{"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/evaluate-predictions","entry":"evaluate_predictions","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":9,"n_papers_ran":5,"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":8,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":2,"unverified":4},"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":"2604.20806","paper":"/paper/arxiv-2604-20806","title":"OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"LightChen233/OMIBench","path":"omi_bench.py","file_url":"https://github.com/LightChen233/OMIBench/blob/HEAD/omi_bench.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d0c9313b7823bdb4","mcp_get_code":{"code_sha256":"d0c9313b7823bdb4"}},{"arxiv_id":"2510.08630","paper":"/paper/arxiv-2510-08630","title":"ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"JingbiaoMei/ExPO-HM","path":"eval/inference/qwen2_hm_inference_vllm.py","file_url":"https://github.com/JingbiaoMei/ExPO-HM/blob/HEAD/eval/inference/qwen2_hm_inference_vllm.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":"bfc48666e7213f2d","mcp_get_code":{"code_sha256":"bfc48666e7213f2d"}},{"arxiv_id":"2405.18942","paper":"/paper/verifiably-robust-conformal-prediction","title":"Verifiably Robust Conformal Prediction","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ddv-lab/Verifiably_Robust_CP","path":"VRCP_Classification/VRCP/experiment.py","file_url":"https://github.com/ddv-lab/Verifiably_Robust_CP/blob/HEAD/VRCP_Classification/VRCP/experiment.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"03cd6687b1d4c3be","mcp_get_code":{"code_sha256":"03cd6687b1d4c3be"}},{"arxiv_id":"2404.19651","paper":"/paper/provably-robust-conformal-prediction-with","title":"Provably Robust Conformal Prediction with Improved Efficiency","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trustworthy-ml-lab/provably-robust-conformal-prediction","path":"code/utils.py","file_url":"https://github.com/trustworthy-ml-lab/provably-robust-conformal-prediction/blob/HEAD/code/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6b2508c0c43f7dee","mcp_get_code":{"code_sha256":"6b2508c0c43f7dee"}},{"arxiv_id":"2401.14490","paper":"/paper/longhealth-a-question-answering-benchmark","title":"LongHealth: A Question Answering Benchmark with Long Clinical Documents","date":"2024-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kbressem/longhealth","path":"eval/evaluate_accuracy_task1.py","file_url":"https://github.com/kbressem/longhealth/blob/HEAD/eval/evaluate_accuracy_task1.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9c88fd4d6b60acdc","mcp_get_code":{"code_sha256":"9c88fd4d6b60acdc"}},{"arxiv_id":"2312.17243","paper":"/paper/unsupervised-universal-image-segmentation","title":"Unsupervised Universal Image Segmentation","date":"2023-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"u2seg/u2seg","path":"u2seg/Instance_Clustering/usl-t_pretraining/usl-t-imagenet-pretrain.py","file_url":"https://github.com/u2seg/u2seg/blob/HEAD/u2seg/Instance_Clustering/usl-t_pretraining/usl-t-imagenet-pretrain.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":"23374018ab9941b5","mcp_get_code":{"code_sha256":"23374018ab9941b5"}},{"arxiv_id":"2110.03006","paper":"/paper/data-centric-semi-supervised-learning","title":"Unsupervised Selective Labeling for More Effective Semi-Supervised Learning","date":"2021-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TonyLianLong/UnsupervisedSelectiveLabeling","path":"usl-t_pretraining/usl-t-imagenet-pretrain.py","file_url":"https://github.com/TonyLianLong/UnsupervisedSelectiveLabeling/blob/HEAD/usl-t_pretraining/usl-t-imagenet-pretrain.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23374018ab9941b5","mcp_get_code":{"code_sha256":"23374018ab9941b5"}},{"arxiv_id":"2109.10686","paper":"/paper/scale-efficiently-insights-from-pre-training","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","date":"2021-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aaronmueller/emergent-syntax","path":"models/pred_eval.py","file_url":"https://github.com/aaronmueller/emergent-syntax/blob/HEAD/models/pred_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0c5a6c34f4b57d8b","mcp_get_code":{"code_sha256":"0c5a6c34f4b57d8b"}},{"arxiv_id":"1904.01561","paper":"/paper/are-learned-molecular-representations-ready","title":"Analyzing Learned Molecular Representations for Property Prediction","date":"2019-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tingweidaniel/chemprop_atomicfp_save_depth_final","path":"chemprop/train/evaluate.py","file_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final/blob/HEAD/chemprop/train/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"37db24e9e0f38c01","mcp_get_code":{"code_sha256":"37db24e9e0f38c01"}}]}