{"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/metrics","entry":"metrics","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":21,"n_papers_ran":4,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":22,"n_samples_ran":4,"n_samples_fingerprinted":1,"n_places":22,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"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":"2609.04105","paper":"/paper/arxiv-2609-04105","title":"Hardware-Aware FP4 FlashAttention-4","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"MrHuff/fp4-fa4","path":"results/fp4_fa4_hao_table_gb200_20260802/build_summary.py","file_url":"https://github.com/MrHuff/fp4-fa4/blob/HEAD/results/fp4_fa4_hao_table_gb200_20260802/build_summary.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":"a5706b1f7b9e38c6","mcp_get_code":{"code_sha256":"a5706b1f7b9e38c6"}},{"arxiv_id":"2601.17301","paper":"/paper/arxiv-2601-17301","title":"Tabular Foundation Models are Strong Graph Anomaly Detectors","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Cloudy1225/TFM4GAD","path":"LimiX/tfm4gad/misc.py","file_url":"https://github.com/Cloudy1225/TFM4GAD/blob/HEAD/LimiX/tfm4gad/misc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3787d583dedfaaa9","mcp_get_code":{"code_sha256":"3787d583dedfaaa9"}},{"arxiv_id":"2506.07883","paper":"/paper/diffusion-counterfactual-generation-with","title":"Diffusion Counterfactual Generation with Semantic Abduction","date":"2025-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rajatrasal/diffusion-counterfactuals","path":"benchmarking/celeba_f1.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/benchmarking/celeba_f1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"42a6db49eebe4a0a","mcp_get_code":{"code_sha256":"42a6db49eebe4a0a"}},{"arxiv_id":"2506.07883","paper":"/paper/diffusion-counterfactual-generation-with","title":"Diffusion Counterfactual Generation with Semantic Abduction","date":"2025-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rajatrasal/diffusion-counterfactuals","path":"benchmarking/celeba_nto.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/benchmarking/celeba_nto.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f1703a9e979afe6b","mcp_get_code":{"code_sha256":"f1703a9e979afe6b"}},{"arxiv_id":"2506.05982","paper":"/paper/mca-bench-a-multimodal-benchmark-for","title":"MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks","date":"2025-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"noheadwuzonglin/mca-bench","path":"tojson/concattojson.py","file_url":"https://github.com/noheadwuzonglin/mca-bench/blob/HEAD/tojson/concattojson.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":"f393293b2dafecbb","mcp_get_code":{"code_sha256":"f393293b2dafecbb"}},{"arxiv_id":"2410.12178","paper":"/paper/model-balancing-helps-low-data-training-and","title":"Model Balancing Helps Low-data Training and Fine-tuning","date":"2024-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zihanghliu/modelbalancing","path":"sciml/pdebench/models/metrics.py","file_url":"https://github.com/zihanghliu/modelbalancing/blob/HEAD/sciml/pdebench/models/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c62bfade3b1b51b2","mcp_get_code":{"code_sha256":"c62bfade3b1b51b2"}},{"arxiv_id":"2401.03748","paper":"/paper/towards-efficient-communication-federated","title":"Towards Efficient Communication and Secure Federated Recommendation System via Low-rank Training","date":"2024-01-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nnhieu/colr-fedrec","path":"rec/evaluate.py","file_url":"https://github.com/nnhieu/colr-fedrec/blob/HEAD/rec/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d61f93e51b55c960","mcp_get_code":{"code_sha256":"d61f93e51b55c960"}},{"arxiv_id":"2312.16490","paper":"/paper/understanding-news-creation-intents-frame","title":"Exploring news intent and its application: A theory-driven approach","date":"2023-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ictmcg/newsint","path":"DMint/utils/utils.py","file_url":"https://github.com/ictmcg/newsint/blob/HEAD/DMint/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"73754ccda72a615e","mcp_get_code":{"code_sha256":"73754ccda72a615e"}},{"arxiv_id":"2311.05784","paper":"/paper/are-hierarchical-visual-representations","title":"Are \"Hierarchical\" Visual Representations Hierarchical?","date":"2023-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ethanlshen/hiernet","path":"cluster_analysis.py","file_url":"https://github.com/ethanlshen/hiernet/blob/HEAD/cluster_analysis.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"00dec92e5e70554d","mcp_get_code":{"code_sha256":"00dec92e5e70554d"}},{"arxiv_id":"2310.16587","paper":null,"title":"arXiv:2310.16587","date":null,"month_inferred_from_arxiv_id":"2023-10","title_source":null,"repo":"HKU-MedAI/bnn_uncertainty","path":"trainer/arht_bnn.py","file_url":"https://github.com/HKU-MedAI/bnn_uncertainty/blob/HEAD/trainer/arht_bnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"072d520b98edb368","mcp_get_code":{"code_sha256":"072d520b98edb368"}},{"arxiv_id":"2310.16121","paper":"/paper/19-parameters-is-all-you-need-tiny-neural","title":"19 Parameters Is All You Need: Tiny Neural Networks for Particle Physics","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abogatskiy/PELICAN-nano","path":"src/models/metrics_classifier.py","file_url":"https://github.com/abogatskiy/PELICAN-nano/blob/HEAD/src/models/metrics_classifier.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"816d22ea559f0e81","mcp_get_code":{"code_sha256":"816d22ea559f0e81"}},{"arxiv_id":"2309.01103","paper":"/paper/multi-relational-contrastive-learning-for","title":"Multi-Relational Contrastive Learning for Recommendation","date":"2023-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HKUDS/RCL","path":"evaluate.py","file_url":"https://github.com/HKUDS/RCL/blob/HEAD/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3b7c5f93a9103398","mcp_get_code":{"code_sha256":"3b7c5f93a9103398"}},{"arxiv_id":"2211.02250","paper":"/paper/real-time-target-sound-extraction","title":"Real-Time Target Sound Extraction","date":"2022-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vb000/waveformer","path":"src/training/non_causal_dcc_tf.py","file_url":"https://github.com/vb000/waveformer/blob/HEAD/src/training/non_causal_dcc_tf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6f25fb9c4e1a5cb1","mcp_get_code":{"code_sha256":"6f25fb9c4e1a5cb1"}},{"arxiv_id":"2204.00987","paper":"/paper/binsformer-revisiting-adaptive-bins-for","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","date":"2022-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhyever/monocular-depth-estimation-toolbox","path":"depth/core/evaluation/metrics.py","file_url":"https://github.com/zhyever/monocular-depth-estimation-toolbox/blob/HEAD/depth/core/evaluation/metrics.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":"8b0bbdc40ef410ff","mcp_get_code":{"code_sha256":"8b0bbdc40ef410ff"}},{"arxiv_id":"2104.14290","paper":"/paper/meta-learning-using-privileged-information","title":"Meta-learning using privileged information for dynamics","date":"2021-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bjd39/lupi-ndp","path":"code/utils.py","file_url":"https://github.com/bjd39/lupi-ndp/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":"c446626d707eda35","mcp_get_code":{"code_sha256":"c446626d707eda35"}},{"arxiv_id":"2008.03781","paper":"/paper/semeval-2020-task-8-memotion-analysis-the","title":"SemEval-2020 Task 8: Memotion Analysis -- The Visuo-Lingual Metaphor!","date":"2020-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"terenceylchow124/Meme-MultiModal","path":"utils/util.py","file_url":"https://github.com/terenceylchow124/Meme-MultiModal/blob/HEAD/utils/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d513f70a7aca634e","mcp_get_code":{"code_sha256":"d513f70a7aca634e"}},{"arxiv_id":"2007.06888","paper":"/paper/jsenet-joint-semantic-segmentation-and-edge","title":"JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds","date":"2020-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hzykent/JSENet","path":"JSENet_code/utils/metrics.py","file_url":"https://github.com/hzykent/JSENet/blob/HEAD/JSENet_code/utils/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5ffd29343f3e8e0d","mcp_get_code":{"code_sha256":"5ffd29343f3e8e0d"}},{"arxiv_id":"2007.05426","paper":"/paper/variational-inference-with-continuously","title":"Variational Inference with Continuously-Indexed Normalizing Flows","date":"2020-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anthonycaterini/cif-vi","path":"cif/metrics.py","file_url":"https://github.com/anthonycaterini/cif-vi/blob/HEAD/cif/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6ec56da05c30193f","mcp_get_code":{"code_sha256":"6ec56da05c30193f"}},{"arxiv_id":"1901.04085","paper":"/paper/passage-re-ranking-with-bert","title":"Passage Re-ranking with BERT","date":"2019-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nyu-dl/dl4marco-bert","path":"metrics.py","file_url":"https://github.com/nyu-dl/dl4marco-bert/blob/HEAD/metrics.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":"54573d73f899d22f","mcp_get_code":{"code_sha256":"54573d73f899d22f"}},{"arxiv_id":"1806.10758","paper":"/paper/evaluating-feature-importance-estimates","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","date":"2018-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"edpclau/ROAR-for-Scikit","path":".ipynb_checkpoints/ROAR-checkpoint.py","file_url":"https://github.com/edpclau/ROAR-for-Scikit/blob/HEAD/.ipynb_checkpoints/ROAR-checkpoint.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df9f26b424227c2f","mcp_get_code":{"code_sha256":"df9f26b424227c2f"}},{"arxiv_id":"ijcai2025_0870","paper":null,"title":"arXiv:ijcai2025_0870","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"XNetLab/ACRF-RNN","path":"Code/util4.py","file_url":"https://github.com/XNetLab/ACRF-RNN/blob/HEAD/Code/util4.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bada305a019a62bf","mcp_get_code":{"code_sha256":"bada305a019a62bf"}},{"arxiv_id":"aaai_32078","paper":null,"title":"arXiv:aaai_32078","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"YifanZhang-git/SKAPP","path":"src/data.py","file_url":"https://github.com/YifanZhang-git/SKAPP/blob/HEAD/src/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1738fbe25b16f83f","mcp_get_code":{"code_sha256":"1738fbe25b16f83f"}}]}