{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/clean-text","entry":"clean_text","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","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)"},"n_papers":84,"n_papers_ran":34,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":80,"n_samples_ran":30,"n_samples_fingerprinted":29,"n_places":87,"n_places_pointer_only":29,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":11,"ran_fixture":0,"ran":19,"unverified":50},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2609.01147","paper":"/paper/arxiv-2609-01147","title":"On the Design Fundamentals of Pixel Text Representation Learning","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"Pixel-Linguist/Pixel-Linguist-II","path":"training/filter_dataset.py","file_url":"https://github.com/Pixel-Linguist/Pixel-Linguist-II/blob/HEAD/training/filter_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b5bb3eecb46f7556","mcp_get_code":{"code_sha256":"b5bb3eecb46f7556"}},{"arxiv_id":"2608.23640","paper":"/paper/arxiv-2608-23640","title":"Auditing the Synthetic Memoir: Measuring Scene-Level Confabulation in LLM-Generated Autobiography Against the Documented Record of the Life It Describes","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"heathriel/synthetic-memoir-audit","path":"analysis/09_build_public_source_registry.py","file_url":"https://github.com/heathriel/synthetic-memoir-audit/blob/HEAD/analysis/09_build_public_source_registry.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"291a30968bfd353d","mcp_get_code":{"code_sha256":"291a30968bfd353d"}},{"arxiv_id":"2608.12836","paper":"/paper/arxiv-2608-12836","title":"From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"obedjunias19/structured-compositional-reasoning","path":"lsata/run_structured_inference.py","file_url":"https://github.com/obedjunias19/structured-compositional-reasoning/blob/HEAD/lsata/run_structured_inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b26dd53b8f714434","mcp_get_code":{"code_sha256":"b26dd53b8f714434"}},{"arxiv_id":"2607.25959","paper":"/paper/arxiv-2607-25959","title":"Detecting Knowledge Inconsistencies Across Text, Tables, and Knowledge Graphs","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"ECLADATTA/KONTRAST","path":"Output_GRASP/Qwen3-4B-Instruct-2507/ComplexQA/tag.py","file_url":"https://github.com/ECLADATTA/KONTRAST/blob/HEAD/Output_GRASP/Qwen3-4B-Instruct-2507/ComplexQA/tag.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc20d3e7db14a81f","mcp_get_code":{"code_sha256":"cc20d3e7db14a81f"}},{"arxiv_id":"2607.23512","paper":"/paper/arxiv-2607-23512","title":"The Cross-Domain Generalization Cost of Offensive Language Detection","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"renruixing/The-Cross-Domain-Generalization-Cost-of-Offensive-Language-Detection","path":"prepare_dataset.py","file_url":"https://github.com/renruixing/The-Cross-Domain-Generalization-Cost-of-Offensive-Language-Detection/blob/HEAD/prepare_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2b3dcbbecbaa9c5b","mcp_get_code":{"code_sha256":"2b3dcbbecbaa9c5b"}},{"arxiv_id":"2607.18235","paper":"/paper/arxiv-2607-18235","title":"Automated Discovery Has No Universally Superior Harness","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"akshat57/harness-generalization","path":"allocation/plot_sheet_config_score_boxes.py","file_url":"https://github.com/akshat57/harness-generalization/blob/HEAD/allocation/plot_sheet_config_score_boxes.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"28dcdd8e4cc20e02","mcp_get_code":{"code_sha256":"28dcdd8e4cc20e02"}},{"arxiv_id":"2606.02578","paper":"/paper/arxiv-2606-02578","title":"Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"kaist-cvml/perception-judge","path":"prepare-datasets/post_processing_filter_after_gen.py","file_url":"https://github.com/kaist-cvml/perception-judge/blob/HEAD/prepare-datasets/post_processing_filter_after_gen.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cfeb19d54f2339b3","mcp_get_code":{"code_sha256":"cfeb19d54f2339b3"}},{"arxiv_id":"2605.28093","paper":"/paper/arxiv-2605-28093","title":"ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"yikai-zhu/ConRAG","path":"src/conrag/common.py","file_url":"https://github.com/yikai-zhu/ConRAG/blob/HEAD/src/conrag/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e0d187ce27d64511","mcp_get_code":{"code_sha256":"e0d187ce27d64511"}},{"arxiv_id":"2605.01317","paper":"/paper/arxiv-2605-01317","title":"Sentiment Analysis of Mobile Legends App Reviews Using Machine Learning and LSTM-Based Deep Learning Models","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Viramhrani/pba2026-Kelompok16","path":"app/app_dl.py","file_url":"https://github.com/Viramhrani/pba2026-Kelompok16/blob/HEAD/app/app_dl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"06580d402622ea57","mcp_get_code":{"code_sha256":"06580d402622ea57"}},{"arxiv_id":"2604.24720","paper":"/paper/arxiv-2604-24720","title":"Sentiment and Emotion Classification of Indonesian E-Commerce Reviews via Multi-Task BiLSTM and AutoML Benchmarking","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"ikii-sd/pba2026-crazyrichteam","path":"src/preprocessing.py","file_url":"https://github.com/ikii-sd/pba2026-crazyrichteam/blob/HEAD/src/preprocessing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a0244a869f42339c","mcp_get_code":{"code_sha256":"a0244a869f42339c"}},{"arxiv_id":"2604.19505","paper":"/paper/arxiv-2604-19505","title":"Enhancing Unsupervised Keyword Extraction in Academic Papers through Integrating Highlights with Abstract","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"xiangyi-njust/Highlight-KPE","path":"code/MDERank/mderank.py","file_url":"https://github.com/xiangyi-njust/Highlight-KPE/blob/HEAD/code/MDERank/mderank.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"276c875f8460a41e","mcp_get_code":{"code_sha256":"276c875f8460a41e"}},{"arxiv_id":"2604.16607","paper":"/paper/arxiv-2604-16607","title":"Spotlights and Blindspots: Evaluating Machine-Generated Text Detection","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"thinkst/zippy","path":"zippy/zippy.py","file_url":"https://github.com/thinkst/zippy/blob/HEAD/zippy/zippy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"279e23ca5da96480","mcp_get_code":{"code_sha256":"279e23ca5da96480"}},{"arxiv_id":"2604.10874","paper":"/paper/arxiv-2604-10874","title":"AOP-Smart: A RAG-Enhanced Large Language Model Framework for Adverse Outcome Pathway Analysis","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"qinjiang-lab/AOP-Smart","path":"AOP-Smart.py","file_url":"https://github.com/qinjiang-lab/AOP-Smart/blob/HEAD/AOP-Smart.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b08f75a14f197c80","mcp_get_code":{"code_sha256":"b08f75a14f197c80"}},{"arxiv_id":"2604.10874","paper":"/paper/arxiv-2604-10874","title":"AOP-Smart: A RAG-Enhanced Large Language Model Framework for Adverse Outcome Pathway Analysis","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"qinjiang-lab/AOP-Smart","path":"XML_analysis.py","file_url":"https://github.com/qinjiang-lab/AOP-Smart/blob/HEAD/XML_analysis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ddb4aa5850a0592","mcp_get_code":{"code_sha256":"0ddb4aa5850a0592"}},{"arxiv_id":"2604.08554","paper":"/paper/arxiv-2604-08554","title":"Drift and selection in LLM text ecosystems","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"SR123/LLM-text-ecosystems","path":"src/drift_selection/cleaning.py","file_url":"https://github.com/SR123/LLM-text-ecosystems/blob/HEAD/src/drift_selection/cleaning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1b6456251fc3b160","mcp_get_code":{"code_sha256":"1b6456251fc3b160"}},{"arxiv_id":"2603.07346","paper":"/paper/arxiv-2603-07346","title":"How Much Noise Can BERT Handle? Insights from Multilingual Sentence Difficulty Detection","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Nouran-Khallaf/denoising-difficulty","path":"models/Baseline.py","file_url":"https://github.com/Nouran-Khallaf/denoising-difficulty/blob/HEAD/models/Baseline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e9eb5d0c4765858b","mcp_get_code":{"code_sha256":"e9eb5d0c4765858b"}},{"arxiv_id":"2603.07346","paper":"/paper/arxiv-2603-07346","title":"How Much Noise Can BERT Handle? Insights from Multilingual Sentence Difficulty Detection","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Nouran-Khallaf/denoising-difficulty","path":"models/baseline.py","file_url":"https://github.com/Nouran-Khallaf/denoising-difficulty/blob/HEAD/models/baseline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"332ce80bbbda4118","mcp_get_code":{"code_sha256":"332ce80bbbda4118"}},{"arxiv_id":"2602.17653","paper":"/paper/arxiv-2602-17653","title":"Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Iskar-Deng/DAM-learning","path":"data_processing/parse.py","file_url":"https://github.com/Iskar-Deng/DAM-learning/blob/HEAD/data_processing/parse.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"42072772adaf6878","mcp_get_code":{"code_sha256":"42072772adaf6878"}},{"arxiv_id":"2602.15898","paper":"/paper/arxiv-2602-15898","title":"MultiCube-RAG for Multi-hop Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"OpenBMB/UltraRAG","path":"servers/corpus/src/corpus.py","file_url":"https://github.com/OpenBMB/UltraRAG/blob/HEAD/servers/corpus/src/corpus.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4de9e8ee4cbe4329","mcp_get_code":{"code_sha256":"4de9e8ee4cbe4329"}},{"arxiv_id":"2601.22920","paper":"/paper/arxiv-2601-22920","title":"Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessment","date":"2026-01-30","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"AMAP-ML/Q-Hawkeye","path":"src/virft/src/open_r1/grpo_am.py","file_url":"https://github.com/AMAP-ML/Q-Hawkeye/blob/HEAD/src/virft/src/open_r1/grpo_am.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ed1cffd12a5fc04","mcp_get_code":{"code_sha256":"7ed1cffd12a5fc04"}},{"arxiv_id":"2601.15115","paper":"/paper/arxiv-2601-15115","title":"Training-Free and Interpretable Hateful Video Detection via Multi-stage Adversarial Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Multimodal-Intelligence-Lab-MIL/MARS","path":"code/MARS/gemini2.5flash.py","file_url":"https://github.com/Multimodal-Intelligence-Lab-MIL/MARS/blob/HEAD/code/MARS/gemini2.5flash.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e609dfa06255ac50","mcp_get_code":{"code_sha256":"e609dfa06255ac50"}},{"arxiv_id":"2510.17425","paper":"/paper/arxiv-2510-17425","title":"Quantifying Climate Policy Action and Its Links to Development Outcomes: A Cross-National Data-Driven Analysis","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"booktrackerGirl/climate_change_policy_analysis","path":"src/extract_content.py","file_url":"https://github.com/booktrackerGirl/climate_change_policy_analysis/blob/HEAD/src/extract_content.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"818185916e2d10a0","mcp_get_code":{"code_sha256":"818185916e2d10a0"}},{"arxiv_id":"2509.24088","paper":"/paper/arxiv-2509-24088","title":"CORRECT: Condensed Error Recognition via Knowledge Transfer in Multi-agent Systems","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"UIUC-MLSys/CORRECT","path":"src/Lib/cloud_paper.py","file_url":"https://github.com/UIUC-MLSys/CORRECT/blob/HEAD/src/Lib/cloud_paper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"18f2cdd35c9ac991","mcp_get_code":{"code_sha256":"18f2cdd35c9ac991"}},{"arxiv_id":"2507.06210","paper":"/paper/cultureclip-empowering-clip-with-cultural","title":"CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions","date":"2025-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lukahhcm/cultureclip","path":"data_curation/diverse_caption.py","file_url":"https://github.com/lukahhcm/cultureclip/blob/HEAD/data_curation/diverse_caption.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"98f3d9a2dbe966f8","mcp_get_code":{"code_sha256":"98f3d9a2dbe966f8"}},{"arxiv_id":"2505.14106","paper":"/paper/a-personalized-conversational-benchmark","title":"A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"persona-bench/persona","path":"PromptMakers/3.3PromptMaker.py","file_url":"https://github.com/persona-bench/persona/blob/HEAD/PromptMakers/3.3PromptMaker.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b3a8c68af7fbac6f","mcp_get_code":{"code_sha256":"b3a8c68af7fbac6f"}},{"arxiv_id":"2503.15092","paper":"/paper/towards-understanding-the-safety-boundaries","title":"Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings","date":"2025-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ny1024/deepseek-safety-eval","path":"eval/base/deepseek_r1.py","file_url":"https://github.com/ny1024/deepseek-safety-eval/blob/HEAD/eval/base/deepseek_r1.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"618e93855f6e4e2b","mcp_get_code":{"code_sha256":"618e93855f6e4e2b"}},{"arxiv_id":"2503.10460","paper":"/paper/light-r1-curriculum-sft-dpo-and-rl-for-long","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","date":"2025-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Qihoo360/Light-R1","path":"decontaminate/character_matching.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/decontaminate/character_matching.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"61619ba901c7b574","mcp_get_code":{"code_sha256":"61619ba901c7b574"}},{"arxiv_id":"2410.08044","paper":"/paper/the-rise-of-ai-generated-content-in-wikipedia","title":"The Rise of AI-Generated Content in Wikipedia","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brooksca3/wiki_collection","path":"eval/binoculars/run_wiki_binoculars.py","file_url":"https://github.com/brooksca3/wiki_collection/blob/HEAD/eval/binoculars/run_wiki_binoculars.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"722efc24678ccc7e","mcp_get_code":{"code_sha256":"722efc24678ccc7e"}},{"arxiv_id":"2410.00593","paper":"/paper/style-specific-neurons-for-steering-llms-in","title":"Style-Specific Neurons for Steering LLMs in Text Style Transfer","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenlai-lavine/sNeuron-TST","path":"Evaluation/cls/authorship.py","file_url":"https://github.com/wenlai-lavine/sNeuron-TST/blob/HEAD/Evaluation/cls/authorship.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5eb4d0e1f153b895","mcp_get_code":{"code_sha256":"5eb4d0e1f153b895"}},{"arxiv_id":"2409.18747","paper":"/paper/cottention-linear-transformers-with-cosine","title":"Cottention: Linear Transformers With Cosine Attention","date":"2024-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gmongaras/Cottention_Transformer","path":"BERT_Trainer/create_hf_datasets.py","file_url":"https://github.com/gmongaras/Cottention_Transformer/blob/HEAD/BERT_Trainer/create_hf_datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"774558f531286112","mcp_get_code":{"code_sha256":"774558f531286112"}},{"arxiv_id":"2409.11295","paper":"/paper/eia-environmental-injection-attack-on","title":"EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage","date":"2024-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"osu-nlp-group/eia_against_webagent","path":"SeeAct/src/data_utils/dom_utils.py","file_url":"https://github.com/osu-nlp-group/eia_against_webagent/blob/HEAD/SeeAct/src/data_utils/dom_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0e07e2733eab1746","mcp_get_code":{"code_sha256":"0e07e2733eab1746"}},{"arxiv_id":"2408.15545","paper":"/paper/scilitllm-how-to-adapt-llms-for-scientific","title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","date":"2024-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dptech-corp/Uni-SMART","path":"SciLitLLM/sft/helper/parse_pdfs.py","file_url":"https://github.com/dptech-corp/Uni-SMART/blob/HEAD/SciLitLLM/sft/helper/parse_pdfs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e366df93e0e0280","mcp_get_code":{"code_sha256":"2e366df93e0e0280"}},{"arxiv_id":"2406.11171","paper":"/paper/sugarcrepe-dataset-vision-language-model","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Sri-Harsha/scpp","path":"generate_sugarcrepe_plus-mistral.py","file_url":"https://github.com/Sri-Harsha/scpp/blob/HEAD/generate_sugarcrepe_plus-mistral.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7c6b861ca90aa566","mcp_get_code":{"code_sha256":"7c6b861ca90aa566"}},{"arxiv_id":"2406.05213","paper":"/paper/on-subjective-uncertainty-quantification-and","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meta-inf/suq-nlg","path":"qa/vu.py","file_url":"https://github.com/meta-inf/suq-nlg/blob/HEAD/qa/vu.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2745a7b067527cea","mcp_get_code":{"code_sha256":"2745a7b067527cea"}},{"arxiv_id":"2405.13845","paper":"/paper/semantic-density-uncertainty-quantification","title":"Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space","date":"2024-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cognizant-ai-labs/semantic-density-paper","path":"experiment_code/get_semantic_density_full_beam_search_unique_datasets_temperature.py","file_url":"https://github.com/cognizant-ai-labs/semantic-density-paper/blob/HEAD/experiment_code/get_semantic_density_full_beam_search_unique_datasets_temperature.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"382e62efddba975b","mcp_get_code":{"code_sha256":"382e62efddba975b"}},{"arxiv_id":"2405.10974","paper":"/paper/bottleneck-minimal-indexing-for-generative","title":"Bottleneck-Minimal Indexing for Generative Document Retrieval","date":"2024-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kduxin/Bottleneck-Minimal-Indexing","path":"NCIRetriever/model.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/NCIRetriever/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d140ce18f0b48ed","mcp_get_code":{"code_sha256":"5d140ce18f0b48ed"}},{"arxiv_id":"2405.10260","paper":"/paper/keep-it-private-unsupervised-privatization-of","title":"Keep It Private: Unsupervised Privatization of Online Text","date":"2024-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csbao/kip-privatization","path":"src/generator.py","file_url":"https://github.com/csbao/kip-privatization/blob/HEAD/src/generator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"32acbc36604380fe","mcp_get_code":{"code_sha256":"32acbc36604380fe"}},{"arxiv_id":"2404.06654","paper":"/paper/ruler-what-s-the-real-context-size-of-your","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","date":"2024-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mungg/OneRuler","path":"OneRuler/eval/evaluate.py","file_url":"https://github.com/mungg/OneRuler/blob/HEAD/OneRuler/eval/evaluate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d7f2c747adfac407","mcp_get_code":{"code_sha256":"d7f2c747adfac407"}},{"arxiv_id":"2404.00614","paper":"/paper/learning-to-plan-for-language-modeling-from","title":"Learning to Plan for Language Modeling from Unlabeled Data","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"natithan/learning-to-plan-for-language-modeling-from-unlabeled-data","path":"eval_generations.py","file_url":"https://github.com/natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/blob/HEAD/eval_generations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"efc543ba6ad34128","mcp_get_code":{"code_sha256":"efc543ba6ad34128"}},{"arxiv_id":"2403.14622","paper":"/paper/language-repository-for-long-video","title":"Language Repository for Long Video Understanding","date":"2024-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kkahatapitiya/langrepo","path":"util.py","file_url":"https://github.com/kkahatapitiya/langrepo/blob/HEAD/util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d3cd8c8e5b09319c","mcp_get_code":{"code_sha256":"d3cd8c8e5b09319c"}},{"arxiv_id":"2403.06764","paper":"/paper/an-image-is-worth-1-2-tokens-after-layer-2","title":"An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pkunlp-icler/fastv","path":"src/FastV/inference/eval/inference_aokvqa.py","file_url":"https://github.com/pkunlp-icler/fastv/blob/HEAD/src/FastV/inference/eval/inference_aokvqa.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"22967b94d546f593","mcp_get_code":{"code_sha256":"22967b94d546f593"}},{"arxiv_id":"2402.15057","paper":"/paper/on-the-multi-turn-instruction-following-for","title":"On the Multi-turn Instruction Following for Conversational Web Agents","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"magicgh/self-map","path":"src/dom_utils.py","file_url":"https://github.com/magicgh/self-map/blob/HEAD/src/dom_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0e07e2733eab1746","mcp_get_code":{"code_sha256":"0e07e2733eab1746"}},{"arxiv_id":"2401.01614","paper":"/paper/gpt-4v-ision-is-a-generalist-web-agent-if","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","date":"2024-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"osu-nlp-group/seeact","path":"src/data_utils/dom_utils.py","file_url":"https://github.com/osu-nlp-group/seeact/blob/HEAD/src/data_utils/dom_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0e07e2733eab1746","mcp_get_code":{"code_sha256":"0e07e2733eab1746"}},{"arxiv_id":"2310.18440","paper":"/paper/modeling-legal-reasoning-lm-annotation-at-the","title":"Modeling Legal Reasoning: LM Annotation at the Edge of Human Agreement","date":"2023-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rosthalken/legal-interpretation","path":"create_samples.py","file_url":"https://github.com/rosthalken/legal-interpretation/blob/HEAD/create_samples.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b305b281072ece66","mcp_get_code":{"code_sha256":"b305b281072ece66"}},{"arxiv_id":"2310.16226","paper":"/paper/tic-clip-continual-training-of-clip-models","title":"TiC-CLIP: Continual Training of CLIP Models","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-tic-clip","path":"dataset_creation/tic-yfcc15m/create_splits.py","file_url":"https://github.com/apple/ml-tic-clip/blob/HEAD/dataset_creation/tic-yfcc15m/create_splits.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"9b270ee2a7164544","mcp_get_code":{"code_sha256":"9b270ee2a7164544"}},{"arxiv_id":"2309.08943","paper":"/paper/contextual-label-projection-for-cross-lingual","title":"Contextual Label Projection for Cross-Lingual Structured Prediction","date":"2023-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pluslabnlp/clap","path":"src/utils.py","file_url":"https://github.com/pluslabnlp/clap/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ef707ceb5ff307d7","mcp_get_code":{"code_sha256":"ef707ceb5ff307d7"}},{"arxiv_id":"2309.08105","paper":"/paper/libriheavy-a-50000-hours-asr-corpus-with","title":"Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context","date":"2023-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"k2-fsa/libriheavy","path":"scripts/extract_and_normalize_transcript.py","file_url":"https://github.com/k2-fsa/libriheavy/blob/HEAD/scripts/extract_and_normalize_transcript.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"20b4ccb36cf358ec","mcp_get_code":{"code_sha256":"20b4ccb36cf358ec"}},{"arxiv_id":"2309.00916","paper":"/paper/blsp-bootstrapping-language-speech-pre-1","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","date":"2023-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cwang621/blsp","path":"data_process/prepare_alpaca.py","file_url":"https://github.com/cwang621/blsp/blob/HEAD/data_process/prepare_alpaca.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"61134cad531c377a","mcp_get_code":{"code_sha256":"61134cad531c377a"}},{"arxiv_id":"2307.03749","paper":"/paper/on-the-efficacy-of-sampling-adapters","title":"On the Efficacy of Sampling Adapters","date":"2023-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rycolab/sampling-adapters","path":"utils.py","file_url":"https://github.com/rycolab/sampling-adapters/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"25466aac44e0d840","mcp_get_code":{"code_sha256":"25466aac44e0d840"}},{"arxiv_id":"2306.06843","paper":"/paper/recurrent-attention-networks-for-long-text","title":"Recurrent Attention Networks for Long-text Modeling","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"4ai/ran","path":"examples/LongCLF/run_20ng.py","file_url":"https://github.com/4ai/ran/blob/HEAD/examples/LongCLF/run_20ng.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"08092de6a633d0d8","mcp_get_code":{"code_sha256":"08092de6a633d0d8"}},{"arxiv_id":"2305.02468","paper":"/paper/task-optimized-adapters-for-an-end-to-end","title":"Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System","date":"2023-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sogang-isds/TOATOD","path":"E2E_TOD/clean_dataset.py","file_url":"https://github.com/sogang-isds/TOATOD/blob/HEAD/E2E_TOD/clean_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"066f7f2b00042eec","mcp_get_code":{"code_sha256":"066f7f2b00042eec"}},{"arxiv_id":"2303.14443","paper":"/paper/no-more-reviewer-2-subverting-automatic-paper","title":"No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning","date":"2023-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rub-syssec/adversarial-papers","path":"src/utils/attack_utils.py","file_url":"https://github.com/rub-syssec/adversarial-papers/blob/HEAD/src/utils/attack_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f71c17baa894982","mcp_get_code":{"code_sha256":"0f71c17baa894982"}},{"arxiv_id":"2302.11520","paper":"/paper/guiding-large-language-models-via-directional-1","title":"Guiding Large Language Models via Directional Stimulus Prompting","date":"2023-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leezekun/directional-stimulus-prompting","path":"sft4lms/MultiWOZ/clean_dataset.py","file_url":"https://github.com/leezekun/directional-stimulus-prompting/blob/HEAD/sft4lms/MultiWOZ/clean_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ea3e5b726884db6d","mcp_get_code":{"code_sha256":"ea3e5b726884db6d"}},{"arxiv_id":"2212.11140","paper":"/paper/benchmarking-large-language-models-for","title":"Benchmarking Large Language Models for Automated Verilog RTL Code Generation","date":"2022-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shailja-thakur/vgen","path":"pdf_extraction_instance.py","file_url":"https://github.com/shailja-thakur/vgen/blob/HEAD/pdf_extraction_instance.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"66956cac853d371d","mcp_get_code":{"code_sha256":"66956cac853d371d"}},{"arxiv_id":"2210.08692","paper":"/paper/a-generative-user-simulator-with-gpt-based","title":"A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems","date":"2022-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-spmi/gus","path":"clean_dataset.py","file_url":"https://github.com/thu-spmi/gus/blob/HEAD/clean_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c20b24a9790d8f15","mcp_get_code":{"code_sha256":"c20b24a9790d8f15"}},{"arxiv_id":"2207.06300","paper":"/paper/re2g-retrieve-rerank-generate-2","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibm/kgi-slot-filling","path":"slot_filling/kilt_passage_corpus.py","file_url":"https://github.com/ibm/kgi-slot-filling/blob/HEAD/slot_filling/kilt_passage_corpus.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d890771bd3e4b3f7","mcp_get_code":{"code_sha256":"d890771bd3e4b3f7"}},{"arxiv_id":"2205.10747","paper":"/paper/language-models-with-image-descriptors-are","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","date":"2022-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mikewangwzhl/vidil","path":"eval_video_captioning_results.py","file_url":"https://github.com/mikewangwzhl/vidil/blob/HEAD/eval_video_captioning_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ff44f0d81c9de63","mcp_get_code":{"code_sha256":"1ff44f0d81c9de63"}},{"arxiv_id":"2112.05682","paper":"/paper/self-attention-does-not-need-o-n-2-memory","title":"Self-attention Does Not Need $O(n^2)$ Memory","date":"2021-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"X-iZhang/Libra","path":"libra/eval/radiology_report.py","file_url":"https://github.com/X-iZhang/Libra/blob/HEAD/libra/eval/radiology_report.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"46c06fec5aedf4a4","mcp_get_code":{"code_sha256":"46c06fec5aedf4a4"}},{"arxiv_id":"2112.05682","paper":"/paper/self-attention-does-not-need-o-n-2-memory","title":"Self-attention Does Not Need $O(n^2)$ Memory","date":"2021-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"X-iZhang/Libra","path":"libra/eval/temporal_f1.py","file_url":"https://github.com/X-iZhang/Libra/blob/HEAD/libra/eval/temporal_f1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cb00b798f297e5f3","mcp_get_code":{"code_sha256":"cb00b798f297e5f3"}},{"arxiv_id":"2110.09753","paper":"/paper/unifying-multimodal-transformer-for-bi","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","date":"2021-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"researchmm/generate-it","path":"diverse-it-generator/sample_images.py","file_url":"https://github.com/researchmm/generate-it/blob/HEAD/diverse-it-generator/sample_images.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54027d44ffd92b3d","mcp_get_code":{"code_sha256":"54027d44ffd92b3d"}},{"arxiv_id":"2109.14739","paper":"/paper/multi-task-pre-training-for-plug-and-play","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","date":"2021-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awslabs/pptod","path":"E2E_TOD/clean_dataset.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/E2E_TOD/clean_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ea3e5b726884db6d","mcp_get_code":{"code_sha256":"ea3e5b726884db6d"}},{"arxiv_id":"2108.13934","paper":"/paper/robust-retrieval-augmented-generation-for","title":"Robust Retrieval Augmented Generation for Zero-shot Slot Filling","date":"2021-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/retrieve-write-slot-filling","path":"slot_filling/kilt_passage_corpus.py","file_url":"https://github.com/IBM/retrieve-write-slot-filling/blob/HEAD/slot_filling/kilt_passage_corpus.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d890771bd3e4b3f7","mcp_get_code":{"code_sha256":"d890771bd3e4b3f7"}},{"arxiv_id":"2108.01879","paper":"/paper/summary-explorer-visualizing-the-state-of-the","title":"Summary Explorer: Visualizing the State of the Art in Text Summarization","date":"2021-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"webis-de/summary-explorer","path":"text-processing/src/utils.py","file_url":"https://github.com/webis-de/summary-explorer/blob/HEAD/text-processing/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f7918be2e65b31a7","mcp_get_code":{"code_sha256":"f7918be2e65b31a7"}},{"arxiv_id":"2104.08202","paper":"/paper/q-2-evaluating-factual-consistency-in","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","date":"2021-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"orhonovich/q-squared","path":"pipeline/score.py","file_url":"https://github.com/orhonovich/q-squared/blob/HEAD/pipeline/score.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"96af2fcff56e897c","mcp_get_code":{"code_sha256":"96af2fcff56e897c"}},{"arxiv_id":"2104.07605","paper":"/paper/summvis-interactive-visual-analysis-of-models","title":"SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization","date":"2021-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"robustness-gym/summvis","path":"utils.py","file_url":"https://github.com/robustness-gym/summvis/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7c9b5b54376420a1","mcp_get_code":{"code_sha256":"7c9b5b54376420a1"}},{"arxiv_id":"2009.12005","paper":"/paper/mintl-minimalist-transfer-learning-for-task","title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","date":"2020-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zlinao/MinTL","path":"damd_multiwoz/clean_dataset.py","file_url":"https://github.com/zlinao/MinTL/blob/HEAD/damd_multiwoz/clean_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5b9d615f09edd9c8","mcp_get_code":{"code_sha256":"5b9d615f09edd9c8"}},{"arxiv_id":"2007.00398","paper":"/paper/docvqa-a-dataset-for-vqa-on-document-images","title":"DocVQA: A Dataset for VQA on Document Images","date":"2020-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anisha2102/docvqa","path":"create_dataset.py","file_url":"https://github.com/anisha2102/docvqa/blob/HEAD/create_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"58efca4ff69d4f1c","mcp_get_code":{"code_sha256":"58efca4ff69d4f1c"}},{"arxiv_id":"2006.06900","paper":"/paper/improving-gan-training-with-probability-ratio","title":"Improving GAN Training with Probability Ratio Clipping and Sample Reweighting","date":"2020-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Holmeswww/PPOGAN","path":"style_transfer/prepare_manual.py","file_url":"https://github.com/Holmeswww/PPOGAN/blob/HEAD/style_transfer/prepare_manual.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d8ab4cdbe05b528e","mcp_get_code":{"code_sha256":"d8ab4cdbe05b528e"}},{"arxiv_id":"1912.07875","paper":"/paper/libri-light-a-benchmark-for-asr-with-limited","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","date":"2019-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"20b4ccb36cf358ec","mcp_get_code":{"code_sha256":"20b4ccb36cf358ec"}},{"arxiv_id":"1909.09702","paper":"/paper/using-clinical-notes-with-time-series-data","title":"Using Clinical Notes with Time Series Data for ICU Management","date":"2019-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaggarwal/ClinicalNotesICU","path":"scripts/extract_notes.py","file_url":"https://github.com/kaggarwal/ClinicalNotesICU/blob/HEAD/scripts/extract_notes.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9c3d3e9f83b541b3","mcp_get_code":{"code_sha256":"9c3d3e9f83b541b3"}},{"arxiv_id":"1908.11049","paper":"/paper/multilingual-and-multi-aspect-hate-speech","title":"Multilingual and Multi-Aspect Hate Speech Analysis","date":"2019-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HKUST-KnowComp/MLMA_hate_speech","path":"annotated_data_processing.py","file_url":"https://github.com/HKUST-KnowComp/MLMA_hate_speech/blob/HEAD/annotated_data_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bfe8c53bc293a85f","mcp_get_code":{"code_sha256":"bfe8c53bc293a85f"}},{"arxiv_id":"1908.08313","paper":"/paper/auditing-radicalization-pathways-on-youtube","title":"Auditing Radicalization Pathways on YouTube","date":null,"month_inferred_from_arxiv_id":"2019-08","title_source":"archive","repo":"markledwich2/YouTubeNetworks","path":"DataScripts/video_entities.py","file_url":"https://github.com/markledwich2/YouTubeNetworks/blob/HEAD/DataScripts/video_entities.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"37c85cb881dd4a3e","mcp_get_code":{"code_sha256":"37c85cb881dd4a3e"}},{"arxiv_id":"1908.06809","paper":"/paper/style-transfer-for-texts-to-err-is-human-but","title":"Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites","date":"2019-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VAShibaev/text_style_transfer","path":"shiftedae/prepare_manual.py","file_url":"https://github.com/VAShibaev/text_style_transfer/blob/HEAD/shiftedae/prepare_manual.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d8ab4cdbe05b528e","mcp_get_code":{"code_sha256":"d8ab4cdbe05b528e"}},{"arxiv_id":"1907.04780","paper":"/paper/reqa-an-evaluation-for-end-to-end-answer","title":"ReQA: An Evaluation for End-to-End Answer Retrieval Models","date":"2019-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google/retrieval-qa-eval","path":"nq_to_squad.py","file_url":"https://github.com/google/retrieval-qa-eval/blob/HEAD/nq_to_squad.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0b0ded1135f95b47","mcp_get_code":{"code_sha256":"0b0ded1135f95b47"}},{"arxiv_id":"1906.06187","paper":"/paper/nlprolog-reasoning-with-weak-unification-for-1","title":"NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language","date":"2019-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leonweber/nlprolog","path":"preprocessing.py","file_url":"https://github.com/leonweber/nlprolog/blob/HEAD/preprocessing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5dc0130fdfd31748","mcp_get_code":{"code_sha256":"5dc0130fdfd31748"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jsantoso2/yelp-clone-ml-project","path":"app/flask-backend/firebase.py","file_url":"https://github.com/jsantoso2/yelp-clone-ml-project/blob/HEAD/app/flask-backend/firebase.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c7f933f28568cfaa","mcp_get_code":{"code_sha256":"c7f933f28568cfaa"}},{"arxiv_id":"1710.10361","paper":"/paper/deep-residual-learning-for-small-footprint","title":"Deep Residual Learning for Small-Footprint Keyword Spotting","date":"2017-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"magahub/honk","path":"utils/client.py","file_url":"https://github.com/magahub/honk/blob/HEAD/utils/client.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"259debd1d954e429","mcp_get_code":{"code_sha256":"259debd1d954e429"}},{"arxiv_id":"1705.09296","paper":"/paper/neural-models-for-documents-with-metadata","title":"Neural Models for Documents with Metadata","date":"2017-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dallascard/scholar","path":"preprocess_data.py","file_url":"https://github.com/dallascard/scholar/blob/HEAD/preprocess_data.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"128fcff9d8fad853","mcp_get_code":{"code_sha256":"128fcff9d8fad853"}},{"arxiv_id":"1612.03651","paper":"/paper/fasttextzip-compressing-text-classification","title":"FastText.zip: Compressing text classification models","date":"2016-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"currentsapi/fastlangid","path":"fastlangid/utils.py","file_url":"https://github.com/currentsapi/fastlangid/blob/HEAD/fastlangid/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cc21a5b05edde91f","mcp_get_code":{"code_sha256":"cc21a5b05edde91f"}},{"arxiv_id":"1512.02595","paper":"/paper/deep-speech-2-end-to-end-speech-recognition","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","date":"2015-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raraz15/DeepTurkish","path":"utilities/text_format.py","file_url":"https://github.com/raraz15/DeepTurkish/blob/HEAD/utilities/text_format.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1486f8a5a335a589","mcp_get_code":{"code_sha256":"1486f8a5a335a589"}},{"arxiv_id":"1409.3215","paper":"/paper/sequence-to-sequence-learning-with-neural","title":"Sequence to Sequence Learning with Neural Networks","date":"2014-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yash-nishaant/Seq2Seq-Chatbot","path":"chatbot.py","file_url":"https://github.com/yash-nishaant/Seq2Seq-Chatbot/blob/HEAD/chatbot.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8eaa3f3c2fa1ed5d","mcp_get_code":{"code_sha256":"8eaa3f3c2fa1ed5d"}},{"arxiv_id":"ijcai2024_0687","paper":null,"title":"arXiv:ijcai2024_0687","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zjunlp/FactCHD","path":"data_generate/text_data_generate.py","file_url":"https://github.com/zjunlp/FactCHD/blob/HEAD/data_generate/text_data_generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4f2d8c4335e3a017","mcp_get_code":{"code_sha256":"4f2d8c4335e3a017"}},{"arxiv_id":"2025.findings-acl.294","paper":null,"title":"arXiv:2025.findings-acl.294","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"kkahatapitiya/LangRepo","path":"util.py","file_url":"https://github.com/kkahatapitiya/LangRepo/blob/HEAD/util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d3cd8c8e5b09319c","mcp_get_code":{"code_sha256":"d3cd8c8e5b09319c"}},{"arxiv_id":"2023.findings-emnlp.730","paper":null,"title":"arXiv:2023.findings-emnlp.730","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"chufeiluo/legalhatespeech","path":"zeroshot/generate_hf.py","file_url":"https://github.com/chufeiluo/legalhatespeech/blob/HEAD/zeroshot/generate_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"03cdc84617a84fa0","mcp_get_code":{"code_sha256":"03cdc84617a84fa0"}},{"arxiv_id":"2023.findings-emnlp.384","paper":null,"title":"arXiv:2023.findings-emnlp.384","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"JHL-HUST/SparseMA","path":"dataloader/crisismmd_dataset.py","file_url":"https://github.com/JHL-HUST/SparseMA/blob/HEAD/dataloader/crisismmd_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b8be2ec62a547e2a","mcp_get_code":{"code_sha256":"b8be2ec62a547e2a"}},{"arxiv_id":"2023.findings-acl.416","paper":null,"title":"arXiv:2023.findings-acl.416","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"cxa-unique/IDEM","path":"collect_surrogate_train_data_nq.py","file_url":"https://github.com/cxa-unique/IDEM/blob/HEAD/collect_surrogate_train_data_nq.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"84895c4785f47e06","mcp_get_code":{"code_sha256":"84895c4785f47e06"}},{"arxiv_id":"2021.findings-emnlp.112","paper":null,"title":"arXiv:2021.findings-emnlp.112","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"bepoetree/MTTOD","path":"utils/clean_dataset.py","file_url":"https://github.com/bepoetree/MTTOD/blob/HEAD/utils/clean_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d7e520c85b455eb3","mcp_get_code":{"code_sha256":"d7e520c85b455eb3"}}]}