{"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/load-datasets","entry":"load_datasets","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":50,"n_papers_ran":25,"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":42,"n_samples_ran":16,"n_samples_fingerprinted":0,"n_places":53,"n_places_pointer_only":12,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":8,"ran_fixture":1,"ran":7,"unverified":26},"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":"2604.01170","paper":"/paper/arxiv-2604-01170","title":"Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"wzekai/ORCA","path":"code/calibrate.py","file_url":"https://github.com/wzekai/ORCA/blob/HEAD/code/calibrate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2f2303b2ebebeabe","mcp_get_code":{"code_sha256":"2f2303b2ebebeabe"}},{"arxiv_id":"2507.07101","paper":null,"title":"arXiv:2507.07101","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"martin-marek/batch-size","path":"finetuning/data.py","file_url":"https://github.com/martin-marek/batch-size/blob/HEAD/finetuning/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"93afdee7a791cc5c","mcp_get_code":{"code_sha256":"93afdee7a791cc5c"}},{"arxiv_id":"2412.09729","paper":"/paper/doubly-robust-conformalized-survival-analysis","title":"Doubly Robust Conformalized Survival Analysis with Right-Censored Data","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jaredleekatzman/DeepSurv","path":"deepsurv/utils.py","file_url":"https://github.com/jaredleekatzman/DeepSurv/blob/HEAD/deepsurv/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1124b42ac7ddd2a7","mcp_get_code":{"code_sha256":"1124b42ac7ddd2a7"}},{"arxiv_id":"2410.18798","paper":"/paper/distill-visual-chart-reasoning-ability-from","title":"Distill Visual Chart Reasoning Ability from LLMs to MLLMs","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hewei2001/reachqa","path":"swift_infer_dataset.py","file_url":"https://github.com/hewei2001/reachqa/blob/HEAD/swift_infer_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"93aa2fdc7356d575","mcp_get_code":{"code_sha256":"93aa2fdc7356d575"}},{"arxiv_id":"2410.03523","paper":"/paper/a-probabilistic-perspective-on-unlearning-and","title":"A Probabilistic Perspective on Unlearning and Alignment for Large Language Models","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yascho/probabilistic-unlearning","path":"unlearning/dataloader.py","file_url":"https://github.com/yascho/probabilistic-unlearning/blob/HEAD/unlearning/dataloader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6aaff75e95232315","mcp_get_code":{"code_sha256":"6aaff75e95232315"}},{"arxiv_id":"2407.21439","paper":"/paper/2407-21439","title":"MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training","date":"2024-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idea-finai/ragllava","path":"webqa_pipeline.py","file_url":"https://github.com/idea-finai/ragllava/blob/HEAD/webqa_pipeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"448b79f91dfb3d41","mcp_get_code":{"code_sha256":"448b79f91dfb3d41"}},{"arxiv_id":"2407.15847","paper":"/paper/llmmap-fingerprinting-for-large-language","title":"LLMmap: Fingerprinting For Large Language Models","date":"2024-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pasquini-dario/LLMmap","path":"LLMmap/dataset.py","file_url":"https://github.com/pasquini-dario/LLMmap/blob/HEAD/LLMmap/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fe509b80ffd62e01","mcp_get_code":{"code_sha256":"fe509b80ffd62e01"}},{"arxiv_id":"2407.01851","paper":"/paper/meerkat-audio-visual-large-language-model-for","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","date":"2024-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"schowdhury671/meerkat","path":"run_clm_llms.py","file_url":"https://github.com/schowdhury671/meerkat/blob/HEAD/run_clm_llms.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":"14a47047d9a6be42","mcp_get_code":{"code_sha256":"14a47047d9a6be42"}},{"arxiv_id":"2407.01851","paper":"/paper/meerkat-audio-visual-large-language-model-for","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","date":"2024-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"schowdhury671/meerkat","path":"run_clm_llms_inference.py","file_url":"https://github.com/schowdhury671/meerkat/blob/HEAD/run_clm_llms_inference.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":"5a4fa70c9f9c5fb7","mcp_get_code":{"code_sha256":"5a4fa70c9f9c5fb7"}},{"arxiv_id":"2406.06046","paper":"/paper/mates-model-aware-data-selection-for","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cxcscmu/MATES","path":"src/pretrain/pretrain.py","file_url":"https://github.com/cxcscmu/MATES/blob/HEAD/src/pretrain/pretrain.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3b5b9d1620b5eb91","mcp_get_code":{"code_sha256":"3b5b9d1620b5eb91"}},{"arxiv_id":"2405.16075","paper":"/paper/continuous-temporal-domain-generalization","title":"Continuous Temporal Domain Generalization","date":"2024-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zekun-Cai/Koodos","path":"util.py","file_url":"https://github.com/Zekun-Cai/Koodos/blob/HEAD/util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aac6bb4977f76c37","mcp_get_code":{"code_sha256":"aac6bb4977f76c37"}},{"arxiv_id":"2403.04706","paper":"/paper/common-7b-language-models-already-possess","title":"Common 7B Language Models Already Possess Strong Math Capabilities","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jerrywu-code/susgen","path":"utils/loadhf_data.py","file_url":"https://github.com/jerrywu-code/susgen/blob/HEAD/utils/loadhf_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"43fd4e86eac55a80","mcp_get_code":{"code_sha256":"43fd4e86eac55a80"}},{"arxiv_id":"2402.11867","paper":"/paper/lora-training-in-the-ntk-regime-has-no","title":"LoRA Training in the NTK Regime has No Spurious Local Minima","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uijeongjang/lora-ntk","path":"tools/generate_k_shot_data.py","file_url":"https://github.com/uijeongjang/lora-ntk/blob/HEAD/tools/generate_k_shot_data.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8e27652a29c8adcc","mcp_get_code":{"code_sha256":"8e27652a29c8adcc"}},{"arxiv_id":"2402.09739","paper":"/paper/qurating-selecting-high-quality-data-for","title":"QuRating: Selecting High-Quality Data for Training Language Models","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/qurating","path":"training/train_preference_model.py","file_url":"https://github.com/princeton-nlp/qurating/blob/HEAD/training/train_preference_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d0518a77df116eb2","mcp_get_code":{"code_sha256":"d0518a77df116eb2"}},{"arxiv_id":"2312.15820","paper":"/paper/webvln-vision-and-language-navigation-on","title":"WebVLN: Vision-and-Language Navigation on Websites","date":"2023-12-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"webvln/webvln","path":"r2r_src/utils.py","file_url":"https://github.com/webvln/webvln/blob/HEAD/r2r_src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b66b7866c664dff2","mcp_get_code":{"code_sha256":"b66b7866c664dff2"}},{"arxiv_id":"2312.08290","paper":"/paper/phendiff-revealing-invisible-phenotypes-with","title":"PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Images","date":"2023-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"warmongeringbeaver/phendiff","path":"src/utils_Img2Img.py","file_url":"https://github.com/warmongeringbeaver/phendiff/blob/HEAD/src/utils_Img2Img.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"15b4e8d47f5259c4","mcp_get_code":{"code_sha256":"15b4e8d47f5259c4"}},{"arxiv_id":"2311.09356","paper":"/paper/lepard-a-large-scale-dataset-of-judges-citing","title":"LePaRD: A Large-Scale Dataset of Judges Citing Precedents","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rmahari/lepard","path":"src/model/prepare_data.py","file_url":"https://github.com/rmahari/lepard/blob/HEAD/src/model/prepare_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8bd2020cd2bd688b","mcp_get_code":{"code_sha256":"8bd2020cd2bd688b"}},{"arxiv_id":"2310.16316","paper":"/paper/sum-of-parts-models-faithful-attributions-for","title":"Sum-of-Parts: Faithful Attributions for Groups of Features","date":"2023-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"debugml/sop","path":"src/sop/metrics/eraser_utils.py","file_url":"https://github.com/debugml/sop/blob/HEAD/src/sop/metrics/eraser_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e1878c4a3bf022ae","mcp_get_code":{"code_sha256":"e1878c4a3bf022ae"}},{"arxiv_id":"2309.13016","paper":"/paper/understanding-deep-gradient-leakage-via-1","title":"Understanding Deep Gradient Leakage via Inversion Influence Functions","date":"2023-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"illidanlab/inversion-influence-function","path":"baseline_utils.py","file_url":"https://github.com/illidanlab/inversion-influence-function/blob/HEAD/baseline_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5575a9343bef8b99","mcp_get_code":{"code_sha256":"5575a9343bef8b99"}},{"arxiv_id":"2309.05173","paper":"/paper/dept-decomposed-prompt-tuning-for-parameter","title":"DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning","date":"2023-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhengxiangshi/powerfulpromptft","path":"src/convert_to_pretrain_tapt_1.py","file_url":"https://github.com/zhengxiangshi/powerfulpromptft/blob/HEAD/src/convert_to_pretrain_tapt_1.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8e27652a29c8adcc","mcp_get_code":{"code_sha256":"8e27652a29c8adcc"}},{"arxiv_id":"2308.12033","paper":"/paper/prefer-prompt-ensemble-learning-via-feedback","title":"PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine","date":"2023-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zcrwind/prefer","path":"scripts/generate_k_shot_data.py","file_url":"https://github.com/zcrwind/prefer/blob/HEAD/scripts/generate_k_shot_data.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"635e168c990149fd","mcp_get_code":{"code_sha256":"635e168c990149fd"}},{"arxiv_id":"2308.04948","paper":"/paper/extrapolating-large-language-models-to-non","title":"Extrapolating Large Language Models to Non-English by Aligning Languages","date":"2023-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NJUNLP/x-LLM","path":"utils.py","file_url":"https://github.com/NJUNLP/x-LLM/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":"57bd6a217c768db9","mcp_get_code":{"code_sha256":"57bd6a217c768db9"}},{"arxiv_id":"2307.04967","paper":null,"title":"arXiv:2307.04967","date":null,"month_inferred_from_arxiv_id":"2023-07","title_source":null,"repo":"LSSTISSC/Tidalsaurus","path":"dataset_preparation.py","file_url":"https://github.com/LSSTISSC/Tidalsaurus/blob/HEAD/dataset_preparation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"750fffb100c623eb","mcp_get_code":{"code_sha256":"750fffb100c623eb"}},{"arxiv_id":"2307.00175","paper":"/paper/still-no-lie-detector-for-language-models","title":"Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks","date":"2023-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"c32cb2b828044b4d","mcp_get_code":{"code_sha256":"c32cb2b828044b4d"}},{"arxiv_id":"2305.01711","paper":"/paper/don-t-stop-pretraining-make-prompt-based-fine","title":"Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner","date":"2023-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhengxiangShi/PowerfulPromptFT","path":"src/convert_to_pretrain_tapt_1.py","file_url":"https://github.com/ZhengxiangShi/PowerfulPromptFT/blob/HEAD/src/convert_to_pretrain_tapt_1.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8e27652a29c8adcc","mcp_get_code":{"code_sha256":"8e27652a29c8adcc"}},{"arxiv_id":"2304.13734","paper":"/paper/the-internal-state-of-an-llm-knows-when-its","title":"The Internal State of an LLM Knows When It's Lying","date":"2023-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"balevinstein/probes","path":"TrainProbes.py","file_url":"https://github.com/balevinstein/probes/blob/HEAD/TrainProbes.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c32cb2b828044b4d","mcp_get_code":{"code_sha256":"c32cb2b828044b4d"}},{"arxiv_id":"2301.01456","paper":"/paper/audio-visual-efficient-conformer-for-robust","title":"Audio-Visual Efficient Conformer for Robust Speech Recognition","date":"2023-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"burchim/avec","path":"functions.py","file_url":"https://github.com/burchim/avec/blob/HEAD/functions.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":"285dd2816d300b3d","mcp_get_code":{"code_sha256":"285dd2816d300b3d"}},{"arxiv_id":"2212.09257","paper":"/paper/promptboosting-black-box-text-classification","title":"PromptBoosting: Black-Box Text Classification with Ten Forward Passes","date":"2022-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsb-nlp-chang/promptboosting","path":"scripts/generate_k_shot_data.py","file_url":"https://github.com/ucsb-nlp-chang/promptboosting/blob/HEAD/scripts/generate_k_shot_data.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aa8835750b7967cd","mcp_get_code":{"code_sha256":"aa8835750b7967cd"}},{"arxiv_id":"2211.03044","paper":"/paper/tuning-language-models-as-training-data","title":"Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning","date":"2022-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yumeng5/fewgen","path":"utils/gen_k_shot.py","file_url":"https://github.com/yumeng5/fewgen/blob/HEAD/utils/gen_k_shot.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8e27652a29c8adcc","mcp_get_code":{"code_sha256":"8e27652a29c8adcc"}},{"arxiv_id":"2210.02748","paper":"/paper/clad-a-contrastive-learning-based-approach","title":"CLAD: A Contrastive Learning based Approach for Background Debiasing","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangke97/clad","path":"src/dataloader.py","file_url":"https://github.com/wangke97/clad/blob/HEAD/src/dataloader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b92206840d06acc7","mcp_get_code":{"code_sha256":"b92206840d06acc7"}},{"arxiv_id":"2206.06340","paper":"/paper/snes-learning-probably-symmetric-neural","title":"SNeS: Learning Probably Symmetric Neural Surfaces from Incomplete Data","date":"2022-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eldar/snes","path":"models/factory.py","file_url":"https://github.com/eldar/snes/blob/HEAD/models/factory.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d7d5462dbe2c1f44","mcp_get_code":{"code_sha256":"d7d5462dbe2c1f44"}},{"arxiv_id":"2204.06239","paper":"/paper/can-question-rewriting-help-conversational","title":"Can Question Rewriting Help Conversational Question Answering?","date":"2022-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hltchkust/cqr4cqa","path":"src/data_utils/convqa_data_utils.py","file_url":"https://github.com/hltchkust/cqr4cqa/blob/HEAD/src/data_utils/convqa_data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c1804882d56dfe15","mcp_get_code":{"code_sha256":"c1804882d56dfe15"}},{"arxiv_id":"2203.13838","paper":"/paper/analyzing-generalization-of-vision-and","title":"Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas","date":"2022-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raphael-sch/map2seq_vln","path":"vln/utils.py","file_url":"https://github.com/raphael-sch/map2seq_vln/blob/HEAD/vln/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":"06e4c15a96bcb6fb","mcp_get_code":{"code_sha256":"06e4c15a96bcb6fb"}},{"arxiv_id":"2203.11591","paper":"/paper/hop-history-and-order-aware-pre-training-for","title":"HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation","date":"2022-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yanyuanqiao/hop-vln","path":"tasks/pretrain/utils.py","file_url":"https://github.com/yanyuanqiao/hop-vln/blob/HEAD/tasks/pretrain/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bd7ea3e7a698a3e0","mcp_get_code":{"code_sha256":"bd7ea3e7a698a3e0"}},{"arxiv_id":"2202.00155","paper":"/paper/fortuitous-forgetting-in-connectionist-1","title":"Fortuitous Forgetting in Connectionist Networks","date":"2022-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hlml/fortuitous_forgetting","path":"targeted_forgetting/mixed_group_training.py","file_url":"https://github.com/hlml/fortuitous_forgetting/blob/HEAD/targeted_forgetting/mixed_group_training.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c3d99cad036fdd02","mcp_get_code":{"code_sha256":"c3d99cad036fdd02"}},{"arxiv_id":"2112.08348","paper":"/paper/prompt-waywardness-the-curious-case-of","title":"Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts","date":"2021-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alrope123/prompt-waywardness","path":"generate_k_shot_data.py","file_url":"https://github.com/alrope123/prompt-waywardness/blob/HEAD/generate_k_shot_data.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5c4435a7bbecdc7","mcp_get_code":{"code_sha256":"c5c4435a7bbecdc7"}},{"arxiv_id":"2111.09453","paper":"/paper/robertuito-a-pre-trained-language-model-for","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","date":"2021-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pysentimiento/robertuito","path":"finetune_vs_scratch/context_hate.py","file_url":"https://github.com/pysentimiento/robertuito/blob/HEAD/finetune_vs_scratch/context_hate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc949dfaed31c76b","mcp_get_code":{"code_sha256":"cc949dfaed31c76b"}},{"arxiv_id":"2111.09453","paper":"/paper/robertuito-a-pre-trained-language-model-for","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","date":"2021-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pysentimiento/robertuito","path":"finetune_vs_scratch/irony.py","file_url":"https://github.com/pysentimiento/robertuito/blob/HEAD/finetune_vs_scratch/irony.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"968608fa8e0a82dc","mcp_get_code":{"code_sha256":"968608fa8e0a82dc"}},{"arxiv_id":"2108.04106","paper":"/paper/noisy-channel-language-model-prompting-for","title":"Noisy Channel Language Model Prompting for Few-Shot Text Classification","date":"2021-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shmsw25/Channel-LM-Prompting","path":"generate_k_shot_data.py","file_url":"https://github.com/shmsw25/Channel-LM-Prompting/blob/HEAD/generate_k_shot_data.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8e27652a29c8adcc","mcp_get_code":{"code_sha256":"8e27652a29c8adcc"}},{"arxiv_id":"2107.07201","paper":"/paper/neighbor-view-enhanced-model-for-vision-and","title":"Neighbor-view Enhanced Model for Vision and Language Navigation","date":"2021-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MarSaKi/NvEM","path":"r2r_src/utils.py","file_url":"https://github.com/MarSaKi/NvEM/blob/HEAD/r2r_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":"1d9c8c3cd78345c4","mcp_get_code":{"code_sha256":"1d9c8c3cd78345c4"}},{"arxiv_id":"2106.03048","paper":"/paper/how-did-this-get-funded-automatically","title":"How Did This Get Funded?! Automatically Identifying Quirky Scientific Achievements","date":"2021-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nadavborenstein/Iggy","path":"model_training/MLP_train.py","file_url":"https://github.com/nadavborenstein/Iggy/blob/HEAD/model_training/MLP_train.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":"91cd24d73916ca4e","mcp_get_code":{"code_sha256":"91cd24d73916ca4e"}},{"arxiv_id":"2105.11589","paper":"/paper/visitron-visual-semantics-aligned","title":"VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator","date":"2021-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alexa/visitron","path":"scripts/generate_pretraining_data.py","file_url":"https://github.com/alexa/visitron/blob/HEAD/scripts/generate_pretraining_data.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT-0","inline_ok":true,"code_sha256_prefix":"1f1fb7ef6c462cab","mcp_get_code":{"code_sha256":"1f1fb7ef6c462cab"}},{"arxiv_id":"2005.00115","paper":"/paper/learning-to-faithfully-rationalize-by","title":"Learning to Faithfully Rationalize by Construction","date":"2020-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"successar/FRESH","path":"Datasets/utils.py","file_url":"https://github.com/successar/FRESH/blob/HEAD/Datasets/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e1878c4a3bf022ae","mcp_get_code":{"code_sha256":"e1878c4a3bf022ae"}},{"arxiv_id":"1911.12377","paper":"/paper/perceive-transform-and-act-multi-modal","title":"Multimodal Attention Networks for Low-Level Vision-and-Language Navigation","date":"2019-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aimagelab/perceive-transform-and-act","path":"tasks/R2R/utils.py","file_url":"https://github.com/aimagelab/perceive-transform-and-act/blob/HEAD/tasks/R2R/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c954fa1f33ae8634","mcp_get_code":{"code_sha256":"c954fa1f33ae8634"}},{"arxiv_id":"1911.03429","paper":"/paper/eraser-a-benchmark-to-evaluate-rationalized","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","date":"2019-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jayded/eraserbenchmark","path":"rationale_benchmark/utils.py","file_url":"https://github.com/jayded/eraserbenchmark/blob/HEAD/rationale_benchmark/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e1878c4a3bf022ae","mcp_get_code":{"code_sha256":"e1878c4a3bf022ae"}},{"arxiv_id":"1904.04195","paper":"/paper/learning-to-navigate-unseen-environments-back","title":"Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout","date":"2019-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"airsplay/R2R-EnvDrop","path":"r2r_src/utils.py","file_url":"https://github.com/airsplay/R2R-EnvDrop/blob/HEAD/r2r_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":"1d9c8c3cd78345c4","mcp_get_code":{"code_sha256":"1d9c8c3cd78345c4"}},{"arxiv_id":"1903.01602","paper":"/paper/the-regretful-agent-heuristic-aided","title":"The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation","date":"2019-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CAVED123/regretful-agent","path":"tasks/R2R-pano/utils.py","file_url":"https://github.com/CAVED123/regretful-agent/blob/HEAD/tasks/R2R-pano/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"be2e80a5268aabb2","mcp_get_code":{"code_sha256":"be2e80a5268aabb2"}},{"arxiv_id":"1903.01602","paper":"/paper/the-regretful-agent-heuristic-aided","title":"The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation","date":"2019-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cacosandon/are-you-looking","path":"tasks/R2R-pano/utils.py","file_url":"https://github.com/cacosandon/are-you-looking/blob/HEAD/tasks/R2R-pano/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"247ba71d3fffa065","mcp_get_code":{"code_sha256":"247ba71d3fffa065"}},{"arxiv_id":"1901.03035","paper":"/paper/self-monitoring-navigation-agent-via","title":"Self-Monitoring Navigation Agent via Auxiliary Progress Estimation","date":"2019-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chihyaoma/selfmonitoring-agent","path":"tasks/R2R-pano/utils.py","file_url":"https://github.com/chihyaoma/selfmonitoring-agent/blob/HEAD/tasks/R2R-pano/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"be2e80a5268aabb2","mcp_get_code":{"code_sha256":"be2e80a5268aabb2"}},{"arxiv_id":"1803.08823","paper":"/paper/a-high-bias-low-variance-introduction-to","title":"A high-bias, low-variance introduction to Machine Learning for physicists","date":"2018-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alexandreday/fast_density_clustering","path":"benchmarks/benchmark_quality.py","file_url":"https://github.com/alexandreday/fast_density_clustering/blob/HEAD/benchmarks/benchmark_quality.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"390c2f6cdaafd18b","mcp_get_code":{"code_sha256":"390c2f6cdaafd18b"}},{"arxiv_id":"1703.09452","paper":"/paper/segan-speech-enhancement-generative","title":"SEGAN: Speech Enhancement Generative Adversarial Network","date":"2017-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haozh7109/SEGAN-TensorFlow2","path":"Inference_singleShot.py","file_url":"https://github.com/haozh7109/SEGAN-TensorFlow2/blob/HEAD/Inference_singleShot.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":"69a97611e4cfefac","mcp_get_code":{"code_sha256":"69a97611e4cfefac"}},{"arxiv_id":"2024.findings-naacl.294","paper":null,"title":"arXiv:2024.findings-naacl.294","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"balevinstein/Probes","path":"TrainProbes.py","file_url":"https://github.com/balevinstein/Probes/blob/HEAD/TrainProbes.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c32cb2b828044b4d","mcp_get_code":{"code_sha256":"c32cb2b828044b4d"}},{"arxiv_id":"2024.findings-acl.307","paper":null,"title":"arXiv:2024.findings-acl.307","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wj210/NLI_ETP","path":"preprocess/eraser_utils.py","file_url":"https://github.com/wj210/NLI_ETP/blob/HEAD/preprocess/eraser_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e1878c4a3bf022ae","mcp_get_code":{"code_sha256":"e1878c4a3bf022ae"}}]}