{"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/precision","entry":"precision","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":25,"n_papers_ran":11,"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":24,"n_samples_ran":8,"n_samples_fingerprinted":1,"n_places":28,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":7,"unverified":16},"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":"2608.07548","paper":"/paper/arxiv-2608-07548","title":"SC 2 -WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"sunrise-ikun/SC2_WM","path":"utils_p/metrics.py","file_url":"https://github.com/sunrise-ikun/SC2_WM/blob/HEAD/utils_p/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"035dc40fdafe0275","mcp_get_code":{"code_sha256":"035dc40fdafe0275"}},{"arxiv_id":"2601.14732","paper":"/paper/arxiv-2601-14732","title":"DeepMoLM: Leveraging Visual and Geometric Structural Information for Molecule-Text Modeling","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"1anj/DeepMoLM","path":"llava/eval/eval_model_loc.py","file_url":"https://github.com/1anj/DeepMoLM/blob/HEAD/llava/eval/eval_model_loc.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":"17bd792b6162fc98","mcp_get_code":{"code_sha256":"17bd792b6162fc98"}},{"arxiv_id":"2508.00649","paper":"/paper/arxiv-2508-00649","title":"Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"Gandolfczjh/APDE","path":"defense/SegmentAndComplete/dice_loss.py","file_url":"https://github.com/Gandolfczjh/APDE/blob/HEAD/defense/SegmentAndComplete/dice_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0a217b21ea93d8c9","mcp_get_code":{"code_sha256":"0a217b21ea93d8c9"}},{"arxiv_id":"2506.23468","paper":"/paper/navmorph-a-self-evolving-world-model-for","title":"NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments","date":"2025-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Feliciaxyao/NavMorph","path":"utils_p/metrics.py","file_url":"https://github.com/Feliciaxyao/NavMorph/blob/HEAD/utils_p/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"035dc40fdafe0275","mcp_get_code":{"code_sha256":"035dc40fdafe0275"}},{"arxiv_id":"2502.19941","paper":"/paper/alleviating-distribution-shift-in-synthetic","title":"Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NJUNLP/njuqe","path":"njuqe/utils.py","file_url":"https://github.com/NJUNLP/njuqe/blob/HEAD/njuqe/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"463dec4b9e606031","mcp_get_code":{"code_sha256":"463dec4b9e606031"}},{"arxiv_id":"2502.19941","paper":"/paper/alleviating-distribution-shift-in-synthetic","title":"Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NJUNLP/njuqe","path":"njuqe/criterions/qe_metric.py","file_url":"https://github.com/NJUNLP/njuqe/blob/HEAD/njuqe/criterions/qe_metric.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"758494073a00f760","mcp_get_code":{"code_sha256":"758494073a00f760"}},{"arxiv_id":"2412.17336","paper":"/paper/apex-2-adaptive-and-extreme-summarization-for","title":"APEX$^2$: Adaptive and Extreme Summarization for Personalized Knowledge Graphs","date":"2024-12-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iDEA-iSAIL-Lab-UIUC/APEX","path":"code/src/metrics.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c610c9ba3b321e3d","mcp_get_code":{"code_sha256":"c610c9ba3b321e3d"}},{"arxiv_id":"2410.09299","paper":"/paper/hierarchical-uncertainty-estimation-for-1","title":"Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging","date":"2024-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HuXiaoling/Regre4Regis","path":"metrics.py","file_url":"https://github.com/HuXiaoling/Regre4Regis/blob/HEAD/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"035dc40fdafe0275","mcp_get_code":{"code_sha256":"035dc40fdafe0275"}},{"arxiv_id":"2406.11612","paper":"/paper/long-code-arena-a-set-of-benchmarks-for-long","title":"Long Code Arena: a Set of Benchmarks for Long-Context Code Models","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jetbrains-research/lca-baselines","path":"bug_localization/src/baselines/metrics/quality_metrics.py","file_url":"https://github.com/jetbrains-research/lca-baselines/blob/HEAD/bug_localization/src/baselines/metrics/quality_metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2026474821ea5965","mcp_get_code":{"code_sha256":"2026474821ea5965"}},{"arxiv_id":"2403.20078","paper":"/paper/negative-label-guided-ood-detection-with","title":"Negative Label Guided OOD Detection with Pretrained Vision-Language Models","date":"2024-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmlr-group/NegLabel","path":"mmcls/core/evaluation/eval_metrics.py","file_url":"https://github.com/tmlr-group/NegLabel/blob/HEAD/mmcls/core/evaluation/eval_metrics.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":"8555810d566238b0","mcp_get_code":{"code_sha256":"8555810d566238b0"}},{"arxiv_id":"2402.01207","paper":"/paper/efficient-causal-graph-discovery-using-large","title":"Efficient Causal Graph Discovery Using Large Language Models","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"superkaiba/causal-llm-bfs","path":"algs/llm/utils.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/algs/llm/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ab810b4b69cebe75","mcp_get_code":{"code_sha256":"ab810b4b69cebe75"}},{"arxiv_id":"2402.01207","paper":"/paper/efficient-causal-graph-discovery-using-large","title":"Efficient Causal Graph Discovery Using Large Language Models","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"superkaiba/causal-llm-bfs","path":"metrics.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b1a73044ab13bc1a","mcp_get_code":{"code_sha256":"b1a73044ab13bc1a"}},{"arxiv_id":"2401.14168","paper":"/paper/vivim-a-video-vision-mamba-for-medical-video","title":"Vivim: a Video Vision Mamba for Medical Video Segmentation","date":"2024-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scott-yjyang/vivim","path":"misc2.py","file_url":"https://github.com/scott-yjyang/vivim/blob/HEAD/misc2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a0be218082173339","mcp_get_code":{"code_sha256":"a0be218082173339"}},{"arxiv_id":"2312.13772","paper":"/paper/on-task-performance-and-model-calibration","title":"On Task Performance and Model Calibration with Supervised and Self-Ensembled In-Context Learning","date":"2023-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridgeltl/ensembled-sicl","path":"utils/evaluator.py","file_url":"https://github.com/cambridgeltl/ensembled-sicl/blob/HEAD/utils/evaluator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"73e30f54a5973543","mcp_get_code":{"code_sha256":"73e30f54a5973543"}},{"arxiv_id":"2310.10696","paper":"/paper/robust-collaborative-filtering-to-popularity","title":"Robust Collaborative Filtering to Popularity Distribution Shift","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anzhang314/popgo","path":"evaluator/backend/python/metric.py","file_url":"https://github.com/anzhang314/popgo/blob/HEAD/evaluator/backend/python/metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f0a0f53980ed3daf","mcp_get_code":{"code_sha256":"f0a0f53980ed3daf"}},{"arxiv_id":"2212.04497","paper":"/paper/unetr-delving-into-efficient-and-accurate-3d","title":"UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation","date":"2022-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amshaker/unetr_plus_plus","path":"unetr_pp/evaluation/metrics.py","file_url":"https://github.com/amshaker/unetr_plus_plus/blob/HEAD/unetr_pp/evaluation/metrics.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":"035dc40fdafe0275","mcp_get_code":{"code_sha256":"035dc40fdafe0275"}},{"arxiv_id":"2107.06099","paper":"/paper/drug-target-interaction-prediction-with-graph","title":"Drug-Target Interaction Prediction with Graph Attention networks","date":"2021-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Haiyang-W/DTI-GRAPH","path":"utils.py","file_url":"https://github.com/Haiyang-W/DTI-GRAPH/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":"4bede4f0f2850885","mcp_get_code":{"code_sha256":"4bede4f0f2850885"}},{"arxiv_id":"2010.02803","paper":"/paper/a-transformer-based-framework-for-1","title":"A Transformer-based Framework for Multivariate Time Series Representation Learning","date":"2020-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gzerveas/mvts_transformer","path":"src/utils/analysis.py","file_url":"https://github.com/gzerveas/mvts_transformer/blob/HEAD/src/utils/analysis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"839af27815f6fa38","mcp_get_code":{"code_sha256":"839af27815f6fa38"}},{"arxiv_id":"2006.15222","paper":"/paper/bertology-meets-biology-interpreting","title":"BERTology Meets Biology: Interpreting Attention in Protein Language Models","date":"2020-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/provis","path":"protein_attention/probing/metrics.py","file_url":"https://github.com/salesforce/provis/blob/HEAD/protein_attention/probing/metrics.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"5404d253452b6807","mcp_get_code":{"code_sha256":"5404d253452b6807"}},{"arxiv_id":"2004.14356","paper":"/paper/axcell-automatic-extraction-of-results-from","title":"AxCell: Automatic Extraction of Results from Machine Learning Papers","date":"2020-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"paperswithcode/axcell","path":"axcell/helpers/evaluate.py","file_url":"https://github.com/paperswithcode/axcell/blob/HEAD/axcell/helpers/evaluate.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":"7fc6d3a39db0d9de","mcp_get_code":{"code_sha256":"7fc6d3a39db0d9de"}},{"arxiv_id":"1902.00153","paper":"/paper/deep-triplet-quantization","title":"Deep Triplet Quantization","date":"2019-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thulab/DeepHash","path":"DeepHash/evaluation/load_and_predict.py","file_url":"https://github.com/thulab/DeepHash/blob/HEAD/DeepHash/evaluation/load_and_predict.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9901bdfb8b1ece6a","mcp_get_code":{"code_sha256":"9901bdfb8b1ece6a"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haydlite/sparse-bert-ner","path":"old_version/tf_metrics.py","file_url":"https://github.com/haydlite/sparse-bert-ner/blob/HEAD/old_version/tf_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"46fcc6e1de355e47","mcp_get_code":{"code_sha256":"46fcc6e1de355e47"}},{"arxiv_id":"1809.10486","paper":"/paper/nnu-net-self-adapting-framework-for-u-net","title":"nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation","date":"2018-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"justld/nnunet_paddle","path":"nnunet_tools/metrics.py","file_url":"https://github.com/justld/nnunet_paddle/blob/HEAD/nnunet_tools/metrics.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":"035dc40fdafe0275","mcp_get_code":{"code_sha256":"035dc40fdafe0275"}},{"arxiv_id":"1710.09829","paper":"/paper/dynamic-routing-between-capsules","title":"Dynamic Routing Between Capsules","date":"2017-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lalonderodney/SegCaps","path":"metrics.py","file_url":"https://github.com/lalonderodney/SegCaps/blob/HEAD/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":"7f6b9d28c90431fb","mcp_get_code":{"code_sha256":"7f6b9d28c90431fb"}},{"arxiv_id":"1703.06870","paper":"/paper/mask-r-cnn","title":"Mask R-CNN","date":"2017-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AKASH2907/bird-species-classification","path":"inception_resnet_v2_finetune.py","file_url":"https://github.com/AKASH2907/bird-species-classification/blob/HEAD/inception_resnet_v2_finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b0079394b94f6c41","mcp_get_code":{"code_sha256":"b0079394b94f6c41"}},{"arxiv_id":"1703.06870","paper":"/paper/mask-r-cnn","title":"Mask R-CNN","date":"2017-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AKASH2907/bird-species-classification","path":"evaluate.py","file_url":"https://github.com/AKASH2907/bird-species-classification/blob/HEAD/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31724c8757cac523","mcp_get_code":{"code_sha256":"31724c8757cac523"}},{"arxiv_id":"1510.01784","paper":"/paper/vbpr-visual-bayesian-personalized-ranking","title":"VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback","date":"2015-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ialab-puc/CuratorNet","path":"src/MetricsUtils.py","file_url":"https://github.com/ialab-puc/CuratorNet/blob/HEAD/src/MetricsUtils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"92cec5bb48aca1b3","mcp_get_code":{"code_sha256":"92cec5bb48aca1b3"}},{"arxiv_id":"0705.2011","paper":"/paper/multi-dimensional-recurrent-neural-networks","title":"Multi-Dimensional Recurrent Neural Networks","date":"2007-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jzbjyb/rri_match","path":"metric.py","file_url":"https://github.com/jzbjyb/rri_match/blob/HEAD/metric.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":"2007c4e9c81aaf2c","mcp_get_code":{"code_sha256":"2007c4e9c81aaf2c"}}]}