{"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-features","entry":"get_features","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":57,"n_papers_ran":17,"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":16,"n_samples_fingerprinted":0,"n_places":62,"n_places_pointer_only":29,"by_status":{"ran_honours":5,"ran_violates":0,"ran_draft_wrong":7,"ran_fixture":2,"ran":2,"unverified":35},"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":"2605.26693","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/datasets/common.py","file_url":"https://github.com/mlfoundations/task_vectors/blob/HEAD/src/datasets/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3b97c12751c0cf5b","mcp_get_code":{"code_sha256":"3b97c12751c0cf5b"}},{"arxiv_id":"2605.20735","paper":"/paper/arxiv-2605-20735","title":"Lowering the Barrier to IREX Participation: Open-Source Algorithms, Toolkit, and Benchmarking for Iris Recognition","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"CVRL/PBM","path":"helper_methods.py","file_url":"https://github.com/CVRL/PBM/blob/HEAD/helper_methods.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"65cd3aa6cac7db06","mcp_get_code":{"code_sha256":"65cd3aa6cac7db06"}},{"arxiv_id":"2602.13700","paper":"/paper/arxiv-2602-13700","title":"Optimal Regret for Policy Optimization in Contextual Bandits","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"vowpalwabbit/vowpal_wabbit","path":"demo/advertising/naive_baseline.py","file_url":"https://github.com/vowpalwabbit/vowpal_wabbit/blob/HEAD/demo/advertising/naive_baseline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"cf20a46278653526","mcp_get_code":{"code_sha256":"cf20a46278653526"}},{"arxiv_id":"2601.22816","paper":"/paper/arxiv-2601-22816","title":"Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"vanderschaarlab/synthcity","path":"src/synthcity/metrics/_utils.py","file_url":"https://github.com/vanderschaarlab/synthcity/blob/HEAD/src/synthcity/metrics/_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":"4f27292c5ebe68b7","mcp_get_code":{"code_sha256":"4f27292c5ebe68b7"}},{"arxiv_id":"2601.22703","paper":"/paper/arxiv-2601-22703","title":"DAVIS: OOD Detection via Dominant Activations and Variance for Increased Separation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"epsilon-2007/DAVIS","path":"utils/score.py","file_url":"https://github.com/epsilon-2007/DAVIS/blob/HEAD/utils/score.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05d4789a4f644b81","mcp_get_code":{"code_sha256":"05d4789a4f644b81"}},{"arxiv_id":"2601.09072","paper":"/paper/arxiv-2601-09072","title":"Human-AI Co-design for Clinical Prediction Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"jjfenglab/HACHI","path":"src/ensemble_trainer/greedy_concept_selector.py","file_url":"https://github.com/jjfenglab/HACHI/blob/HEAD/src/ensemble_trainer/greedy_concept_selector.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"b0bcd9a5ee0ca100","mcp_get_code":{"code_sha256":"b0bcd9a5ee0ca100"}},{"arxiv_id":"2512.18248","paper":"/paper/arxiv-2512-18248","title":"On the Convergence Rate of LoRA Gradient Descent","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"siqiaomu/lora","path":"feature_extraction.py","file_url":"https://github.com/siqiaomu/lora/blob/HEAD/feature_extraction.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c8cdb15842f969b","mcp_get_code":{"code_sha256":"3c8cdb15842f969b"}},{"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/datasets/common.py","file_url":"https://github.com/yankd22/calm/blob/HEAD/src/datasets/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3b97c12751c0cf5b","mcp_get_code":{"code_sha256":"3b97c12751c0cf5b"}},{"arxiv_id":"2503.18406","paper":"/paper/instruct-clip-improving-instruction-guided","title":"Instruct-CLIP: Improving Instruction-Guided Image Editing with Automated Data Refinement Using Contrastive Learning","date":"2025-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SherryXTChen/Instruct-CLIP","path":"model.py","file_url":"https://github.com/SherryXTChen/Instruct-CLIP/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"86961ea7f4dc10d3","mcp_get_code":{"code_sha256":"86961ea7f4dc10d3"}},{"arxiv_id":"2502.18195","paper":"/paper/multi-perspective-data-augmentation-for-few","title":"Multi-Perspective Data Augmentation for Few-shot Object Detection","date":"2025-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nvakhoa/mpad","path":"mpad_generation/main_generate_data.py","file_url":"https://github.com/nvakhoa/mpad/blob/HEAD/mpad_generation/main_generate_data.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"747fa523e7e9b04b","mcp_get_code":{"code_sha256":"747fa523e7e9b04b"}},{"arxiv_id":"2502.10362","paper":"/paper/clamp-3-universal-music-information-retrieval","title":"CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages","date":null,"month_inferred_from_arxiv_id":"2025-02","title_source":"archive","repo":"sanderwood/clamp3","path":"inference/clamp3_score.py","file_url":"https://github.com/sanderwood/clamp3/blob/HEAD/inference/clamp3_score.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"33dfdbcc3d495cb8","mcp_get_code":{"code_sha256":"33dfdbcc3d495cb8"}},{"arxiv_id":"2502.10362","paper":"/paper/clamp-3-universal-music-information-retrieval","title":"CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages","date":null,"month_inferred_from_arxiv_id":"2025-02","title_source":"archive","repo":"sanderwood/clamp3","path":"inference/clamp3_eval.py","file_url":"https://github.com/sanderwood/clamp3/blob/HEAD/inference/clamp3_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3f1865499c582a59","mcp_get_code":{"code_sha256":"3f1865499c582a59"}},{"arxiv_id":"2501.18511","paper":"/paper/wildchat-50m-a-deep-dive-into-the-role-of","title":"WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training","date":"2025-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"penfever/wildchat-50m","path":"src/core/generate_model_responses.py","file_url":"https://github.com/penfever/wildchat-50m/blob/HEAD/src/core/generate_model_responses.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":"28053bf1dae0da2c","mcp_get_code":{"code_sha256":"28053bf1dae0da2c"}},{"arxiv_id":"2501.04694","paper":"/paper/epicoder-encompassing-diversity-and","title":"EpiCoder: Encompassing Diversity and Complexity in Code Generation","date":"2025-01-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DeepLearnXMU/EpiCoder","path":"extract/construct_tree.py","file_url":"https://github.com/DeepLearnXMU/EpiCoder/blob/HEAD/extract/construct_tree.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"e6d8c07fb59f049e","mcp_get_code":{"code_sha256":"e6d8c07fb59f049e"}},{"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/dataset/common.py","file_url":"https://github.com/JH-GEECS/CART_public/blob/HEAD/src/dataset/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3b97c12751c0cf5b","mcp_get_code":{"code_sha256":"3b97c12751c0cf5b"}},{"arxiv_id":"2412.09945","paper":"/paper/going-beyond-feature-similarity-effective","title":"Going Beyond Feature Similarity: Effective Dataset Distillation based on Class-Aware Conditional Mutual Information","date":"2024-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ndhg1213/CMIDD","path":"IDC/coreset.py","file_url":"https://github.com/ndhg1213/CMIDD/blob/HEAD/IDC/coreset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"27c45694acd469da","mcp_get_code":{"code_sha256":"27c45694acd469da"}},{"arxiv_id":"2411.19757","paper":"/paper/dual-risk-minimization-towards-next-level","title":"Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models","date":"2024-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vaynexie/DRM","path":"src/datasets/common.py","file_url":"https://github.com/vaynexie/DRM/blob/HEAD/src/datasets/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b5474dbf23edd87","mcp_get_code":{"code_sha256":"4b5474dbf23edd87"}},{"arxiv_id":"2411.06966","paper":"/paper/robust-fine-tuning-of-zero-shot-models-via","title":"Robust Fine-tuning of Zero-shot Models via Variance Reduction","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BeierZhu/VRF","path":"src/datasets/common.py","file_url":"https://github.com/BeierZhu/VRF/blob/HEAD/src/datasets/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3b97c12751c0cf5b","mcp_get_code":{"code_sha256":"3b97c12751c0cf5b"}},{"arxiv_id":"2410.17146","paper":"/paper/lines-post-training-layer-scaling-prevents","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","date":"2024-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wang-kee/LiNeS","path":"src/datasets/common.py","file_url":"https://github.com/wang-kee/LiNeS/blob/HEAD/src/datasets/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3b97c12751c0cf5b","mcp_get_code":{"code_sha256":"3b97c12751c0cf5b"}},{"arxiv_id":"2410.03955","paper":"/paper/model-developmental-safety-a-safety-centric","title":"A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ganglii/devsafety","path":"src/datasets/common.py","file_url":"https://github.com/ganglii/devsafety/blob/HEAD/src/datasets/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7727c964cfcd56e6","mcp_get_code":{"code_sha256":"7727c964cfcd56e6"}},{"arxiv_id":"2409.19663","paper":"/paper/identifying-knowledge-editing-types-in-large","title":"Identifying Knowledge Editing Types in Large Language Models","date":"2024-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xpq-tech/keti","path":"extract_features.py","file_url":"https://github.com/xpq-tech/keti/blob/HEAD/extract_features.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96c1f23ed670da04","mcp_get_code":{"code_sha256":"96c1f23ed670da04"}},{"arxiv_id":"2406.09173","paper":"/paper/potion-towards-poison-unlearning","title":"Potion: Towards Poison Unlearning","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"if-loops/towards_poison_unlearning","path":"src/analyze_feats.py","file_url":"https://github.com/if-loops/towards_poison_unlearning/blob/HEAD/src/analyze_feats.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"d17fd04d5d7ea7a0","mcp_get_code":{"code_sha256":"d17fd04d5d7ea7a0"}},{"arxiv_id":"2406.07236","paper":"/paper/let-go-of-your-labels-with-unsupervised-1","title":"Let Go of Your Labels with Unsupervised Transfer","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlbio-epfl/turtle","path":"precompute_representations.py","file_url":"https://github.com/mlbio-epfl/turtle/blob/HEAD/precompute_representations.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b300ef9fae8f3a37","mcp_get_code":{"code_sha256":"b300ef9fae8f3a37"}},{"arxiv_id":"2406.05184","paper":"/paper/the-unmet-promise-of-synthetic-training","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scottgeng00/unmet-promise","path":"adapt/src/datasets/common.py","file_url":"https://github.com/scottgeng00/unmet-promise/blob/HEAD/adapt/src/datasets/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ccb94c5b63b85a6","mcp_get_code":{"code_sha256":"3ccb94c5b63b85a6"}},{"arxiv_id":"2405.14737","paper":"/paper/clipscope-enhancing-zero-shot-ood-detection","title":"CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoring","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fu1001hao/clipscope","path":"CLIPScope.py","file_url":"https://github.com/fu1001hao/clipscope/blob/HEAD/CLIPScope.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0143ebb6ea0e7ac9","mcp_get_code":{"code_sha256":"0143ebb6ea0e7ac9"}},{"arxiv_id":"2405.07813","paper":"/paper/localizing-task-information-for-improved","title":"Localizing Task Information for Improved Model Merging and Compression","date":"2024-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nik-dim/tall_masks","path":"src/datasets/common.py","file_url":"https://github.com/nik-dim/tall_masks/blob/HEAD/src/datasets/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3b97c12751c0cf5b","mcp_get_code":{"code_sha256":"3b97c12751c0cf5b"}},{"arxiv_id":"2405.02363","paper":"/paper/llm-as-dataset-analyst-subpopulation","title":"LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model","date":"2024-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"llm-as-dataset-analyst/SSDLLM","path":"step2_criteria_initialization/Step2.3_InitializingCriterias.py","file_url":"https://github.com/llm-as-dataset-analyst/SSDLLM/blob/HEAD/step2_criteria_initialization/Step2.3_InitializingCriterias.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5dd05e4643e18e77","mcp_get_code":{"code_sha256":"5dd05e4643e18e77"}},{"arxiv_id":"2403.06075","paper":"/paper/multisize-dataset-condensation","title":"Multisize Dataset Condensation","date":"2024-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"he-y/Multisize-Dataset-Condensation","path":"coreset.py","file_url":"https://github.com/he-y/Multisize-Dataset-Condensation/blob/HEAD/coreset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"27c45694acd469da","mcp_get_code":{"code_sha256":"27c45694acd469da"}},{"arxiv_id":"2402.14015","paper":"/paper/corrective-machine-unlearning","title":"Corrective Machine Unlearning","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"drimpossible/corrective-unlearning-bench","path":"src/analyze_feats.py","file_url":"https://github.com/drimpossible/corrective-unlearning-bench/blob/HEAD/src/analyze_feats.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"d17fd04d5d7ea7a0","mcp_get_code":{"code_sha256":"d17fd04d5d7ea7a0"}},{"arxiv_id":"2402.09739","paper":"/paper/qurating-selecting-high-quality-data-for","title":"QuRating: Selecting High-Quality Data for Training Language Models","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/qurating","path":"analysis/cluster.py","file_url":"https://github.com/princeton-nlp/qurating/blob/HEAD/analysis/cluster.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"16c94cce1b3d8fd4","mcp_get_code":{"code_sha256":"16c94cce1b3d8fd4"}},{"arxiv_id":"2312.02546","paper":"/paper/machine-vision-therapy-multimodal-large","title":"Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmllab/2024_icml_dicl","path":"ImageNet_datasets/common.py","file_url":"https://github.com/tmllab/2024_icml_dicl/blob/HEAD/ImageNet_datasets/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7727c964cfcd56e6","mcp_get_code":{"code_sha256":"7727c964cfcd56e6"}},{"arxiv_id":"2311.01723","paper":"/paper/towards-calibrated-robust-fine-tuning-of","title":"Towards Calibrated Robust Fine-Tuning of Vision-Language Models","date":"2023-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MLAI-Yonsei/CaRot","path":"src/datasets_/common.py","file_url":"https://github.com/MLAI-Yonsei/CaRot/blob/HEAD/src/datasets_/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"35ec3a8e556cc61c","mcp_get_code":{"code_sha256":"35ec3a8e556cc61c"}},{"arxiv_id":"2308.15005","paper":"/paper/few-shot-object-detection-via-synthetic","title":"Few-Shot Object Detection via Synthetic Features with Optimal Transport","date":"2023-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"747fa523e7e9b04b","mcp_get_code":{"code_sha256":"747fa523e7e9b04b"}},{"arxiv_id":"2308.01313","paper":"/paper/more-context-less-distraction-visual","title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","date":"2023-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umd-huang-lab/perceptionclip","path":"src/zero_shot_inference/perceptionclip_two_step.py","file_url":"https://github.com/umd-huang-lab/perceptionclip/blob/HEAD/src/zero_shot_inference/perceptionclip_two_step.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69f5c5edbc89d5b8","mcp_get_code":{"code_sha256":"69f5c5edbc89d5b8"}},{"arxiv_id":"2308.01313","paper":"/paper/more-context-less-distraction-visual","title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","date":"2023-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umd-huang-lab/perceptionCLIP","path":"src/datasets/common.py","file_url":"https://github.com/umd-huang-lab/perceptionCLIP/blob/HEAD/src/datasets/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7727c964cfcd56e6","mcp_get_code":{"code_sha256":"7727c964cfcd56e6"}},{"arxiv_id":"2307.16177","paper":"/paper/fusing-vhr-post-disaster-aerial-imagery-and","title":"Fusing VHR Post-disaster Aerial Imagery and LiDAR Data for Roof Classification in the Caribbean","date":"2023-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GFDRR/caribbean-rooftop-classification","path":"utils/fusion_utils.py","file_url":"https://github.com/GFDRR/caribbean-rooftop-classification/blob/HEAD/utils/fusion_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"542ebb17cd101f6a","mcp_get_code":{"code_sha256":"542ebb17cd101f6a"}},{"arxiv_id":"2305.14035","paper":"/paper/can-self-supervised-neural-networks-pre","title":"Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idiap/ssl-caller-detection","path":"src/extract_features.py","file_url":"https://github.com/idiap/ssl-caller-detection/blob/HEAD/src/extract_features.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"9be3680cccfbba85","mcp_get_code":{"code_sha256":"9be3680cccfbba85"}},{"arxiv_id":"2302.12758","paper":"/paper/defending-against-backdoor-attacks-by-layer","title":"Defending Against Backdoor Attacks by Layer-wise Feature Analysis","date":"2023-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"najeebjebreel/dbalfa","path":"utils.py","file_url":"https://github.com/najeebjebreel/dbalfa/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":"c469ddae1a6c4775","mcp_get_code":{"code_sha256":"c469ddae1a6c4775"}},{"arxiv_id":"2302.09795","paper":"/paper/simple-disentanglement-of-style-and-content","title":"Simple Disentanglement of Style and Content in Visual Representations","date":"2023-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lilianngweta/pisco","path":"experiments/feature_extractors/ImageNet_ResNet50_feature_extractor_stylized.py","file_url":"https://github.com/lilianngweta/pisco/blob/HEAD/experiments/feature_extractors/ImageNet_ResNet50_feature_extractor_stylized.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14e9567a9e02e3a6","mcp_get_code":{"code_sha256":"14e9567a9e02e3a6"}},{"arxiv_id":"2302.02628","paper":"/paper/trust-but-verify-using-self-supervised","title":"Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness","date":"2023-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"d-ailin/ssprobing","path":"mis_detect.py","file_url":"https://github.com/d-ailin/ssprobing/blob/HEAD/mis_detect.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"71630cb6ffc1154c","mcp_get_code":{"code_sha256":"71630cb6ffc1154c"}},{"arxiv_id":"2301.07597","paper":"/paper/how-close-is-chatgpt-to-human-experts","title":"How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection","date":"2023-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lsc-1/pecola","path":"lib/inference/draw.py","file_url":"https://github.com/lsc-1/pecola/blob/HEAD/lib/inference/draw.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dd94c31be0cd6720","mcp_get_code":{"code_sha256":"dd94c31be0cd6720"}},{"arxiv_id":"2210.11589","paper":"/paper/monotonic-risk-relationships-under","title":"Monotonic Risk Relationships under Distribution Shifts for Regularized Risk Minimization","date":"2022-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mli-lab/monotonic_risk_relationships","path":"bounding_box_coordinate_prediction/run_experiment.py","file_url":"https://github.com/mli-lab/monotonic_risk_relationships/blob/HEAD/bounding_box_coordinate_prediction/run_experiment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3e4881d413bd67c3","mcp_get_code":{"code_sha256":"3e4881d413bd67c3"}},{"arxiv_id":"2210.09452","paper":"/paper/multiple-instance-learning-via-iterative-self","title":"Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning","date":"2022-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kangningthu/its2clr","path":"train/trainer.py","file_url":"https://github.com/kangningthu/its2clr/blob/HEAD/train/trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e0af36e605bcb2e","mcp_get_code":{"code_sha256":"2e0af36e605bcb2e"}},{"arxiv_id":"2209.09341","paper":"/paper/a-simple-and-powerful-global-optimization-for","title":"A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation","date":"2022-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ponimatkin/ssl-vos","path":"extract_dino_features.py","file_url":"https://github.com/ponimatkin/ssl-vos/blob/HEAD/extract_dino_features.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e51dba2659ab8684","mcp_get_code":{"code_sha256":"e51dba2659ab8684"}},{"arxiv_id":"2205.13616","paper":"/paper/fight-poison-with-poison-detecting-backdoor","title":"Towards A Proactive ML Approach for Detecting Backdoor Poison Samples","date":"2022-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"unispac/fight-poison-with-poison","path":"confusion_training.py","file_url":"https://github.com/unispac/fight-poison-with-poison/blob/HEAD/confusion_training.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"519506e21b1f832b","mcp_get_code":{"code_sha256":"519506e21b1f832b"}},{"arxiv_id":"2102.07804","paper":"/paper/scaling-up-exact-neural-network-compression","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","date":"2021-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuxwind/exactcompression","path":"train_fcnn.py","file_url":"https://github.com/yuxwind/exactcompression/blob/HEAD/train_fcnn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2893257a02af7980","mcp_get_code":{"code_sha256":"2893257a02af7980"}},{"arxiv_id":"2008.11297","paper":"/paper/transductive-information-maximization-for-few","title":"Transductive Information Maximization For Few-Shot Learning","date":"2020-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mboudiaf/TIM","path":"src/utils.py","file_url":"https://github.com/mboudiaf/TIM/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":"12cbd4d101797d30","mcp_get_code":{"code_sha256":"12cbd4d101797d30"}},{"arxiv_id":"2002.05709","paper":"/paper/a-simple-framework-for-contrastive-learning","title":"A Simple Framework for Contrastive Learning of Visual Representations","date":"2020-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Spijkervet/SimCLR","path":"linear_evaluation.py","file_url":"https://github.com/Spijkervet/SimCLR/blob/HEAD/linear_evaluation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb291d2ffc7590c7","mcp_get_code":{"code_sha256":"cb291d2ffc7590c7"}},{"arxiv_id":"1911.11834","paper":"/paper/towards-fairness-in-visual-recognition","title":"Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation","date":"2019-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junjie1003/DL-Fairness-Study","path":"FLAC/get_imagenet_bias_features.py","file_url":"https://github.com/junjie1003/DL-Fairness-Study/blob/HEAD/FLAC/get_imagenet_bias_features.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":"959c350e8c71f0f1","mcp_get_code":{"code_sha256":"959c350e8c71f0f1"}},{"arxiv_id":"1911.00484","paper":"/paper/select-answer-and-explain-interpretable-multi","title":"Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents","date":"2019-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jd-ai-research-silicon-valley/sae","path":"prepro.py","file_url":"https://github.com/jd-ai-research-silicon-valley/sae/blob/HEAD/prepro.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4196e08cc75d063a","mcp_get_code":{"code_sha256":"4196e08cc75d063a"}},{"arxiv_id":"1908.00375","paper":"/paper/quality-assessment-of-in-the-wild-videos","title":"Quality Assessment of In-the-Wild Videos","date":"2019-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SpikeKing/VQA-v2","path":"CNNfeatures.py","file_url":"https://github.com/SpikeKing/VQA-v2/blob/HEAD/CNNfeatures.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc8708ffff5c61d7","mcp_get_code":{"code_sha256":"bc8708ffff5c61d7"}},{"arxiv_id":"1905.05583","paper":"/paper/how-to-fine-tune-bert-for-text-classification","title":"How to Fine-Tune BERT for Text Classification?","date":"2019-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uzaymacar/comparatively-finetuning-bert","path":"utils/data_utils.py","file_url":"https://github.com/uzaymacar/comparatively-finetuning-bert/blob/HEAD/utils/data_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a9ecfcb35141c0d8","mcp_get_code":{"code_sha256":"a9ecfcb35141c0d8"}},{"arxiv_id":"1904.06991","paper":"/paper/improved-precision-and-recall-metric-for","title":"Improved Precision and Recall Metric for Assessing Generative Models","date":"2019-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thomaskerdreux/pdm_sar_insar_generation","path":"utils/utils_precision_and_recall.py","file_url":"https://github.com/thomaskerdreux/pdm_sar_insar_generation/blob/HEAD/utils/utils_precision_and_recall.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c9ddbe660f0c2da","mcp_get_code":{"code_sha256":"6c9ddbe660f0c2da"}},{"arxiv_id":"1904.03208","paper":"/paper/semantic-aware-knowledge-preservation-for","title":"Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval","date":"2019-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qliu24/SAKE","path":"src/test_cse_resnet_tuberlin_zeroshot.py","file_url":"https://github.com/qliu24/SAKE/blob/HEAD/src/test_cse_resnet_tuberlin_zeroshot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fd37118c88a91608","mcp_get_code":{"code_sha256":"fd37118c88a91608"}},{"arxiv_id":"1802.06257","paper":"/paper/regal-representation-learning-based-graph","title":"REGAL: Representation Learning-based Graph Alignment","date":null,"month_inferred_from_arxiv_id":"2018-02","title_source":"archive","repo":"GemsLab/REGAL","path":"xnetmf.py","file_url":"https://github.com/GemsLab/REGAL/blob/HEAD/xnetmf.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"91a5d50365f220e5","mcp_get_code":{"code_sha256":"91a5d50365f220e5"}},{"arxiv_id":"1708.00489","paper":"/paper/active-learning-for-convolutional-neural","title":"Active Learning for Convolutional Neural Networks: A Core-Set Approach","date":"2017-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"svdesai/coreset-al","path":"active_learn.py","file_url":"https://github.com/svdesai/coreset-al/blob/HEAD/active_learn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9f2a097ed541f2e8","mcp_get_code":{"code_sha256":"9f2a097ed541f2e8"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anhoangphuc/neural_style_transfer","path":"style_transfer_script.py","file_url":"https://github.com/anhoangphuc/neural_style_transfer/blob/HEAD/style_transfer_script.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2e53f16d3df80194","mcp_get_code":{"code_sha256":"2e53f16d3df80194"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pravitc/Neural-style-transfer-using-Pytorch","path":"style_transfer.py","file_url":"https://github.com/pravitc/Neural-style-transfer-using-Pytorch/blob/HEAD/style_transfer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f8354f1977f18aba","mcp_get_code":{"code_sha256":"f8354f1977f18aba"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"divyanshu092/Photorealistic_Style_Transfer","path":"Code/utils.py","file_url":"https://github.com/divyanshu092/Photorealistic_Style_Transfer/blob/HEAD/Code/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2510489172d8e8f","mcp_get_code":{"code_sha256":"c2510489172d8e8f"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"itzpankajpanwar/Style-Transfer","path":"style_transfer.py","file_url":"https://github.com/itzpankajpanwar/Style-Transfer/blob/HEAD/style_transfer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f8efa1daf9783b9c","mcp_get_code":{"code_sha256":"f8efa1daf9783b9c"}},{"arxiv_id":"Tiong_Flexible_Biometrics_Recognition_Bridging_the_Multimodality_Gap_through_Attention_Alignment_CVPR_2024_paper","paper":null,"title":"arXiv:Tiong_Flexible_Biometrics_Recognition_Bridging_the_Multimodality_Gap_through_Attention_Alignment_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"MIS-DevWorks/FBR","path":"utils/model_utils.py","file_url":"https://github.com/MIS-DevWorks/FBR/blob/HEAD/utils/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":"578fca7002bbbf86","mcp_get_code":{"code_sha256":"578fca7002bbbf86"}},{"arxiv_id":"2022.findings-emnlp.497","paper":null,"title":"arXiv:2022.findings-emnlp.497","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lancopku/Avg-Avg","path":"lib/inference/draw.py","file_url":"https://github.com/lancopku/Avg-Avg/blob/HEAD/lib/inference/draw.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dd94c31be0cd6720","mcp_get_code":{"code_sha256":"dd94c31be0cd6720"}}]}