{"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-examples","entry":"load_examples","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":3,"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":4,"n_samples_fingerprinted":0,"n_places":13,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":8},"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":"2606.10537","paper":"/paper/arxiv-2606-10537","title":"Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"menik1126/Prefilling-dLLM","path":"prefilling_dllm_eval/eval_fastdllm_parallelcomp_scbench.py","file_url":"https://github.com/menik1126/Prefilling-dLLM/blob/HEAD/prefilling_dllm_eval/eval_fastdllm_parallelcomp_scbench.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2423c7f82a371875","mcp_get_code":{"code_sha256":"2423c7f82a371875"}},{"arxiv_id":"2601.04435","paper":"/paper/arxiv-2601-04435","title":"Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"myracheng/accommodation","path":"evaluation_scripts/cancereval.py","file_url":"https://github.com/myracheng/accommodation/blob/HEAD/evaluation_scripts/cancereval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8ad32edd59d3b14a","mcp_get_code":{"code_sha256":"8ad32edd59d3b14a"}},{"arxiv_id":"2406.13892","paper":"/paper/adaptable-logical-control-for-large-language","title":"Adaptable Logical Control for Large Language Models","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joshuacnf/Ctrl-G","path":"distillation/lvd_hmm.py","file_url":"https://github.com/joshuacnf/Ctrl-G/blob/HEAD/distillation/lvd_hmm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"89f1bdb63107dedb","mcp_get_code":{"code_sha256":"89f1bdb63107dedb"}},{"arxiv_id":"2406.13892","paper":"/paper/adaptable-logical-control-for-large-language","title":"Adaptable Logical Control for Large Language Models","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joshuacnf/Ctrl-G","path":"distillation_vllm/lvd_hmm.py","file_url":"https://github.com/joshuacnf/Ctrl-G/blob/HEAD/distillation_vllm/lvd_hmm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d7065ff3317ecdf8","mcp_get_code":{"code_sha256":"d7065ff3317ecdf8"}},{"arxiv_id":"2401.06766","paper":"/paper/mind-your-format-towards-consistent","title":"Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yandex-research/mind-your-format","path":"examples.py","file_url":"https://github.com/yandex-research/mind-your-format/blob/HEAD/examples.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":"6047b9a8b85a7ea6","mcp_get_code":{"code_sha256":"6047b9a8b85a7ea6"}},{"arxiv_id":"2209.02071","paper":"/paper/concrete-improving-cross-lingual-fact","title":"CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval","date":"2022-09-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"khuangaf/concrete","path":"src/xfact_eval.py","file_url":"https://github.com/khuangaf/concrete/blob/HEAD/src/xfact_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":"0ff469fd7e461be9","mcp_get_code":{"code_sha256":"0ff469fd7e461be9"}},{"arxiv_id":"2106.09248","paper":"/paper/x-fact-a-new-benchmark-dataset-for","title":"X-FACT: A New Benchmark Dataset for Multilingual Fact Checking","date":"2021-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"utahnlp/x-fact","path":"transformers/calculate_fscore.py","file_url":"https://github.com/utahnlp/x-fact/blob/HEAD/transformers/calculate_fscore.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ff469fd7e461be9","mcp_get_code":{"code_sha256":"0ff469fd7e461be9"}},{"arxiv_id":"2106.09248","paper":"/paper/x-fact-a-new-benchmark-dataset-for","title":"X-FACT: A New Benchmark Dataset for Multilingual Fact Checking","date":"2021-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"utahnlp/x-fact","path":"transformers/format_xfact_to_sst2.py","file_url":"https://github.com/utahnlp/x-fact/blob/HEAD/transformers/format_xfact_to_sst2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"db6cdf5092632d53","mcp_get_code":{"code_sha256":"db6cdf5092632d53"}},{"arxiv_id":"2106.09248","paper":"/paper/x-fact-a-new-benchmark-dataset-for","title":"X-FACT: A New Benchmark Dataset for Multilingual Fact Checking","date":"2021-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"utahnlp/x-fact","path":"transformers/randomize_snippets.py","file_url":"https://github.com/utahnlp/x-fact/blob/HEAD/transformers/randomize_snippets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f04e5c9effb7af68","mcp_get_code":{"code_sha256":"f04e5c9effb7af68"}},{"arxiv_id":"2106.09248","paper":"/paper/x-fact-a-new-benchmark-dataset-for","title":"X-FACT: A New Benchmark Dataset for Multilingual Fact Checking","date":"2021-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"utahnlp/x-fact","path":"transformers/remove_labels.py","file_url":"https://github.com/utahnlp/x-fact/blob/HEAD/transformers/remove_labels.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35dcc7eeb3e15598","mcp_get_code":{"code_sha256":"35dcc7eeb3e15598"}},{"arxiv_id":"aaai_29726","paper":null,"title":"arXiv:aaai_29726","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"shesshan/CEIB","path":"utils/data_utils.py","file_url":"https://github.com/shesshan/CEIB/blob/HEAD/utils/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e345fd83104bebbf","mcp_get_code":{"code_sha256":"e345fd83104bebbf"}},{"arxiv_id":"2023.findings-emnlp.179","paper":null,"title":"arXiv:2023.findings-emnlp.179","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"noewangjy/SP-CoT","path":"tasks/build_pseudo_dataset.py","file_url":"https://github.com/noewangjy/SP-CoT/blob/HEAD/tasks/build_pseudo_dataset.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":"a11709598ddc989b","mcp_get_code":{"code_sha256":"a11709598ddc989b"}},{"arxiv_id":"2021.findings-emnlp.386","paper":null,"title":"arXiv:2021.findings-emnlp.386","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lbe0613/GCC","path":"finetune/run_finetune.py","file_url":"https://github.com/lbe0613/GCC/blob/HEAD/finetune/run_finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5cf3da838aa2bab8","mcp_get_code":{"code_sha256":"5cf3da838aa2bab8"}}]}