{"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/build-dataloader","entry":"build_dataloader","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":19,"n_papers_ran":4,"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":17,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":19,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":14},"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":"2605.13475","paper":"/paper/arxiv-2605-13475","title":"FedHPro: Federated Hyper-Prototype Learning via Gradient Matching","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"mala-lab/FedHPro","path":"main_run.py","file_url":"https://github.com/mala-lab/FedHPro/blob/HEAD/main_run.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b57b5bd7c4b8f301","mcp_get_code":{"code_sha256":"b57b5bd7c4b8f301"}},{"arxiv_id":"2601.05776","paper":"/paper/arxiv-2601-05776","title":"One Script Instead of Hundreds? On Pretraining Romanized Encoder Language Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"AnswerDotAI/ModernBERT","path":"src/convert_dataset.py","file_url":"https://github.com/AnswerDotAI/ModernBERT/blob/HEAD/src/convert_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":"eb04bca046263ad3","mcp_get_code":{"code_sha256":"eb04bca046263ad3"}},{"arxiv_id":"2508.17817","paper":"/paper/arxiv-2508-17817","title":"TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaboration","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"Meiqi-Gong/TemCoCo","path":"dataset.py","file_url":"https://github.com/Meiqi-Gong/TemCoCo/blob/HEAD/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3acc39c2c638ec21","mcp_get_code":{"code_sha256":"3acc39c2c638ec21"}},{"arxiv_id":"2502.17421","paper":"/paper/longspec-long-context-speculative-decoding","title":"LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification","date":"2025-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/longspec","path":"longspec/train/general_util/evaluator.py","file_url":"https://github.com/sail-sg/longspec/blob/HEAD/longspec/train/general_util/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d0a17385afef041","mcp_get_code":{"code_sha256":"8d0a17385afef041"}},{"arxiv_id":"2409.01236","paper":"/paper/spatial-aware-conformal-prediction-for","title":"Spatial-Aware Conformal Prediction for Trustworthy Hyperspectral Image Classification","date":"2024-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"j4ckliu/sacp","path":"dataset.py","file_url":"https://github.com/j4ckliu/sacp/blob/HEAD/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bdbf26ec81afb90c","mcp_get_code":{"code_sha256":"bdbf26ec81afb90c"}},{"arxiv_id":"2407.09941","paper":"/paper/hydra-bidirectional-state-space-models","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","date":"2024-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"goombalab/hydra","path":"hydra/bert/src/convert_dataset.py","file_url":"https://github.com/goombalab/hydra/blob/HEAD/hydra/bert/src/convert_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb04bca046263ad3","mcp_get_code":{"code_sha256":"eb04bca046263ad3"}},{"arxiv_id":"2407.00891","paper":"/paper/zeroddi-a-zero-shot-drug-drug-interaction","title":"ZeroDDI: A Zero-Shot Drug-Drug Interaction Event Prediction Method with Semantic Enhanced Learning and Dual-Modal Uniform Alignment","date":"2024-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wzy-Sarah/ZeroDDI","path":"datasets/builder.py","file_url":"https://github.com/wzy-Sarah/ZeroDDI/blob/HEAD/datasets/builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0e5a791f0c815ccc","mcp_get_code":{"code_sha256":"0e5a791f0c815ccc"}},{"arxiv_id":"2403.09977","paper":"/paper/efficientvmamba-atrous-selective-scan-for","title":"EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba","date":"2024-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"terrypei/efficientvmamba","path":"classification/lib/dataset/builder.py","file_url":"https://github.com/terrypei/efficientvmamba/blob/HEAD/classification/lib/dataset/builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c09346f52c0603a3","mcp_get_code":{"code_sha256":"c09346f52c0603a3"}},{"arxiv_id":"2312.02010","paper":"/paper/towards-learning-a-generalist-model-for","title":"Towards Learning a Generalist Model for Embodied Navigation","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lavi-lab/navillm","path":"tasks/loaders.py","file_url":"https://github.com/lavi-lab/navillm/blob/HEAD/tasks/loaders.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dd2ac0ab9c587094","mcp_get_code":{"code_sha256":"dd2ac0ab9c587094"}},{"arxiv_id":"2312.01502","paper":"/paper/normed-spaces-for-graph-embedding","title":"Normed Spaces for Graph Embedding","date":"2023-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andyweizhao/graphs-normed-spaces","path":"run_lp_gnn.py","file_url":"https://github.com/andyweizhao/graphs-normed-spaces/blob/HEAD/run_lp_gnn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"91406925210078fc","mcp_get_code":{"code_sha256":"91406925210078fc"}},{"arxiv_id":"2311.11202","paper":"/paper/unmasking-and-improving-data-credibility-a","title":"Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models","date":"2023-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Docta-ai/docta","path":"docta/core/preprocess.py","file_url":"https://github.com/Docta-ai/docta/blob/HEAD/docta/core/preprocess.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"89343e9ce4529f54","mcp_get_code":{"code_sha256":"89343e9ce4529f54"}},{"arxiv_id":"2301.08810","paper":"/paper/phoneme-level-bert-for-enhanced-prosody-of","title":"Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions","date":"2023-01-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yl4579/pl-bert","path":"simple_loader.py","file_url":"https://github.com/yl4579/pl-bert/blob/HEAD/simple_loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"164d730b65626a89","mcp_get_code":{"code_sha256":"164d730b65626a89"}},{"arxiv_id":"2207.07267","paper":"/paper/scalenet-searching-for-the-model-to-scale","title":"ScaleNet: Searching for the Model to Scale","date":"2022-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luminolx/ScaleNet","path":"core/dataset/build_dataloader.py","file_url":"https://github.com/luminolx/ScaleNet/blob/HEAD/core/dataset/build_dataloader.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":"d724b53fbfb7a4e4","mcp_get_code":{"code_sha256":"d724b53fbfb7a4e4"}},{"arxiv_id":"2206.01204","paper":"/paper/siamese-image-modeling-for-self-supervised","title":"Siamese Image Modeling for Self-Supervised Vision Representation Learning","date":"2022-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fundamentalvision/unigrad","path":"project/dataloader.py","file_url":"https://github.com/fundamentalvision/unigrad/blob/HEAD/project/dataloader.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":"28f62e0c183cc93f","mcp_get_code":{"code_sha256":"28f62e0c183cc93f"}},{"arxiv_id":"2103.15808","paper":"/paper/cvt-introducing-convolutions-to-vision","title":"CvT: Introducing Convolutions to Vision Transformers","date":"2021-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/CvT","path":"lib/dataset/build.py","file_url":"https://github.com/microsoft/CvT/blob/HEAD/lib/dataset/build.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"51dc0ff05a226bd7","mcp_get_code":{"code_sha256":"51dc0ff05a226bd7"}},{"arxiv_id":"1911.10375","paper":"/paper/region-normalization-for-image-inpainting","title":"Region Normalization for Image Inpainting","date":"2019-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"geekyutao/RN","path":"dataset.py","file_url":"https://github.com/geekyutao/RN/blob/HEAD/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"811f2b8c51d59ae6","mcp_get_code":{"code_sha256":"811f2b8c51d59ae6"}},{"arxiv_id":"1802.06455","paper":"/paper/bayesian-uncertainty-estimation-for-batch","title":"Bayesian Uncertainty Estimation for Batch Normalized Deep Networks","date":"2018-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Glutamat42/mcbn-pytorch","path":"cifar_dataloader.py","file_url":"https://github.com/Glutamat42/mcbn-pytorch/blob/HEAD/cifar_dataloader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e54f691055f3d284","mcp_get_code":{"code_sha256":"e54f691055f3d284"}},{"arxiv_id":"Zheng_Towards_Learning_a_Generalist_Model_for_Embodied_Navigation_CVPR_2024_paper","paper":null,"title":"arXiv:Zheng_Towards_Learning_a_Generalist_Model_for_Embodied_Navigation_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LaVi-Lab/NaviLLM","path":"tasks/loaders.py","file_url":"https://github.com/LaVi-Lab/NaviLLM/blob/HEAD/tasks/loaders.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dd2ac0ab9c587094","mcp_get_code":{"code_sha256":"dd2ac0ab9c587094"}},{"arxiv_id":"Li_FPEM_Face_Prior_Enhanced_Facial_Attractiveness_Prediction_for_Live_Videos_ICCV_2025_paper","paper":null,"title":"arXiv:Li_FPEM_Face_Prior_Enhanced_Facial_Attractiveness_Prediction_for_Live_Videos_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Estella-LH/FPEM","path":"dataloader/dataloader.py","file_url":"https://github.com/Estella-LH/FPEM/blob/HEAD/dataloader/dataloader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8daf3d3b33df8a23","mcp_get_code":{"code_sha256":"8daf3d3b33df8a23"}}]}