{"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/prediction","entry":"prediction","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":11,"n_papers_ran":6,"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":11,"n_samples_ran":6,"n_samples_fingerprinted":2,"n_places":11,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":1,"ran":2,"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":"2506.15201","paper":null,"title":"arXiv:2506.15201","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"JiayinXu5499/PSIC","path":"loss/prediction.py","file_url":"https://github.com/JiayinXu5499/PSIC/blob/HEAD/loss/prediction.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"79e0e21fd9372961","mcp_get_code":{"code_sha256":"79e0e21fd9372961"}},{"arxiv_id":"2410.13080","paper":"/paper/graph-constrained-reasoning-faithful","title":"Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models","date":"2024-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rmanluo/graph-constrained-reasoning","path":"workflow/predict_paths_and_answers.py","file_url":"https://github.com/rmanluo/graph-constrained-reasoning/blob/HEAD/workflow/predict_paths_and_answers.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bcfb6bdefa6b543","mcp_get_code":{"code_sha256":"0bcfb6bdefa6b543"}},{"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5351b0a2e6494ed5","mcp_get_code":{"code_sha256":"5351b0a2e6494ed5"}},{"arxiv_id":"2403.06014","paper":"/paper/hard-label-based-small-query-black-box","title":"Hard-label based Small Query Black-box Adversarial Attack","date":"2024-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jpark04-qub/sqba","path":"attacks.py","file_url":"https://github.com/jpark04-qub/sqba/blob/HEAD/attacks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ce868ca72a63358","mcp_get_code":{"code_sha256":"7ce868ca72a63358"}},{"arxiv_id":"2311.15614","paper":"/paper/freeal-towards-human-free-active-learning-in","title":"FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models","date":"2023-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Justherozen/FreeAL","path":"self_training_slm/utils/utils.py","file_url":"https://github.com/Justherozen/FreeAL/blob/HEAD/self_training_slm/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"551cc564f2aea34d","mcp_get_code":{"code_sha256":"551cc564f2aea34d"}},{"arxiv_id":"2306.03030","paper":"/paper/benchmarking-large-language-models-on-cmexam","title":"Benchmarking Large Language Models on CMExam -- A Comprehensive Chinese Medical Exam Dataset","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"williamliujl/cmexam","path":"src/evaluation/evaluate_chatglm_result.py","file_url":"https://github.com/williamliujl/cmexam/blob/HEAD/src/evaluation/evaluate_chatglm_result.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":"2dee8b79c911b143","mcp_get_code":{"code_sha256":"2dee8b79c911b143"}},{"arxiv_id":"2302.02169","paper":"/paper/how-many-and-which-training-points-would-need","title":"How Many and Which Training Points Would Need to be Removed to Flip this Prediction?","date":"2023-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ecielyang/smallest_set","path":"recursive.py","file_url":"https://github.com/ecielyang/smallest_set/blob/HEAD/recursive.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6154bee9b6ca26bd","mcp_get_code":{"code_sha256":"6154bee9b6ca26bd"}},{"arxiv_id":"2005.11079","paper":"/paper/graph-random-neural-network","title":"Graph Random Neural Network for Semi-Supervised Learning on Graphs","date":"2020-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junzhuang-code/graphss","path":"graphSS/models_SS.py","file_url":"https://github.com/junzhuang-code/graphss/blob/HEAD/graphSS/models_SS.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bce344d99820bd8","mcp_get_code":{"code_sha256":"3bce344d99820bd8"}},{"arxiv_id":"1901.08394","paper":"/paper/application-of-decision-rules-for-handling","title":"Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation","date":"2019-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"robin-chan/decision-rules","path":"scripts-predict/predict.py","file_url":"https://github.com/robin-chan/decision-rules/blob/HEAD/scripts-predict/predict.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4fa6717c9d8a2be2","mcp_get_code":{"code_sha256":"4fa6717c9d8a2be2"}},{"arxiv_id":"1703.04009","paper":"/paper/automated-hate-speech-detection-and-the","title":"Automated Hate Speech Detection and the Problem of Offensive Language","date":"2017-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"renuka-fernando/sinhalese_language_racism_detection","path":"classifier/python/classifier/validate.py","file_url":"https://github.com/renuka-fernando/sinhalese_language_racism_detection/blob/HEAD/classifier/python/classifier/validate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3a614652957cc69a","mcp_get_code":{"code_sha256":"3a614652957cc69a"}},{"arxiv_id":"2024.findings-emnlp.253","paper":null,"title":"arXiv:2024.findings-emnlp.253","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"WilliamZR/ProTrix","path":"evaluation/eval_with_llm.py","file_url":"https://github.com/WilliamZR/ProTrix/blob/HEAD/evaluation/eval_with_llm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a142eefafa8c89eb","mcp_get_code":{"code_sha256":"a142eefafa8c89eb"}}]}