{"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/make-qid-to-has-ans","entry":"make_qid_to_has_ans","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":12,"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":4,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":15,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":2},"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":"2608.08024","paper":"/paper/arxiv-2608-08024","title":"Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"zazamrykh/internal_probing","path":"src/dataset/squad_eval.py","file_url":"https://github.com/zazamrykh/internal_probing/blob/HEAD/src/dataset/squad_eval.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":"e91c44f5680827e2","mcp_get_code":{"code_sha256":"e91c44f5680827e2"}},{"arxiv_id":"2311.09821","paper":"/paper/towards-robust-temporal-reasoning-of-large","title":"Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nusnlp/complex-tr","path":"prompt_experiment/sem_metric/evaluate.py","file_url":"https://github.com/nusnlp/complex-tr/blob/HEAD/prompt_experiment/sem_metric/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"41e5ac23be97994b","mcp_get_code":{"code_sha256":"41e5ac23be97994b"}},{"arxiv_id":"2308.16475","paper":"/paper/transformer-compression-via-subspace","title":"$\\rm SP^3$: Enhancing Structured Pruning via PCA Projection","date":"2023-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hyx1999/sp3","path":"bert/metric/squad_v2.py","file_url":"https://github.com/hyx1999/sp3/blob/HEAD/bert/metric/squad_v2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"41e5ac23be97994b","mcp_get_code":{"code_sha256":"41e5ac23be97994b"}},{"arxiv_id":"2306.06191","paper":"/paper/open-data-on-github-unlocking-the-potential","title":"Open Data on GitHub: Unlocking the Potential of AI","date":"2023-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rajpurkar/SQuAD-explorer","path":"evaluate-v2.0.py","file_url":"https://github.com/rajpurkar/SQuAD-explorer/blob/HEAD/evaluate-v2.0.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":"e91c44f5680827e2","mcp_get_code":{"code_sha256":"e91c44f5680827e2"}},{"arxiv_id":"2205.06435","paper":"/paper/tie-topological-information-enhanced","title":"TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages","date":"2022-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"x-lance/tie","path":"src/utils_evaluate.py","file_url":"https://github.com/x-lance/tie/blob/HEAD/src/utils_evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ff051538e6b183e","mcp_get_code":{"code_sha256":"3ff051538e6b183e"}},{"arxiv_id":"2010.08983","paper":"/paper/towards-interpreting-bert-for-reading","title":"Towards Interpreting BERT for Reading Comprehension Based QA","date":"2020-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iitmnlp/BERT-Analysis-RCQA","path":"bert/evaluate-v2.0.py","file_url":"https://github.com/iitmnlp/BERT-Analysis-RCQA/blob/HEAD/bert/evaluate-v2.0.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":"e91c44f5680827e2","mcp_get_code":{"code_sha256":"e91c44f5680827e2"}},{"arxiv_id":"2006.12467","paper":"/paper/limits-to-depth-efficiencies-of-self","title":"The Depth-to-Width Interplay in Self-Attention","date":"2020-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uf-hobi-informatics-lab/GatorTron","path":"finetuning/qa/evaluate-squad-v2.0.py","file_url":"https://github.com/uf-hobi-informatics-lab/GatorTron/blob/HEAD/finetuning/qa/evaluate-squad-v2.0.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":"e91c44f5680827e2","mcp_get_code":{"code_sha256":"e91c44f5680827e2"}},{"arxiv_id":"2004.13922","paper":"/paper/revisiting-pre-trained-models-for-chinese","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","date":"2020-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ymcui/Chinese-PreTrained-XLNet","path":"src/squad_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/squad_utils.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":"e91c44f5680827e2","mcp_get_code":{"code_sha256":"e91c44f5680827e2"}},{"arxiv_id":"1911.02984","paper":"/paper/the-techqa-dataset","title":"The TechQA Dataset","date":"2019-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibm/techqa","path":"techqa_evaluation.py","file_url":"https://github.com/ibm/techqa/blob/HEAD/techqa_evaluation.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":"b63023126d0278b8","mcp_get_code":{"code_sha256":"b63023126d0278b8"}},{"arxiv_id":"1910.01244","paper":"/paper/linking-artificial-and-human-neural","title":"Linking artificial and human neural representations of language","date":"2019-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hans/nn-decoding","path":"bin/eval_squad.py","file_url":"https://github.com/hans/nn-decoding/blob/HEAD/bin/eval_squad.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":"e91c44f5680827e2","mcp_get_code":{"code_sha256":"e91c44f5680827e2"}},{"arxiv_id":"1908.08962","paper":"/paper/well-read-students-learn-better-the-impact-of","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","date":"2019-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"somiltg/bert","path":"evaluate-v2.0.py","file_url":"https://github.com/somiltg/bert/blob/HEAD/evaluate-v2.0.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":"e91c44f5680827e2","mcp_get_code":{"code_sha256":"e91c44f5680827e2"}},{"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":"Zehui127/SQUAD_BERT","path":"SQUAD/evaluate-v2.0.py","file_url":"https://github.com/Zehui127/SQUAD_BERT/blob/HEAD/SQUAD/evaluate-v2.0.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":"e91c44f5680827e2","mcp_get_code":{"code_sha256":"e91c44f5680827e2"}},{"arxiv_id":"aaai_16733","paper":null,"title":"arXiv:aaai_16733","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"rajammanabrolu/WorldGeneration","path":"neural-based/KG-extraction/utils_squad_evaluate.py","file_url":"https://github.com/rajammanabrolu/WorldGeneration/blob/HEAD/neural-based/KG-extraction/utils_squad_evaluate.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":"e91c44f5680827e2","mcp_get_code":{"code_sha256":"e91c44f5680827e2"}},{"arxiv_id":"2024.findings-emnlp.365","paper":null,"title":"arXiv:2024.findings-emnlp.365","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"UKPLab/m2qa","path":"Experiments/M2QA_Metric/m2qa_metric_official_squad_v2_eval_script.py","file_url":"https://github.com/UKPLab/m2qa/blob/HEAD/Experiments/M2QA_Metric/m2qa_metric_official_squad_v2_eval_script.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":"e91c44f5680827e2","mcp_get_code":{"code_sha256":"e91c44f5680827e2"}},{"arxiv_id":"2024.findings-emnlp.365","paper":null,"title":"arXiv:2024.findings-emnlp.365","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"UKPLab/m2qa","path":"Experiments/M2QA_Metric/m2qa_metric.py","file_url":"https://github.com/UKPLab/m2qa/blob/HEAD/Experiments/M2QA_Metric/m2qa_metric.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":"41e5ac23be97994b","mcp_get_code":{"code_sha256":"41e5ac23be97994b"}}]}