{"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/unwrap-model","entry":"unwrap_model","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":41,"n_papers_ran":12,"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":26,"n_samples_ran":8,"n_samples_fingerprinted":0,"n_places":41,"n_places_pointer_only":12,"by_status":{"ran_honours":0,"ran_violates":3,"ran_draft_wrong":2,"ran_fixture":0,"ran":3,"unverified":18},"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":"2609.04110","paper":"/paper/arxiv-2609-04110","title":"The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"ANDgate99/VT-Contrast","path":"utils/model_utils.py","file_url":"https://github.com/ANDgate99/VT-Contrast/blob/HEAD/utils/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6b24fbf0b77326ea","mcp_get_code":{"code_sha256":"6b24fbf0b77326ea"}},{"arxiv_id":"2608.13717","paper":"/paper/arxiv-2608-13717","title":"StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"NVIDIA-NeMo/Speech","path":"nemo/utils/model_utils.py","file_url":"https://github.com/NVIDIA-NeMo/Speech/blob/HEAD/nemo/utils/model_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d0b9c431aaf4be9f","mcp_get_code":{"code_sha256":"d0b9c431aaf4be9f"}},{"arxiv_id":"2607.19181","paper":"/paper/arxiv-2607-19181","title":"Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"aixiuxiuxiu/Legal-MT-SFT-RL","path":"model/utils.py","file_url":"https://github.com/aixiuxiuxiu/Legal-MT-SFT-RL/blob/HEAD/model/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0c3ff94987c68b53","mcp_get_code":{"code_sha256":"0c3ff94987c68b53"}},{"arxiv_id":"2607.16117","paper":"/paper/arxiv-2607-16117","title":"Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"ziegler-ingo/rate-utility-frontiers","path":"ruf/utils.py","file_url":"https://github.com/ziegler-ingo/rate-utility-frontiers/blob/HEAD/ruf/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d353aa5026e7865e","mcp_get_code":{"code_sha256":"d353aa5026e7865e"}},{"arxiv_id":"2607.06982","paper":"/paper/arxiv-2607-06982","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"ntuliuteam/edge-compress","path":"core/dynamic.py","file_url":"https://github.com/ntuliuteam/edge-compress/blob/HEAD/core/dynamic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7165fcf78de9cfb2","mcp_get_code":{"code_sha256":"7165fcf78de9cfb2"}},{"arxiv_id":"2606.06047","paper":"/paper/arxiv-2606-06047","title":"Automatic Labelling of Speech Translation Errors","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"NVIDIA-NeMo/NeMo","path":"nemo/utils/model_utils.py","file_url":"https://github.com/NVIDIA-NeMo/NeMo/blob/HEAD/nemo/utils/model_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d0b9c431aaf4be9f","mcp_get_code":{"code_sha256":"d0b9c431aaf4be9f"}},{"arxiv_id":"2602.13303","paper":"/paper/arxiv-2602-13303","title":"Spectral Collapse in Diffusion Inversion","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"nicoboou/ovg","path":"utils/helpers.py","file_url":"https://github.com/nicoboou/ovg/blob/HEAD/utils/helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4367fc8188e7115f","mcp_get_code":{"code_sha256":"4367fc8188e7115f"}},{"arxiv_id":"2602.11933","paper":"/paper/arxiv-2602-11933","title":"Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"NVIDIA/NeMo","path":"nemo/utils/model_utils.py","file_url":"https://github.com/NVIDIA/NeMo/blob/HEAD/nemo/utils/model_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d0b9c431aaf4be9f","mcp_get_code":{"code_sha256":"d0b9c431aaf4be9f"}},{"arxiv_id":"2602.02232","paper":"/paper/arxiv-2602-02232","title":"LiFlow: Flow Matching for 3D LiDAR Scene Completion","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"matteandre/LiFlow","path":"liflow/models/ema_callback.py","file_url":"https://github.com/matteandre/LiFlow/blob/HEAD/liflow/models/ema_callback.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9603dea3759c2ec7","mcp_get_code":{"code_sha256":"9603dea3759c2ec7"}},{"arxiv_id":"2601.15014","paper":"/paper/arxiv-2601-15014","title":"Efficient and Minimax Optimal In-context Nonparametric Regression with Transformers","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"tianyima2000/ICL_LocPol","path":"ICL_locpol.py","file_url":"https://github.com/tianyima2000/ICL_LocPol/blob/HEAD/ICL_locpol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"35ea6edb8b5b4542","mcp_get_code":{"code_sha256":"35ea6edb8b5b4542"}},{"arxiv_id":"2512.00239","paper":"/paper/arxiv-2512-00239","title":"Self-Supervised Dynamical System Representations for Physiological Time-Series","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"yuqinie98/PatchTST","path":"PatchTST_self_supervised/src/utils.py","file_url":"https://github.com/yuqinie98/PatchTST/blob/HEAD/PatchTST_self_supervised/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":"3cc94cf719642c1f","mcp_get_code":{"code_sha256":"3cc94cf719642c1f"}},{"arxiv_id":"2507.09990","paper":"/paper/differentially-private-federated-low-rank","title":"Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix","date":"2025-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FLEECERmw/PrivacyFedLLM","path":"policy/policy_scaffold.py","file_url":"https://github.com/FLEECERmw/PrivacyFedLLM/blob/HEAD/policy/policy_scaffold.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":"fd9a34654ce589b0","mcp_get_code":{"code_sha256":"fd9a34654ce589b0"}},{"arxiv_id":"2506.03355","paper":"/paper/robustness-in-both-domains-clip-needs-a","title":"Robustness in Both Domains: CLIP Needs a Robust Text Encoder","date":"2025-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LIONS-EPFL/LEAF","path":"src/robust_vlm/train/adversarial_training_clip.py","file_url":"https://github.com/LIONS-EPFL/LEAF/blob/HEAD/src/robust_vlm/train/adversarial_training_clip.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a72cc58ae0995b23","mcp_get_code":{"code_sha256":"a72cc58ae0995b23"}},{"arxiv_id":"2412.08580","paper":"/paper/laion-sg-an-enhanced-large-scale-dataset-for","title":"LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations","date":"2024-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mengcye/LAION-SG","path":"sgEncoderTraining/training/train_and_val_one_iter.py","file_url":"https://github.com/mengcye/LAION-SG/blob/HEAD/sgEncoderTraining/training/train_and_val_one_iter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2bf62c0287050bdd","mcp_get_code":{"code_sha256":"2bf62c0287050bdd"}},{"arxiv_id":"2409.00935","paper":"/paper/self-judge-selective-instruction-following","title":"Self-Judge: Selective Instruction Following with Alignment Self-Evaluation","date":"2024-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nusnlp/Self-J","path":"kd.py","file_url":"https://github.com/nusnlp/Self-J/blob/HEAD/kd.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"551e41129f773314","mcp_get_code":{"code_sha256":"551e41129f773314"}},{"arxiv_id":"2408.11051","paper":"/paper/flame-learning-to-navigate-with-multimodal","title":"FLAME: Learning to Navigate with Multimodal LLM in Urban Environments","date":"2024-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xyz9911/FLAME","path":"llm_nav/trainer.py","file_url":"https://github.com/xyz9911/FLAME/blob/HEAD/llm_nav/trainer.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":"54b2d55aa476a3bc","mcp_get_code":{"code_sha256":"54b2d55aa476a3bc"}},{"arxiv_id":"2407.10240","paper":"/paper/xlstmtime-long-term-time-series-forecasting","title":"xLSTMTime : Long-term Time Series Forecasting With xLSTM","date":"2024-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"muslehal/xLSTMTime","path":"src/utils.py","file_url":"https://github.com/muslehal/xLSTMTime/blob/HEAD/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":"3cc94cf719642c1f","mcp_get_code":{"code_sha256":"3cc94cf719642c1f"}},{"arxiv_id":"2406.10216","paper":"/paper/regularizing-hidden-states-enables-learning","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangrui2015/generalizable-reward-model","path":"rlhf/ppo/model_utils.py","file_url":"https://github.com/yangrui2015/generalizable-reward-model/blob/HEAD/rlhf/ppo/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54b2d55aa476a3bc","mcp_get_code":{"code_sha256":"54b2d55aa476a3bc"}},{"arxiv_id":"2405.05808","paper":"/paper/fast-and-controllable-post-training-sparsity","title":"Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes","date":"2024-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ModelTC/FCPTS","path":"utils.py","file_url":"https://github.com/ModelTC/FCPTS/blob/HEAD/utils.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8ba24560996e7d76","mcp_get_code":{"code_sha256":"8ba24560996e7d76"}},{"arxiv_id":"2403.16831","paper":"/paper/urbanvlp-a-multi-granularity-vision-language","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"citymind-lab/urbanvlp","path":"models/utils.py","file_url":"https://github.com/citymind-lab/urbanvlp/blob/HEAD/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2bf62c0287050bdd","mcp_get_code":{"code_sha256":"2bf62c0287050bdd"}},{"arxiv_id":"2403.04746","paper":"/paper/llms-in-the-imaginarium-tool-learning-through","title":"LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/simulated-trial-and-error","path":"llama-recipes/model_checkpointing/checkpoint_handler.py","file_url":"https://github.com/microsoft/simulated-trial-and-error/blob/HEAD/llama-recipes/model_checkpointing/checkpoint_handler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b530360e413bc3fd","mcp_get_code":{"code_sha256":"b530360e413bc3fd"}},{"arxiv_id":"2402.12336","paper":"/paper/robust-clip-unsupervised-adversarial-fine","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chs20/robustvlm","path":"train/adversarial_training_clip.py","file_url":"https://github.com/chs20/robustvlm/blob/HEAD/train/adversarial_training_clip.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04cf221e803c96d7","mcp_get_code":{"code_sha256":"04cf221e803c96d7"}},{"arxiv_id":"2312.06739","paper":"/paper/smartedit-exploring-complex-instruction-based","title":"SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TencentARC/SmartEdit","path":"train/DS_SmartEdit_train.py","file_url":"https://github.com/TencentARC/SmartEdit/blob/HEAD/train/DS_SmartEdit_train.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"53f81df53706a39a","mcp_get_code":{"code_sha256":"53f81df53706a39a"}},{"arxiv_id":"2311.13435","paper":"/paper/pg-video-llava-pixel-grounding-large-video","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","date":"2023-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mbzuai-oryx/video-llava","path":"video_chatgpt/train/llava_trainer.py","file_url":"https://github.com/mbzuai-oryx/video-llava/blob/HEAD/video_chatgpt/train/llava_trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"54b2d55aa476a3bc","mcp_get_code":{"code_sha256":"54b2d55aa476a3bc"}},{"arxiv_id":"2311.11514","paper":"/paper/hexgen-generative-inference-of-foundation","title":"HexGen: Generative Inference of Large Language Model over Heterogeneous Environment","date":null,"month_inferred_from_arxiv_id":"2023-11","title_source":"archive","repo":"relaxed-system-lab/hexgen","path":"hexgen/hexgen_core/heterogeneous_pipeline.py","file_url":"https://github.com/relaxed-system-lab/hexgen/blob/HEAD/hexgen/hexgen_core/heterogeneous_pipeline.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":"85b5684d7d73dde9","mcp_get_code":{"code_sha256":"85b5684d7d73dde9"}},{"arxiv_id":"2310.01225","paper":"/paper/a-path-norm-toolkit-for-modern-networks","title":"A path-norm toolkit for modern networks: consequences, promises and challenges","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agonon/pathnorm_toolkit","path":"repro/icml25/utils/pathnorm_transform.py","file_url":"https://github.com/agonon/pathnorm_toolkit/blob/HEAD/repro/icml25/utils/pathnorm_transform.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":"25a99cb17f71ec59","mcp_get_code":{"code_sha256":"25a99cb17f71ec59"}},{"arxiv_id":"2309.17002","paper":"/paper/understanding-and-mitigating-the-label-noise","title":"Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hhhhhhao/Noisy-Model-Learning","path":"timm/utils/model.py","file_url":"https://github.com/Hhhhhhao/Noisy-Model-Learning/blob/HEAD/timm/utils/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7a86fad403e4e95e","mcp_get_code":{"code_sha256":"7a86fad403e4e95e"}},{"arxiv_id":"2308.05734","paper":"/paper/audioldm-2-learning-holistic-audio-generation","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","date":"2023-08-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoheliu/audioldm-training-finetuning","path":"audioldm_train/modules/clap/training/lp_train.py","file_url":"https://github.com/haoheliu/audioldm-training-finetuning/blob/HEAD/audioldm_train/modules/clap/training/lp_train.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2bf62c0287050bdd","mcp_get_code":{"code_sha256":"2bf62c0287050bdd"}},{"arxiv_id":"2304.14636","paper":"/paper/prenas-preferred-one-shot-learning-towards","title":"PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search","date":null,"month_inferred_from_arxiv_id":"2023-04","title_source":"archive","repo":"tinyvision/PreNAS","path":"lib/score_maker.py","file_url":"https://github.com/tinyvision/PreNAS/blob/HEAD/lib/score_maker.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"2bf62c0287050bdd","mcp_get_code":{"code_sha256":"2bf62c0287050bdd"}},{"arxiv_id":"2212.04129","paper":"/paper/deep-model-assembling","title":"Deep Incubation: Training Large Models by Divide-and-Conquering","date":"2022-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/model-assembling","path":"timm/utils/model.py","file_url":"https://github.com/leaplabthu/model-assembling/blob/HEAD/timm/utils/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7a86fad403e4e95e","mcp_get_code":{"code_sha256":"7a86fad403e4e95e"}},{"arxiv_id":"2201.11147","paper":"/paper/ontoprotein-protein-pretraining-with-gene-1","title":"OntoProtein: Protein Pretraining With Gene Ontology Embedding","date":"2022-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/OntoProtein","path":"src/models.py","file_url":"https://github.com/zjunlp/OntoProtein/blob/HEAD/src/models.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d0f318a102295076","mcp_get_code":{"code_sha256":"d0f318a102295076"}},{"arxiv_id":"2003.00482","paper":"/paper/state-aware-tracker-for-real-time-video","title":"State-Aware Tracker for Real-Time Video Object Segmentation","date":"2020-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MegviiDetection/video_analyst","path":"videoanalyst/utils/torch_module.py","file_url":"https://github.com/MegviiDetection/video_analyst/blob/HEAD/videoanalyst/utils/torch_module.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"99a642ee770823da","mcp_get_code":{"code_sha256":"99a642ee770823da"}},{"arxiv_id":"2002.09564","paper":"/paper/towards-robust-and-reproducible-active","title":"Towards Robust and Reproducible Active Learning Using Neural Networks","date":"2020-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"acl21/deep-active-learning-pytorch","path":"pycls/core/net.py","file_url":"https://github.com/acl21/deep-active-learning-pytorch/blob/HEAD/pycls/core/net.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ba24560996e7d76","mcp_get_code":{"code_sha256":"8ba24560996e7d76"}},{"arxiv_id":"1905.13214","paper":"/paper/on-network-design-spaces-for-visual","title":"On Network Design Spaces for Visual Recognition","date":"2019-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tuggeluk/pycls","path":"pycls/core/net.py","file_url":"https://github.com/tuggeluk/pycls/blob/HEAD/pycls/core/net.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ba24560996e7d76","mcp_get_code":{"code_sha256":"8ba24560996e7d76"}},{"arxiv_id":"1902.08570","paper":"/paper/particlenet-jet-tagging-via-particle-clouds","title":"ParticleNet: Jet Tagging via Particle Clouds","date":"2019-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hqucms/weaver-core","path":"weaver/utils/nn/tools.py","file_url":"https://github.com/hqucms/weaver-core/blob/HEAD/weaver/utils/nn/tools.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"464cf959f947b7c4","mcp_get_code":{"code_sha256":"464cf959f947b7c4"}},{"arxiv_id":"1608.08710","paper":"/paper/pruning-filters-for-efficient-convnets","title":"Pruning Filters for Efficient ConvNets","date":"2016-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"siyuan0/pytorch_model_prune","path":"prune.py","file_url":"https://github.com/siyuan0/pytorch_model_prune/blob/HEAD/prune.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":"f21b8549dee8b153","mcp_get_code":{"code_sha256":"f21b8549dee8b153"}},{"arxiv_id":"Zhang_Spiking_Transformers_for_Event-Based_Single_Object_Tracking_CVPR_2022_paper","paper":null,"title":"arXiv:Zhang_Spiking_Transformers_for_Event-Based_Single_Object_Tracking_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Jee-King/CVPR2022_STNet","path":"videoanalyst/utils/torch_module.py","file_url":"https://github.com/Jee-King/CVPR2022_STNet/blob/HEAD/videoanalyst/utils/torch_module.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"99a642ee770823da","mcp_get_code":{"code_sha256":"99a642ee770823da"}},{"arxiv_id":"Yang_Attentive_Mask_CLIP_ICCV_2023_paper","paper":null,"title":"arXiv:Yang_Attentive_Mask_CLIP_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"microsoft/A-CLIP","path":"utils.py","file_url":"https://github.com/microsoft/A-CLIP/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":"2bf62c0287050bdd","mcp_get_code":{"code_sha256":"2bf62c0287050bdd"}},{"arxiv_id":"Tang_Progressive_Attention_on_Multi-Level_Dense_Difference_Maps_for_Generic_Event_CVPR_2022_paper","paper":null,"title":"arXiv:Tang_Progressive_Attention_on_Multi-Level_Dense_Difference_Maps_for_Generic_Event_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"MCG-NJU/DDM","path":"DDM-Net/utils/checkpoint_saver.py","file_url":"https://github.com/MCG-NJU/DDM/blob/HEAD/DDM-Net/utils/checkpoint_saver.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7a86fad403e4e95e","mcp_get_code":{"code_sha256":"7a86fad403e4e95e"}},{"arxiv_id":"2025.naacl-long.298","paper":null,"title":"arXiv:2025.naacl-long.298","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"pyf98/NeMo_VoiceTextBlender","path":"nemo/utils/model_utils.py","file_url":"https://github.com/pyf98/NeMo_VoiceTextBlender/blob/HEAD/nemo/utils/model_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":"aaa3faafc96337d0","mcp_get_code":{"code_sha256":"aaa3faafc96337d0"}},{"arxiv_id":"2025.emnlp-main.19","paper":null,"title":"arXiv:2025.emnlp-main.19","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zechenli03/SensorLLM","path":"sensorllm/train/sensorllm_trainer.py","file_url":"https://github.com/zechenli03/SensorLLM/blob/HEAD/sensorllm/train/sensorllm_trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54b2d55aa476a3bc","mcp_get_code":{"code_sha256":"54b2d55aa476a3bc"}}]}