{"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/get-loaders","entry":"get_loaders","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":51,"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":51,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":54,"n_places_pointer_only":16,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":47},"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":"2606.25347","paper":"/paper/arxiv-2606-25347","title":"Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"HXuSz11/GATF_ECCV2026","path":"src/datasets/data_loader.py","file_url":"https://github.com/HXuSz11/GATF_ECCV2026/blob/HEAD/src/datasets/data_loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d80980af3f736cda","mcp_get_code":{"code_sha256":"d80980af3f736cda"}},{"arxiv_id":"2603.04340","paper":"/paper/arxiv-2603-04340","title":"Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"vlbthambawita/SynCMRI","path":"mask_generation/data_loading.py","file_url":"https://github.com/vlbthambawita/SynCMRI/blob/HEAD/mask_generation/data_loading.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4dce07ff377af4b1","mcp_get_code":{"code_sha256":"4dce07ff377af4b1"}},{"arxiv_id":"2601.06787","paper":"/paper/arxiv-2601-06787","title":"Garbage Attention in Large Language Models: <BOS> Sink Heads and Sink-aware Pruning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"CASIA-LMC-Lab/FLAP","path":"lib/prune.py","file_url":"https://github.com/CASIA-LMC-Lab/FLAP/blob/HEAD/lib/prune.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":"21ef6425a9e8b029","mcp_get_code":{"code_sha256":"21ef6425a9e8b029"}},{"arxiv_id":"2511.04805","paper":"/paper/arxiv-2511-04805","title":"PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Fine-Grained Expert Merging and Bit-packed Inference","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"Supercomputing-System-AI-Lab/PuzzleMoE","path":"puzzlemoe/utils/merge_experts_function.py","file_url":"https://github.com/Supercomputing-System-AI-Lab/PuzzleMoE/blob/HEAD/puzzlemoe/utils/merge_experts_function.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":"3770bd0cab131a2b","mcp_get_code":{"code_sha256":"3770bd0cab131a2b"}},{"arxiv_id":"2510.01650","paper":"/paper/arxiv-2510-01650","title":"The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"log-postech/elsa","path":"lib/data.py","file_url":"https://github.com/log-postech/elsa/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2c3c36c497f9fe0","mcp_get_code":{"code_sha256":"e2c3c36c497f9fe0"}},{"arxiv_id":"2507.23279","paper":null,"title":"arXiv:2507.23279","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"ZunhaiSu/Super-Experts-Profilling","path":"data_utils.py","file_url":"https://github.com/ZunhaiSu/Super-Experts-Profilling/blob/HEAD/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b74616b7db8928f","mcp_get_code":{"code_sha256":"4b74616b7db8928f"}},{"arxiv_id":"2506.09351","paper":null,"title":"arXiv:2506.09351","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"yuchenblah/DIVE","path":"lib/evaldata.py","file_url":"https://github.com/yuchenblah/DIVE/blob/HEAD/lib/evaldata.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":"7e68b286b9a062c5","mcp_get_code":{"code_sha256":"7e68b286b9a062c5"}},{"arxiv_id":"2506.06866","paper":"/paper/safe-finding-sparse-and-flat-minima-to","title":"SAFE: Finding Sparse and Flat Minima to Improve Pruning","date":"2025-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LOG-postech/safe-torch","path":"language/lib/prune.py","file_url":"https://github.com/LOG-postech/safe-torch/blob/HEAD/language/lib/prune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d6ccfa34fac6df39","mcp_get_code":{"code_sha256":"d6ccfa34fac6df39"}},{"arxiv_id":"2505.23807","paper":"/paper/dlp-dynamic-layerwise-pruning-in-large","title":"DLP: Dynamic Layerwise Pruning in Large Language Models","date":"2025-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ironartisan/dlp","path":"lib/prune.py","file_url":"https://github.com/ironartisan/dlp/blob/HEAD/lib/prune.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":"2eaf81f9b2452228","mcp_get_code":{"code_sha256":"2eaf81f9b2452228"}},{"arxiv_id":"2411.10606","paper":"/paper/amoeballm-constructing-any-shape-large","title":"AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment","date":"2024-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GATECH-EIC/AmoebaLLM","path":"width_shrink/data.py","file_url":"https://github.com/GATECH-EIC/AmoebaLLM/blob/HEAD/width_shrink/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"16994008353af958","mcp_get_code":{"code_sha256":"16994008353af958"}},{"arxiv_id":"2411.02926","paper":"/paper/privacy-preserving-graph-based-machine","title":"Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fabecode/GraphML-FHE","path":"gnn_fhe_pipeline/train_util.py","file_url":"https://github.com/fabecode/GraphML-FHE/blob/HEAD/gnn_fhe_pipeline/train_util.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":"7a4b3977f9af49ca","mcp_get_code":{"code_sha256":"7a4b3977f9af49ca"}},{"arxiv_id":"2410.21352","paper":"/paper/llmcbench-benchmarking-large-language-model","title":"LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AboveParadise/LLMCBench","path":"evaluate_ppl.py","file_url":"https://github.com/AboveParadise/LLMCBench/blob/HEAD/evaluate_ppl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3f1d2bce76741bc0","mcp_get_code":{"code_sha256":"3f1d2bce76741bc0"}},{"arxiv_id":"2410.17509","paper":"/paper/wagle-strategic-weight-attribution-for","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OPTML-Group/WAGLE","path":"src/dataset/dataset.py","file_url":"https://github.com/OPTML-Group/WAGLE/blob/HEAD/src/dataset/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"16994008353af958","mcp_get_code":{"code_sha256":"16994008353af958"}},{"arxiv_id":"2410.09344","paper":"/paper/dare-the-extreme-revisiting-delta-parameter","title":"DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vengdeng/darex","path":"utils/getwx.py","file_url":"https://github.com/vengdeng/darex/blob/HEAD/utils/getwx.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a54651cc8454cb77","mcp_get_code":{"code_sha256":"a54651cc8454cb77"}},{"arxiv_id":"2409.17481","paper":"/paper/maskllm-learnable-semi-structured-sparsity","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/MaskLLM","path":"eval_llama_ppl.py","file_url":"https://github.com/NVlabs/MaskLLM/blob/HEAD/eval_llama_ppl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a6cf7a5e8f29a402","mcp_get_code":{"code_sha256":"a6cf7a5e8f29a402"}},{"arxiv_id":"2407.06483","paper":"/paper/composable-interventions-for-language-models","title":"Composable Interventions for Language Models","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hartvigsen-group/composable-interventions","path":"sparsellm/lib/data.py","file_url":"https://github.com/hartvigsen-group/composable-interventions/blob/HEAD/sparsellm/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d280312c1c709fbb","mcp_get_code":{"code_sha256":"d280312c1c709fbb"}},{"arxiv_id":"2406.02924","paper":"/paper/pruner-zero-evolving-symbolic-pruning-metric","title":"Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pprp/pruner-zero","path":"lib/data.py","file_url":"https://github.com/pprp/pruner-zero/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6ec51bc8a06ee71","mcp_get_code":{"code_sha256":"b6ec51bc8a06ee71"}},{"arxiv_id":"2406.02924","paper":"/paper/pruner-zero-evolving-symbolic-pruning-metric","title":"Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pprp/pruner-zero","path":"lib/gradient_computation.py","file_url":"https://github.com/pprp/pruner-zero/blob/HEAD/lib/gradient_computation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35a6bbc8f64f77b7","mcp_get_code":{"code_sha256":"35a6bbc8f64f77b7"}},{"arxiv_id":"2405.16262","paper":"/paper/layer-aware-analysis-of-catastrophic","title":"Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency","date":"2024-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmllab/2024_ICML_LAP","path":"CIFAR10/utils.py","file_url":"https://github.com/tmllab/2024_ICML_LAP/blob/HEAD/CIFAR10/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"816caa026adecbe6","mcp_get_code":{"code_sha256":"816caa026adecbe6"}},{"arxiv_id":"2405.09629","paper":"/paper/calodream-detector-response-emulation-via","title":"CaloDREAM -- Detector Response Emulation via Attentive flow Matching","date":null,"month_inferred_from_arxiv_id":"2024-05","title_source":"archive","repo":"heidelberg-hepml/calo_dreamer","path":"src/datasets.py","file_url":"https://github.com/heidelberg-hepml/calo_dreamer/blob/HEAD/src/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"456a769435ec2115","mcp_get_code":{"code_sha256":"456a769435ec2115"}},{"arxiv_id":"2404.18239","paper":"/paper/soul-unlocking-the-power-of-second-order","title":"SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning","date":"2024-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"optml-group/soul","path":"src/dataset/dataset.py","file_url":"https://github.com/optml-group/soul/blob/HEAD/src/dataset/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"16994008353af958","mcp_get_code":{"code_sha256":"16994008353af958"}},{"arxiv_id":"2404.08168","paper":"/paper/conformal-prediction-via-regression-as","title":"Conformal Prediction via Regression-as-Classification","date":"2024-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EtashGuha/R2CCP","path":"R2CCP/data.py","file_url":"https://github.com/EtashGuha/R2CCP/blob/HEAD/R2CCP/data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba314ff194ec3aa8","mcp_get_code":{"code_sha256":"ba314ff194ec3aa8"}},{"arxiv_id":"2403.02580","paper":"/paper/what-do-we-learn-from-inverting-clip-models","title":"What do we learn from inverting CLIP models?","date":"2024-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hamidkazemi22/clipinversion","path":"helpers/utils.py","file_url":"https://github.com/hamidkazemi22/clipinversion/blob/HEAD/helpers/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"52c6392743c5bd39","mcp_get_code":{"code_sha256":"52c6392743c5bd39"}},{"arxiv_id":"2402.11917","paper":"/paper/a-mechanistic-analysis-of-a-transformer","title":"A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abhay-sheshadri/backward-chaining-circuits","path":"src/utils.py","file_url":"https://github.com/abhay-sheshadri/backward-chaining-circuits/blob/HEAD/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":"acd6a741f6a7a07f","mcp_get_code":{"code_sha256":"acd6a741f6a7a07f"}},{"arxiv_id":"2402.02834","paper":"/paper/shortened-llama-a-simple-depth-pruning-for","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nota-netspresso/shortened-llm","path":"src/dataset.py","file_url":"https://github.com/nota-netspresso/shortened-llm/blob/HEAD/src/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4ef386ce30344069","mcp_get_code":{"code_sha256":"4ef386ce30344069"}},{"arxiv_id":"2401.02938","paper":"/paper/fast-and-optimal-weight-update-for-pruned","title":"Fast and Effective Weight Update for Pruned Large Language Models","date":"2024-01-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fmfi-compbio/admm-pruning","path":"lib/data.py","file_url":"https://github.com/fmfi-compbio/admm-pruning/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d0b76a86bef8bcaa","mcp_get_code":{"code_sha256":"d0b76a86bef8bcaa"}},{"arxiv_id":"2311.04902","paper":"/paper/beyond-size-how-gradients-shape-pruning","title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models","date":"2023-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rocktimjyotidas/gblm-pruner","path":"lib/data.py","file_url":"https://github.com/rocktimjyotidas/gblm-pruner/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"938021b9c285abea","mcp_get_code":{"code_sha256":"938021b9c285abea"}},{"arxiv_id":"2310.17468","paper":"/paper/cross-modal-active-complementary-learning-1","title":"Cross-modal Active Complementary Learning with Self-refining Correspondence","date":"2023-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QinYang79/CRCL","path":"CRCL_NeurIPS23/data.py","file_url":"https://github.com/QinYang79/CRCL/blob/HEAD/CRCL_NeurIPS23/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c2c0455d61babb92","mcp_get_code":{"code_sha256":"c2c0455d61babb92"}},{"arxiv_id":"2310.16640","paper":"/paper/emoclip-a-vision-language-method-for-zero","title":"EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition","date":"2023-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nickyfot/emoclip","path":"DataLoaders/get_loader.py","file_url":"https://github.com/nickyfot/emoclip/blob/HEAD/DataLoaders/get_loader.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":"368b5461230215d6","mcp_get_code":{"code_sha256":"368b5461230215d6"}},{"arxiv_id":"2310.08915","paper":"/paper/dynamic-sparse-no-training-training-free-fine","title":"Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs","date":"2023-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zyxxmu/dsnot","path":"lib/prune.py","file_url":"https://github.com/zyxxmu/dsnot/blob/HEAD/lib/prune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2551834c320a844b","mcp_get_code":{"code_sha256":"2551834c320a844b"}},{"arxiv_id":"2310.05175","paper":"/paper/outlier-weighed-layerwise-sparsity-owl-a","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","date":"2023-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luuyin/owl","path":"lib/prune_all.py","file_url":"https://github.com/luuyin/owl/blob/HEAD/lib/prune_all.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d4b7e939c6fa46b","mcp_get_code":{"code_sha256":"2d4b7e939c6fa46b"}},{"arxiv_id":"2310.01382","paper":"/paper/compressing-llms-the-truth-is-rarely-pure-and","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/llm-kick","path":"GPTQ_experiment/lib/data.py","file_url":"https://github.com/VITA-Group/llm-kick/blob/HEAD/GPTQ_experiment/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e871931ae9a838f9","mcp_get_code":{"code_sha256":"e871931ae9a838f9"}},{"arxiv_id":"2309.17430","paper":"/paper/facts-first-amplify-correlations-and-then-1","title":"FACTS: First Amplify Correlations and Then Slice to Discover Bias","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yvsriram/FACTS","path":"utils/datasets.py","file_url":"https://github.com/yvsriram/FACTS/blob/HEAD/utils/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9d167bde46e08be","mcp_get_code":{"code_sha256":"f9d167bde46e08be"}},{"arxiv_id":"2306.11695","paper":"/paper/a-simple-and-effective-pruning-approach-for","title":"A Simple and Effective Pruning Approach for Large Language Models","date":"2023-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"crystaleye42/eval-safety","path":"lib/prune.py","file_url":"https://github.com/crystaleye42/eval-safety/blob/HEAD/lib/prune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"142350989c8691e6","mcp_get_code":{"code_sha256":"142350989c8691e6"}},{"arxiv_id":"2306.11695","paper":"/paper/a-simple-and-effective-pruning-approach-for","title":"A Simple and Effective Pruning Approach for Large Language Models","date":"2023-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qiaoxiao7282/seft","path":"lib/prune_all.py","file_url":"https://github.com/qiaoxiao7282/seft/blob/HEAD/lib/prune_all.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a0fc985586f0984c","mcp_get_code":{"code_sha256":"a0fc985586f0984c"}},{"arxiv_id":"2306.11695","paper":"/paper/a-simple-and-effective-pruning-approach-for","title":"A Simple and Effective Pruning Approach for Large Language Models","date":"2023-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"locuslab/wanda","path":"lib/prune.py","file_url":"https://github.com/locuslab/wanda/blob/HEAD/lib/prune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d2a4a72ebbf33444","mcp_get_code":{"code_sha256":"d2a4a72ebbf33444"}},{"arxiv_id":"2305.12396","paper":"/paper/joint-feature-and-differentiable-k-nn-graph","title":"Joint Feature and Differentiable $ k $-NN Graph Learning using Dirichlet Energy","date":"2023-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GhadaSokar/WAST","path":"utils.py","file_url":"https://github.com/GhadaSokar/WAST/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb797c04116322a3","mcp_get_code":{"code_sha256":"bb797c04116322a3"}},{"arxiv_id":"2212.13345","paper":"/paper/the-forward-forward-algorithm-some-1","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","date":"2022-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ads-cmu/forwardforward","path":"previous_implementation/utilities.py","file_url":"https://github.com/ads-cmu/forwardforward/blob/HEAD/previous_implementation/utilities.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4613748f89bf60c7","mcp_get_code":{"code_sha256":"4613748f89bf60c7"}},{"arxiv_id":"2208.13049","paper":"/paper/trojvit-trojan-insertion-in-vision","title":"TrojViT: Trojan Insertion in Vision Transformers","date":"2022-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mxzheng/trojvit","path":"utils.py","file_url":"https://github.com/mxzheng/trojvit/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"95bc0f22b2452460","mcp_get_code":{"code_sha256":"95bc0f22b2452460"}},{"arxiv_id":"2208.08270","paper":"/paper/on-the-privacy-effect-of-data-enhancement-via","title":"On the Privacy Effect of Data Enhancement via the Lens of Memorization","date":"2022-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lixiaothu/privacy_and_aug","path":"dataset.py","file_url":"https://github.com/lixiaothu/privacy_and_aug/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":"e259e3b8e5627125","mcp_get_code":{"code_sha256":"e259e3b8e5627125"}},{"arxiv_id":"2206.07737","paper":"/paper/disparate-impact-in-differential-privacy-from","title":"Disparate Impact in Differential Privacy from Gradient Misalignment","date":"2022-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"layer6ai-labs/fair-dp","path":"datasets/loaders.py","file_url":"https://github.com/layer6ai-labs/fair-dp/blob/HEAD/datasets/loaders.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":"890beb904c12fdd3","mcp_get_code":{"code_sha256":"890beb904c12fdd3"}},{"arxiv_id":"2206.02659","paper":"/paper/robust-fine-tuning-of-deep-neural-networks","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","date":"2022-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VirtuosoResearch/Robust-fine-tuning","path":"exps_on_image_datasets/data_loader/mini_domain_net.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/data_loader/mini_domain_net.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fa25db77d8a7f54f","mcp_get_code":{"code_sha256":"fa25db77d8a7f54f"}},{"arxiv_id":"2203.08392","paper":"/paper/patch-fool-are-vision-transformers-always-1","title":"Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RICE-EIC/Patch-Fool","path":"utils.py","file_url":"https://github.com/RICE-EIC/Patch-Fool/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"94ca6bbcc2bbe97e","mcp_get_code":{"code_sha256":"94ca6bbcc2bbe97e"}},{"arxiv_id":"2106.11930","paper":"/paper/on-the-importance-of-cross-task-features-for","title":"On the importance of cross-task features for class-incremental learning","date":"2021-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AlbinSou/cross_task_cil","path":"src/datasets/data_loader.py","file_url":"https://github.com/AlbinSou/cross_task_cil/blob/HEAD/src/datasets/data_loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"00e4bb5fb503e035","mcp_get_code":{"code_sha256":"00e4bb5fb503e035"}},{"arxiv_id":"2010.03403","paper":"/paper/universal-weighting-metric-learning-for-cross-1","title":"Universal Weighting Metric Learning for Cross-Modal Matching","date":"2020-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wayne980/PolyLoss","path":"data.py","file_url":"https://github.com/wayne980/PolyLoss/blob/HEAD/data.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":"a90b1e5a707539c5","mcp_get_code":{"code_sha256":"a90b1e5a707539c5"}},{"arxiv_id":"2007.05426","paper":"/paper/variational-inference-with-continuously","title":"Variational Inference with Continuously-Indexed Normalizing Flows","date":"2020-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anthonycaterini/cif-vi","path":"cif/datasets/loaders.py","file_url":"https://github.com/anthonycaterini/cif-vi/blob/HEAD/cif/datasets/loaders.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2b5ed06aec1d27b3","mcp_get_code":{"code_sha256":"2b5ed06aec1d27b3"}},{"arxiv_id":"2006.12135","paper":"/paper/learning-to-generate-noise-for-robustness","title":"Learning to Generate Noise for Multi-Attack Robustness","date":"2020-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"divyam3897/MNG_AC","path":"train_pgd.py","file_url":"https://github.com/divyam3897/MNG_AC/blob/HEAD/train_pgd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4829fc02195f0c39","mcp_get_code":{"code_sha256":"4829fc02195f0c39"}},{"arxiv_id":"2006.06574","paper":"/paper/dynamically-stable-infinite-width-limits-of","title":"Dynamically Stable Infinite-Width Limits of Neural Classifiers","date":"2020-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepmipt/research","path":"Infinite_Width_Limits_of_Neural_Classifiers/utils/data_loaders.py","file_url":"https://github.com/deepmipt/research/blob/HEAD/Infinite_Width_Limits_of_Neural_Classifiers/utils/data_loaders.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a3acc2c4331bedae","mcp_get_code":{"code_sha256":"a3acc2c4331bedae"}},{"arxiv_id":"2004.00070","paper":"/paper/conditional-channel-gated-networks-for-task","title":"Conditional Channel Gated Networks for Task-Aware Continual Learning","date":"2020-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lit-leo/cgate","path":"src/data.py","file_url":"https://github.com/lit-leo/cgate/blob/HEAD/src/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"de186ee17852ec67","mcp_get_code":{"code_sha256":"de186ee17852ec67"}},{"arxiv_id":"1803.08024","paper":"/paper/stacked-cross-attention-for-image-text","title":"Stacked Cross Attention for Image-Text Matching","date":"2018-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idejie/SCAN","path":"data.py","file_url":"https://github.com/idejie/SCAN/blob/HEAD/data.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":"a3b22af17bee87cc","mcp_get_code":{"code_sha256":"a3b22af17bee87cc"}},{"arxiv_id":"1802.10026","paper":"/paper/loss-surfaces-mode-connectivity-and-fast","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","date":"2018-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tjwhitaker/prune-and-tune-ensembles","path":"src/data.py","file_url":"https://github.com/tjwhitaker/prune-and-tune-ensembles/blob/HEAD/src/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b373666065863fd","mcp_get_code":{"code_sha256":"4b373666065863fd"}},{"arxiv_id":"2025.acl-long.590","paper":null,"title":"arXiv:2025.acl-long.590","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ChnQ/SPIN","path":"src/utils.py","file_url":"https://github.com/ChnQ/SPIN/blob/HEAD/src/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":"653a16cc7fc93fe0","mcp_get_code":{"code_sha256":"653a16cc7fc93fe0"}},{"arxiv_id":"2024.findings-emnlp.579","paper":null,"title":"arXiv:2024.findings-emnlp.579","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"RazvanDu/DynamicSlicing","path":"src/slicegpt/data.lib.py","file_url":"https://github.com/RazvanDu/DynamicSlicing/blob/HEAD/src/slicegpt/data.lib.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"16994008353af958","mcp_get_code":{"code_sha256":"16994008353af958"}},{"arxiv_id":"136910021","paper":null,"title":"arXiv:136910021","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"UCDvision/CMSF","path":"self_supervised/eval_knn.py","file_url":"https://github.com/UCDvision/CMSF/blob/HEAD/self_supervised/eval_knn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31aaac6f71c512ca","mcp_get_code":{"code_sha256":"31aaac6f71c512ca"}}]}