{"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/cosine-lr","entry":"cosine_lr","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":31,"n_papers_ran":15,"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":7,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":31,"n_places_pointer_only":12,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":2,"unverified":3},"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":"2606.22589","paper":"/paper/arxiv-2606-22589","title":"Training-free Task Classification for Multi-Task Model Merging","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"BAIKLAB/SiM","path":"src/utils.py","file_url":"https://github.com/BAIKLAB/SiM/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":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"arxiv_id":"2605.26693","paper":"/paper/arxiv-2605-26693","title":"Model Merging on Loss Landscape: A Geometry Perspective","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"mlfoundations/task_vectors","path":"src/utils.py","file_url":"https://github.com/mlfoundations/task_vectors/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":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"arxiv_id":"2605.20803","paper":"/paper/arxiv-2605-20803","title":"Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"KeiHiroshima/tunable-magmax","path":"src/utils.py","file_url":"https://github.com/KeiHiroshima/tunable-magmax/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"arxiv_id":"2512.12997","paper":"/paper/arxiv-2512-12997","title":"Calibrating Uncertainty for Zero-Shot Adversarial CLIP","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"VivienLu/UCAT","path":"utils.py","file_url":"https://github.com/VivienLu/UCAT/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2507.12998","paper":null,"title":"arXiv:2507.12998","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"MediaBrain-SJTU/DISSect","path":"src/scheduler.py","file_url":"https://github.com/MediaBrain-SJTU/DISSect/blob/HEAD/src/scheduler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2506.13406","paper":"/paper/calm-consensus-aware-localized-merging-for","title":"CALM: Consensus-Aware Localized Merging for Multi-Task Learning","date":"2025-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yankd22/calm","path":"src/utils.py","file_url":"https://github.com/yankd22/calm/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":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"arxiv_id":"2503.10657","paper":"/paper/routereval-a-comprehensive-benchmark-for","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","date":"2025-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"milkthink-lab/routereval","path":"router/MLPR_LinearR/tools.py","file_url":"https://github.com/milkthink-lab/routereval/blob/HEAD/router/MLPR_LinearR/tools.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7529a26792fd6da5","mcp_get_code":{"code_sha256":"7529a26792fd6da5"}},{"arxiv_id":"2502.01015","paper":"/paper/efficient-model-editing-with-task-vector","title":"Efficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable Approach","date":"2025-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uiuctml/TaskVectorBasis","path":"src/utils.py","file_url":"https://github.com/uiuctml/TaskVectorBasis/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"arxiv_id":"2412.12153","paper":"/paper/revisiting-weight-averaging-for-model-merging","title":"Revisiting Weight Averaging for Model Merging","date":"2024-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JH-GEECS/CART_public","path":"src/utils.py","file_url":"https://github.com/JH-GEECS/CART_public/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":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"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/scheduler.py","file_url":"https://github.com/mengcye/LAION-SG/blob/HEAD/sgEncoderTraining/training/scheduler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2411.19666","paper":"/paper/multimodal-whole-slide-foundation-model-for","title":"Multimodal Whole Slide Foundation Model for Pathology","date":"2024-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mahmoodlab/titan","path":"titan/finetune.py","file_url":"https://github.com/mahmoodlab/titan/blob/HEAD/titan/finetune.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":"e5ad400fe0abbe9a","mcp_get_code":{"code_sha256":"e5ad400fe0abbe9a"}},{"arxiv_id":"2411.19331","paper":"/paper/talking-to-dino-bridging-self-supervised","title":"Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation","date":"2024-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lorebianchi98/Talk2DINO","path":"src/train_util.py","file_url":"https://github.com/lorebianchi98/Talk2DINO/blob/HEAD/src/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":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2410.14389","paper":"/paper/surgeryv2-bridging-the-gap-between-model","title":"SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EnnengYang/SurgeryV2","path":"src/utils.py","file_url":"https://github.com/EnnengYang/SurgeryV2/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":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"arxiv_id":"2410.05583","paper":"/paper/negmerge-consensual-weight-negation-for","title":"NegMerge: Consensual Weight Negation for Strong Machine Unlearning","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver-ai/negmerge","path":"CLIP_MU/src/utils.py","file_url":"https://github.com/naver-ai/negmerge/blob/HEAD/CLIP_MU/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":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"arxiv_id":"2409.01936","paper":"/paper/optimizing-clip-models-for-image-retrieval","title":"Optimizing CLIP Models for Image Retrieval with Maintained Joint-Embedding Alignment","date":"2024-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Visual-Computing/MCIP","path":"MCIP/src/realignment/scheduler.py","file_url":"https://github.com/Visual-Computing/MCIP/blob/HEAD/MCIP/src/realignment/scheduler.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":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2405.08815","paper":"/paper/efficient-vision-language-pre-training-by","title":"Efficient Vision-Language Pre-training by Cluster Masking","date":"2024-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zi-hao-wei/efficient-vision-language-pre-training-by-cluster-masking","path":"training/scheduler.py","file_url":"https://github.com/zi-hao-wei/efficient-vision-language-pre-training-by-cluster-masking/blob/HEAD/training/scheduler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2405.03988","paper":"/paper/knowledge-adaptation-from-large-language","title":"LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adxcreative/LEARN","path":"src/training/scheduler.py","file_url":"https://github.com/adxcreative/LEARN/blob/HEAD/src/training/scheduler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2404.19287","paper":"/paper/revisiting-the-adversarial-robustness-of","title":"Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ellezwq/mmcoa","path":"utils.py","file_url":"https://github.com/ellezwq/mmcoa/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":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2401.04350","paper":"/paper/pre-trained-model-guided-fine-tuning-for-zero","title":"Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness","date":"2024-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"serendipity1122/Pre-trained-Model-Guided-Fine-Tuning-for-Zero-Shot-Adversarial-Robustness","path":"utils.py","file_url":"https://github.com/serendipity1122/Pre-trained-Model-Guided-Fine-Tuning-for-Zero-Shot-Adversarial-Robustness/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2308.12213","paper":"/paper/clipn-for-zero-shot-ood-detection-teaching","title":"CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No","date":"2023-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xmed-lab/clipn","path":"src/tuning_util.py","file_url":"https://github.com/xmed-lab/clipn/blob/HEAD/src/tuning_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"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/scheduler.py","file_url":"https://github.com/haoheliu/audioldm-training-finetuning/blob/HEAD/audioldm_train/modules/clap/training/scheduler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2305.12827","paper":"/paper/task-arithmetic-in-the-tangent-space-improved","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gortizji/tangent_task_arithmetic","path":"src/utils.py","file_url":"https://github.com/gortizji/tangent_task_arithmetic/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"arxiv_id":"2304.04858","paper":"/paper/simulated-annealing-in-early-layers-leads-to","title":"Simulated Annealing in Early Layers Leads to Better Generalization","date":"2023-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amiiir-sarfi/seal","path":"core.py","file_url":"https://github.com/amiiir-sarfi/seal/blob/HEAD/core.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":"2e32661e8d23fbbb","mcp_get_code":{"code_sha256":"2e32661e8d23fbbb"}},{"arxiv_id":"2302.14042","paper":"/paper/knowledge-enhanced-pre-training-for-auto","title":"Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaoman-zhang/kad","path":"A2_KEBERT/training/scheduler.py","file_url":"https://github.com/xiaoman-zhang/kad/blob/HEAD/A2_KEBERT/training/scheduler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2209.00179","paper":"/paper/universal-multi-modality-retrieval-with-one","title":"Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval","date":"2022-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/univl-dr","path":"UniVL-DR/gen_embeddings.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/gen_embeddings.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2208.05592","paper":"/paper/patching-open-vocabulary-models-by","title":"Patching open-vocabulary models by interpolating weights","date":"2022-08-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlfoundations/patching","path":"src/utils.py","file_url":"https://github.com/mlfoundations/patching/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}},{"arxiv_id":"2203.17274","paper":"/paper/visual-prompting-modifying-pixel-space-to","title":"Exploring Visual Prompts for Adapting Large-Scale Models","date":"2022-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hjbahng/visual_prompting","path":"utils.py","file_url":"https://github.com/hjbahng/visual_prompting/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":"932d44bbf8bd0e3f","mcp_get_code":{"code_sha256":"932d44bbf8bd0e3f"}},{"arxiv_id":"2203.14145","paper":"/paper/reverse-engineering-of-imperceptible-1","title":"Reverse Engineering of Imperceptible Adversarial Image Perturbations","date":"2022-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yifanfanfanfan/reverse-engineering-of-imperceptible-adversarial-image-perturbations","path":"RED_train_with_trans.py","file_url":"https://github.com/yifanfanfanfan/reverse-engineering-of-imperceptible-adversarial-image-perturbations/blob/HEAD/RED_train_with_trans.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5196b556b5ecc5a","mcp_get_code":{"code_sha256":"c5196b556b5ecc5a"}},{"arxiv_id":"2103.05152","paper":"/paper/knowledge-evolution-in-neural-networks","title":"Knowledge Evolution in Neural Networks","date":"2021-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ahmdtaha/knowledge_evolution","path":"KE_model.py","file_url":"https://github.com/ahmdtaha/knowledge_evolution/blob/HEAD/KE_model.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":"e00ffa6d0e1a9ddb","mcp_get_code":{"code_sha256":"e00ffa6d0e1a9ddb"}},{"arxiv_id":"1811.12254","paper":"/paper/the-effect-of-heterogeneous-data-for","title":"The Effect of Heterogeneous Data for Alzheimer's Disease Detection from Speech","date":"2018-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ychnlgy/Chebyshev-Lagrange","path":"shake-shake_pytorch/utils.py","file_url":"https://github.com/ychnlgy/Chebyshev-Lagrange/blob/HEAD/shake-shake_pytorch/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7529a26792fd6da5","mcp_get_code":{"code_sha256":"7529a26792fd6da5"}},{"arxiv_id":"aaai_27950","paper":null,"title":"arXiv:aaai_27950","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"gaojingsheng/LAMM","path":"utils.py","file_url":"https://github.com/gaojingsheng/LAMM/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d5d7a12d8de02b7","mcp_get_code":{"code_sha256":"2d5d7a12d8de02b7"}}]}