{"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/compute-auroc","entry":"compute_auroc","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":14,"n_papers_ran":9,"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":12,"n_samples_ran":7,"n_samples_fingerprinted":5,"n_places":14,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":2,"ran":5,"unverified":5},"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":"2609.03677","paper":"/paper/arxiv-2609-03677","title":"Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"KIT-MRT/AD-Diff","path":"components/ranker.py","file_url":"https://github.com/KIT-MRT/AD-Diff/blob/HEAD/components/ranker.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"45d2d6219284199f","mcp_get_code":{"code_sha256":"45d2d6219284199f"}},{"arxiv_id":"2606.11063","paper":"/paper/arxiv-2606-11063","title":"CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"JoachimSchaeffer/CIAware-Bench","path":"cia/analysis/metrics.py","file_url":"https://github.com/JoachimSchaeffer/CIAware-Bench/blob/HEAD/cia/analysis/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0aa1c47293980174","mcp_get_code":{"code_sha256":"0aa1c47293980174"}},{"arxiv_id":"2605.06673","paper":"/paper/arxiv-2605-06673","title":"Domain-level metacognitive monitoring in frontier LLMs: A 33-model atlas","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"synthiumjp/validity-scaling-llm","path":"analysis/selective_prediction_analysis.py","file_url":"https://github.com/synthiumjp/validity-scaling-llm/blob/HEAD/analysis/selective_prediction_analysis.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"209e6b034ddb8641","mcp_get_code":{"code_sha256":"209e6b034ddb8641"}},{"arxiv_id":"2410.11397","paper":"/paper/foogd-federated-collaboration-for-both-out-of","title":"FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XeniaLLL/FOOGD-main","path":"src/utils/accuracy.py","file_url":"https://github.com/XeniaLLL/FOOGD-main/blob/HEAD/src/utils/accuracy.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"581a8583346c6d6e","mcp_get_code":{"code_sha256":"581a8583346c6d6e"}},{"arxiv_id":"2410.10744","paper":"/paper/adversarially-robust-out-of-distribution","title":"Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AdaptiveMotorControlLab/AROS","path":"aros_node/evaluate.py","file_url":"https://github.com/AdaptiveMotorControlLab/AROS/blob/HEAD/aros_node/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"986e9e947c04d66f","mcp_get_code":{"code_sha256":"986e9e947c04d66f"}},{"arxiv_id":"2406.19501","paper":"/paper/monitoring-latent-world-states-in-language","title":"Monitoring Latent World States in Language Models with Propositional Probes","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiahai-feng/prop-probes-iclr","path":"src/coref/probes/evaluate.py","file_url":"https://github.com/jiahai-feng/prop-probes-iclr/blob/HEAD/src/coref/probes/evaluate.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c9fad5291f826959","mcp_get_code":{"code_sha256":"c9fad5291f826959"}},{"arxiv_id":"2402.13213","paper":"/paper/softmax-probabilities-mostly-predict-large","title":"Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bplaut/softmax-probs-predict-llm-correctness","path":"plotting_functions.py","file_url":"https://github.com/bplaut/softmax-probs-predict-llm-correctness/blob/HEAD/plotting_functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4e2deaf4a017eea3","mcp_get_code":{"code_sha256":"4e2deaf4a017eea3"}},{"arxiv_id":"2312.02974","paper":"/paper/describing-differences-in-image-sets-with","title":"Describing Differences in Image Sets with Natural Language","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"understanding-visual-datasets/visdiff","path":"components/ranker.py","file_url":"https://github.com/understanding-visual-datasets/visdiff/blob/HEAD/components/ranker.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"45d2d6219284199f","mcp_get_code":{"code_sha256":"45d2d6219284199f"}},{"arxiv_id":"2310.07511","paper":"/paper/a-unified-remote-sensing-anomaly-detector","title":"Learning a Cross-modality Anomaly Detector for Remote Sensing Imagery","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jingtao-li-cver/uniadrs","path":"metrics/auroc.py","file_url":"https://github.com/jingtao-li-cver/uniadrs/blob/HEAD/metrics/auroc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f0d319b4958b3d0f","mcp_get_code":{"code_sha256":"f0d319b4958b3d0f"}},{"arxiv_id":"2309.16519","paper":"/paper/atomsurf-surface-representation-for-learning","title":"AtomSurf : Surface Representation for Learning on Protein Structures","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vincentx15/atom2d","path":"atom2d/holoprot/pl_module.py","file_url":"https://github.com/vincentx15/atom2d/blob/HEAD/atom2d/holoprot/pl_module.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ebaf20fa3e67c3d","mcp_get_code":{"code_sha256":"7ebaf20fa3e67c3d"}},{"arxiv_id":"2208.10992","paper":"/paper/unsupervised-anomaly-localization-with","title":"Unsupervised Anomaly Localization with Structural Feature-Autoencoders","date":"2022-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"felime/feature-autoencoder","path":"fae/utils/evaluation.py","file_url":"https://github.com/felime/feature-autoencoder/blob/HEAD/fae/utils/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a53a84989fef934c","mcp_get_code":{"code_sha256":"a53a84989fef934c"}},{"arxiv_id":"2202.03299","paper":"/paper/training-ood-detectors-in-their-natural","title":"Training OOD Detectors in their Natural Habitats","date":"2022-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jkatzsam/woods_ood","path":"CIFAR/plot_results.py","file_url":"https://github.com/jkatzsam/woods_ood/blob/HEAD/CIFAR/plot_results.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"581a8583346c6d6e","mcp_get_code":{"code_sha256":"581a8583346c6d6e"}},{"arxiv_id":"2109.06827","paper":"/paper/types-of-out-of-distribution-texts-and-how-to","title":"Types of Out-of-Distribution Texts and How to Detect Them","date":"2021-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uditarora/ood-text-emnlp","path":"utils.py","file_url":"https://github.com/uditarora/ood-text-emnlp/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":"72563a8679267472","mcp_get_code":{"code_sha256":"72563a8679267472"}},{"arxiv_id":"1902.10191","paper":"/paper/evolvegcn-evolving-graph-convolutional","title":"EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs","date":"2019-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunnan191/evisec","path":"detector.py","file_url":"https://github.com/sunnan191/evisec/blob/HEAD/detector.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0544ac6dc2820f74","mcp_get_code":{"code_sha256":"0544ac6dc2820f74"}}]}