{"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/load-test-data","entry":"load_test_data","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":7,"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":20,"n_samples_ran":9,"n_samples_fingerprinted":0,"n_places":26,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":1,"ran":6,"unverified":11},"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":"2605.24286","paper":"/paper/arxiv-2605-24286","title":"Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"safety-research/faithful-cot","path":"eval/compute_faithfulness_from_generations.py","file_url":"https://github.com/safety-research/faithful-cot/blob/HEAD/eval/compute_faithfulness_from_generations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3dce64568cc99197","mcp_get_code":{"code_sha256":"3dce64568cc99197"}},{"arxiv_id":"2605.24286","paper":"/paper/arxiv-2605-24286","title":"Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"safety-research/faithful-cot","path":"eval/evaluate_hacking_ratio.py","file_url":"https://github.com/safety-research/faithful-cot/blob/HEAD/eval/evaluate_hacking_ratio.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c0afdae4075d5d9b","mcp_get_code":{"code_sha256":"c0afdae4075d5d9b"}},{"arxiv_id":"2507.11316","paper":null,"title":"arXiv:2507.11316","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"hr-jin/ConVA","path":"src/cav_gen.py","file_url":"https://github.com/hr-jin/ConVA/blob/HEAD/src/cav_gen.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cfedddf754d3385e","mcp_get_code":{"code_sha256":"cfedddf754d3385e"}},{"arxiv_id":"2504.17568","paper":"/paper/beyond-cox-models-assessing-the-performance","title":"Beyond Cox Models: Assessing the Performance of Machine-Learning Methods in Non-Proportional Hazards and Non-Linear Survival Analysis","date":"2025-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"compbiomed-unito/survhive","path":"survhive/util.py","file_url":"https://github.com/compbiomed-unito/survhive/blob/HEAD/survhive/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"179a976dea96da76","mcp_get_code":{"code_sha256":"179a976dea96da76"}},{"arxiv_id":"2406.06007","paper":"/paper/cares-a-comprehensive-benchmark-of","title":"CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"richard-peng-xia/CARES","path":"src/eval/eval_multichoice.py","file_url":"https://github.com/richard-peng-xia/CARES/blob/HEAD/src/eval/eval_multichoice.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"CC-BY-4.0","inline_ok":false,"code_sha256_prefix":"ed60b77b1a3f750d","mcp_get_code":{"code_sha256":"ed60b77b1a3f750d"}},{"arxiv_id":"2402.11349","paper":"/paper/tasks-that-language-models-don-t-learn","title":"Language Models Don't Learn the Physical Manifestation of Language","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brucewlee/h-test","path":"generate_h_test_training.py","file_url":"https://github.com/brucewlee/h-test/blob/HEAD/generate_h_test_training.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"810602b6e416585c","mcp_get_code":{"code_sha256":"810602b6e416585c"}},{"arxiv_id":"2402.08198","paper":"/paper/psc-cpi-multi-scale-protein-sequence","title":"PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Prediction","date":"2024-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lirongwu/psc-cpi","path":"code/dataset.py","file_url":"https://github.com/lirongwu/psc-cpi/blob/HEAD/code/dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"62050b71a90939d5","mcp_get_code":{"code_sha256":"62050b71a90939d5"}},{"arxiv_id":"2401.06853","paper":"/paper/large-language-models-can-learn-temporal","title":"Large Language Models Can Learn Temporal Reasoning","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiongsiheng/tg-llm","path":"src/Inference_in_context_learning.py","file_url":"https://github.com/xiongsiheng/tg-llm/blob/HEAD/src/Inference_in_context_learning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cce7996e68e164e1","mcp_get_code":{"code_sha256":"cce7996e68e164e1"}},{"arxiv_id":"2310.00813","paper":"/paper/oceannet-a-principled-neural-operator-based","title":"OceanNet: A principled neural operator-based digital twin for regional oceans","date":"2023-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"magray-ncsu/oceannet","path":"data_loader_SSH.py","file_url":"https://github.com/magray-ncsu/oceannet/blob/HEAD/data_loader_SSH.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4627e4b84652343d","mcp_get_code":{"code_sha256":"4627e4b84652343d"}},{"arxiv_id":"2310.00813","paper":"/paper/oceannet-a-principled-neural-operator-based","title":"OceanNet: A principled neural operator-based digital twin for regional oceans","date":"2023-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"magray-ncsu/oceannet","path":"data_loader_SSH_two_step.py","file_url":"https://github.com/magray-ncsu/oceannet/blob/HEAD/data_loader_SSH_two_step.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df2a0db95ac24611","mcp_get_code":{"code_sha256":"df2a0db95ac24611"}},{"arxiv_id":"2307.15247","paper":"/paper/is-this-model-reliable-for-everyone-testing","title":"Is this model reliable for everyone? Testing for strong calibration","date":"2023-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jjfeng/testing_strong_calibration","path":"src/subgroup_testing.py","file_url":"https://github.com/jjfeng/testing_strong_calibration/blob/HEAD/src/subgroup_testing.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7e1ca43fa2d13b29","mcp_get_code":{"code_sha256":"7e1ca43fa2d13b29"}},{"arxiv_id":"2305.15086","paper":"/paper/unpaired-image-to-image-translation-via-1","title":"Unpaired Image-to-Image Translation via Neural Schrödinger Bridge","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alpc91/NICE-GAN-pytorch","path":"utils.py","file_url":"https://github.com/alpc91/NICE-GAN-pytorch/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":"8d4ee7233484c7ee","mcp_get_code":{"code_sha256":"8d4ee7233484c7ee"}},{"arxiv_id":"2202.01875","paper":"/paper/rethinking-explainability-as-a-dialogue-a","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","date":"2022-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dylan-slack/talktomodel","path":"experiments/utils.py","file_url":"https://github.com/dylan-slack/talktomodel/blob/HEAD/experiments/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4ef7b9ed808f62a2","mcp_get_code":{"code_sha256":"4ef7b9ed808f62a2"}},{"arxiv_id":"2110.07682","paper":"/paper/sound-and-complete-neural-network-repair-with-1","title":"Sound and Complete Neural Network Repair with Minimality and Locality Guarantees","date":"2021-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bu-depend-lab/reassure","path":"ICLR/Experiments/ImageNet/ImageNetTools.py","file_url":"https://github.com/bu-depend-lab/reassure/blob/HEAD/ICLR/Experiments/ImageNet/ImageNetTools.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0414b3043c518f80","mcp_get_code":{"code_sha256":"0414b3043c518f80"}},{"arxiv_id":"2006.06676","paper":"/paper/training-generative-adversarial-networks-with-2","title":"Training Generative Adversarial Networks with Limited Data","date":"2020-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sangyun884/Face2Webtoon","path":"utils.py","file_url":"https://github.com/sangyun884/Face2Webtoon/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":"8d4ee7233484c7ee","mcp_get_code":{"code_sha256":"8d4ee7233484c7ee"}},{"arxiv_id":"2004.02088","paper":"/paper/feature-quantization-improves-gan-training","title":"Feature Quantization Improves GAN Training","date":"2020-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/UGATIT","path":"utils.py","file_url":"https://github.com/taki0112/UGATIT/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":"dcce1222c3697159","mcp_get_code":{"code_sha256":"dcce1222c3697159"}},{"arxiv_id":"1907.10830","paper":"/paper/u-gat-it-unsupervised-generative-attentional","title":"U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation","date":"2019-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"znxlwm/UGATIT-pytorch","path":"utils.py","file_url":"https://github.com/znxlwm/UGATIT-pytorch/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":"8d4ee7233484c7ee","mcp_get_code":{"code_sha256":"8d4ee7233484c7ee"}},{"arxiv_id":"1907.10830","paper":"/paper/u-gat-it-unsupervised-generative-attentional","title":"U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation","date":"2019-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WuZhewei/my_First_GAN_tryout","path":"utils.py","file_url":"https://github.com/WuZhewei/my_First_GAN_tryout/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":"dcce1222c3697159","mcp_get_code":{"code_sha256":"dcce1222c3697159"}},{"arxiv_id":"1907.10830","paper":"/paper/u-gat-it-unsupervised-generative-attentional","title":"U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation","date":"2019-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minivision-ai/photo2cartoon","path":"utils/utils.py","file_url":"https://github.com/minivision-ai/photo2cartoon/blob/HEAD/utils/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2723b22ce3e5bcf","mcp_get_code":{"code_sha256":"f2723b22ce3e5bcf"}},{"arxiv_id":"1905.01270","paper":"/paper/drit-diverse-image-to-image-translation-via","title":"DRIT++: Diverse Image-to-Image Translation via Disentangled Representations","date":"2019-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/DRIT-Tensorflow","path":"utils.py","file_url":"https://github.com/taki0112/DRIT-Tensorflow/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":"8d4ee7233484c7ee","mcp_get_code":{"code_sha256":"8d4ee7233484c7ee"}},{"arxiv_id":"1812.09912","paper":"/paper/image-to-image-translation-via-group-wise","title":"Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation","date":"2018-12-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/GDWCT-Tensorflow","path":"utils.py","file_url":"https://github.com/taki0112/GDWCT-Tensorflow/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":"bb95d212dc8441e6","mcp_get_code":{"code_sha256":"bb95d212dc8441e6"}},{"arxiv_id":"1807.11164","paper":"/paper/shufflenet-v2-practical-guidelines-for","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","date":"2018-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CellProfiling/HPA-Special-Prize","path":"inference/special_eval.py","file_url":"https://github.com/CellProfiling/HPA-Special-Prize/blob/HEAD/inference/special_eval.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":"e5b4c800ffeec6c5","mcp_get_code":{"code_sha256":"e5b4c800ffeec6c5"}},{"arxiv_id":"1804.04732","paper":"/paper/multimodal-unsupervised-image-to-image","title":"Multimodal Unsupervised Image-to-Image Translation","date":"2018-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/MUNIT-Tensorflow","path":"utils.py","file_url":"https://github.com/taki0112/MUNIT-Tensorflow/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":"bb95d212dc8441e6","mcp_get_code":{"code_sha256":"bb95d212dc8441e6"}},{"arxiv_id":"1703.00848","paper":"/paper/unsupervised-image-to-image-translation","title":"Unsupervised Image-to-Image Translation Networks","date":"2017-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/UNIT-Tensorflow","path":"DatasetAPI/utils.py","file_url":"https://github.com/taki0112/UNIT-Tensorflow/blob/HEAD/DatasetAPI/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d4ee7233484c7ee","mcp_get_code":{"code_sha256":"8d4ee7233484c7ee"}},{"arxiv_id":"1703.00848","paper":"/paper/unsupervised-image-to-image-translation","title":"Unsupervised Image-to-Image Translation Networks","date":"2017-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/UNIT-Tensorflow","path":"utils.py","file_url":"https://github.com/taki0112/UNIT-Tensorflow/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":"c35237a13dc4f943","mcp_get_code":{"code_sha256":"c35237a13dc4f943"}},{"arxiv_id":"1603.09320","paper":"/paper/efficient-and-robust-approximate-nearest","title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","date":"2016-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kakao/n2","path":"benchmarks/benchmark_script.py","file_url":"https://github.com/kakao/n2/blob/HEAD/benchmarks/benchmark_script.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":"4e54de2be24f817c","mcp_get_code":{"code_sha256":"4e54de2be24f817c"}}]}