title":"FLAIM: AIM-based Synthetic Data Generation in the Federated Setting","date":"2023-10-05","arxiv_id":"2310.03447","repositories_listed":1,"syntology":null},{"url":"/paper/stable-training-of-probabilistic-models-using","slug":"stable-training-of-probabilistic-models-using","title":"Stable Training of Probabilistic Models Using the Leave-One-Out Maximum Log-Likelihood Objective","date":"2023-10-05","arxiv_id":"2310.03556","repositories_listed":1,"syntology":null},{"url":"/paper/text-data-augmentation-in-low-resource","slug":"text-data-augmentation-in-low-resource","title":"Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models","date":"2023-10-02","arxiv_id":"2310.01119","repositories_listed":1,"syntology":null},{"url":"/paper/gecturk-grammatical-error-correction-and","slug":"gecturk-grammatical-error-correction-and","title":"GECTurk: Grammatical Error Correction and Detection Dataset for Turkish","date":"2023-09-20","arxiv_id":"2309.11346","repositories_listed":1,"syntology":null},{"url":"/paper/converser-few-shot-conversational-dense","slug":"converser-few-shot-conversational-dense","title":"CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generation","date":"2023-09-13","arxiv_id":"2309.06748","repositories_listed":1,"syntology":null},{"url":"/paper/leyes-a-lightweight-framework-for-deep","slug":"leyes-a-lightweight-framework-for-deep","title":"LEyes: A Lightweight Framework for Deep Learning-Based Eye Tracking using Synthetic Eye Images","date":"2023-09-12","arxiv_id":"2309.06129","repositories_listed":1,"syntology":null},{"url":"/paper/distributional-data-augmentation-methods-for","slug":"distributional-data-augmentation-methods-for","title":"Distributional Data Augmentation Methods for Low Resource Language","date":"2023-09-09","arxiv_id":"2309.04862","repositories_listed":1,"syntology":null},{"url":"/paper/findiff-diffusion-models-for-financial","slug":"findiff-diffusion-models-for-financial","title":"FinDiff: Diffusion Models for Financial Tabular Data Generation","date":"2023-09-04","arxiv_id":"2309.01472","repositories_listed":1,"syntology":null},{"url":"/paper/generating-tabular-datasets-under","slug":"generating-tabular-datasets-under","title":"Generating tabular datasets under differential privacy","date":"2023-08-28","arxiv_id":"2308.14784","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generating-tabular-datasets-under#ran","syntology_url":"https://syntology.ai/paper/2308.14784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14784"}},"official":{"repos":["gianlucatruda/TableDiffusion"],"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"]}}}],"record_sha256":"5c50ab814c9c3f904e8c5841d2084713087955595aed37bdc6cc91e957d5caa6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}