{"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/f1","entry":"f1","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":57,"n_papers_ran":19,"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":36,"n_samples_ran":17,"n_samples_fingerprinted":4,"n_places":61,"n_places_pointer_only":23,"by_status":{"ran_honours":2,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":1,"ran":13,"unverified":19},"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":"2607.26339","paper":"/paper/arxiv-2607-26339","title":"RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"RAGuard-AI/RAGuard","path":"defences/scorer.py","file_url":"https://github.com/RAGuard-AI/RAGuard/blob/HEAD/defences/scorer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c31fa0dc73b0f2e6","mcp_get_code":{"code_sha256":"c31fa0dc73b0f2e6"}},{"arxiv_id":"2604.22937","paper":"/paper/arxiv-2604-22937","title":"AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"megagonlabs/AutoPyVerifier","path":"src/autopyverifier/search.py","file_url":"https://github.com/megagonlabs/AutoPyVerifier/blob/HEAD/src/autopyverifier/search.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"9a5c2eab3c6aee32","mcp_get_code":{"code_sha256":"9a5c2eab3c6aee32"}},{"arxiv_id":"2602.17155","paper":"/paper/arxiv-2602-17155","title":"Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"OPTML-Group/ZO-Muon","path":"llm/metrics.py","file_url":"https://github.com/OPTML-Group/ZO-Muon/blob/HEAD/llm/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b989d4bce26f77ce","mcp_get_code":{"code_sha256":"b989d4bce26f77ce"}},{"arxiv_id":"2601.18672","paper":"/paper/arxiv-2601-18672","title":"A Dynamic Framework for Grid Adaptation in Kolmogorov-Arnold Networks","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"srigas/kan_grid","path":"benchmarks/custom_funcs.py","file_url":"https://github.com/srigas/kan_grid/blob/HEAD/benchmarks/custom_funcs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"92442691ba7feffb","mcp_get_code":{"code_sha256":"92442691ba7feffb"}},{"arxiv_id":"2601.18672","paper":"/paper/arxiv-2601-18672","title":"A Dynamic Framework for Grid Adaptation in Kolmogorov-Arnold Networks","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"srigas/kan_grid","path":"benchmarks/feynman.py","file_url":"https://github.com/srigas/kan_grid/blob/HEAD/benchmarks/feynman.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ef974f15b06dab67","mcp_get_code":{"code_sha256":"ef974f15b06dab67"}},{"arxiv_id":"2507.12075","paper":null,"title":"arXiv:2507.12075","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"sapienzanlp/bookcoref","path":"src/metrics.py","file_url":"https://github.com/sapienzanlp/bookcoref/blob/HEAD/src/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"2505.13430","paper":"/paper/fine-tuning-quantized-neural-networks-with","title":"Fine-tuning Quantized Neural Networks with Zeroth-order Optimization","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maifoundations/qzo","path":"large_language_models/metrics.py","file_url":"https://github.com/maifoundations/qzo/blob/HEAD/large_language_models/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b989d4bce26f77ce","mcp_get_code":{"code_sha256":"b989d4bce26f77ce"}},{"arxiv_id":"2410.13681","paper":"/paper/ab-initio-nonparametric-variable-selection","title":"Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mattsheng/PAN_SR","path":"experiment/evaluate_model.py","file_url":"https://github.com/mattsheng/PAN_SR/blob/HEAD/experiment/evaluate_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"78fbb3b513d540ed","mcp_get_code":{"code_sha256":"78fbb3b513d540ed"}},{"arxiv_id":"2410.08989","paper":"/paper/subzero-random-subspace-zeroth-order","title":"Zeroth-Order Fine-Tuning of LLMs in Random Subspaces","date":"2024-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zimingyy/subzero","path":"large_models/metrics.py","file_url":"https://github.com/zimingyy/subzero/blob/HEAD/large_models/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"b989d4bce26f77ce","mcp_get_code":{"code_sha256":"b989d4bce26f77ce"}},{"arxiv_id":"2410.05162","paper":"/paper/deciphering-the-interplay-of-parametric-and","title":"Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"m3hrdadfi/rag-memory-interplay","path":"src/atlas/evaluation.py","file_url":"https://github.com/m3hrdadfi/rag-memory-interplay/blob/HEAD/src/atlas/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e2f0b798a3d70d2","mcp_get_code":{"code_sha256":"5e2f0b798a3d70d2"}},{"arxiv_id":"2407.21489","paper":"/paper/2407-21489","title":"Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends","date":"2024-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SapienzaNLP/maverick-coref","path":"maverick/common/metrics.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/common/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"2406.18847","paper":"/paper/learning-retrieval-augmentation-for","title":"Learning Retrieval Augmentation for Personalized Dialogue Generation","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hqsiswiliam/lapdog","path":"src/evaluation.py","file_url":"https://github.com/hqsiswiliam/lapdog/blob/HEAD/src/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e2f0b798a3d70d2","mcp_get_code":{"code_sha256":"5e2f0b798a3d70d2"}},{"arxiv_id":"2406.18187","paper":"/paper/selective-prompting-tuning-for-personalized","title":"Selective Prompting Tuning for Personalized Conversations with LLMs","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hqsiswiliam/SPT","path":"evaluation.py","file_url":"https://github.com/hqsiswiliam/SPT/blob/HEAD/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e2f0b798a3d70d2","mcp_get_code":{"code_sha256":"5e2f0b798a3d70d2"}},{"arxiv_id":"2405.03728","paper":"/paper/glhf-general-learned-evolutionary-algorithm","title":"Pretrained Optimization Model for Zero-Shot Black Box Optimization","date":"2024-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ninja-wm/pom","path":"BBOB_pkg/BBOB/bbobfunctions.py","file_url":"https://github.com/ninja-wm/pom/blob/HEAD/BBOB_pkg/BBOB/bbobfunctions.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"01d23dbb9edf690f","mcp_get_code":{"code_sha256":"01d23dbb9edf690f"}},{"arxiv_id":"2404.18185","paper":"/paper/ranked-list-truncation-for-large-language","title":"Ranked List Truncation for Large Language Model-based Re-Ranking","date":"2024-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chuanmeng/rlt4reranking","path":"rlt/retrieval_labels.py","file_url":"https://github.com/chuanmeng/rlt4reranking/blob/HEAD/rlt/retrieval_labels.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"95df88355bf0a4a5","mcp_get_code":{"code_sha256":"95df88355bf0a4a5"}},{"arxiv_id":"2402.11592","paper":"/paper/revisiting-zeroth-order-optimization-for","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zo-bench/zo-llm","path":"zo-bench/metrics.py","file_url":"https://github.com/zo-bench/zo-llm/blob/HEAD/zo-bench/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"b989d4bce26f77ce","mcp_get_code":{"code_sha256":"b989d4bce26f77ce"}},{"arxiv_id":"2402.11417","paper":"/paper/loretta-low-rank-economic-tensor-train","title":"LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yifanycc/loretta","path":"bert_model/metrics.py","file_url":"https://github.com/yifanycc/loretta/blob/HEAD/bert_model/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"b989d4bce26f77ce","mcp_get_code":{"code_sha256":"b989d4bce26f77ce"}},{"arxiv_id":"2401.09646","paper":"/paper/climategpt-towards-ai-synthesizing","title":"ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change","date":"2024-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eci-io/climategpt-evaluation","path":"tasks/exeter/utils.py","file_url":"https://github.com/eci-io/climategpt-evaluation/blob/HEAD/tasks/exeter/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9ca40505158717f6","mcp_get_code":{"code_sha256":"9ca40505158717f6"}},{"arxiv_id":"2401.09646","paper":"/paper/climategpt-towards-ai-synthesizing","title":"ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change","date":"2024-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eci-io/climategpt-evaluation","path":"tasks/pira_mcq/utils.py","file_url":"https://github.com/eci-io/climategpt-evaluation/blob/HEAD/tasks/pira_mcq/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1eb73c7c88a4339a","mcp_get_code":{"code_sha256":"1eb73c7c88a4339a"}},{"arxiv_id":"2401.09646","paper":"/paper/climategpt-towards-ai-synthesizing","title":"ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change","date":"2024-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eci-io/climategpt-evaluation","path":"tasks/climabench/clima_text/utils.py","file_url":"https://github.com/eci-io/climategpt-evaluation/blob/HEAD/tasks/climabench/clima_text/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ca45f4106331bb0","mcp_get_code":{"code_sha256":"6ca45f4106331bb0"}},{"arxiv_id":"2312.15184","paper":"/paper/zo-adamu-optimizer-adapting-perturbation-by","title":"ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization","date":"2023-12-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mathisall/zo-adamu","path":"metrics.py","file_url":"https://github.com/mathisall/zo-adamu/blob/HEAD/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b989d4bce26f77ce","mcp_get_code":{"code_sha256":"b989d4bce26f77ce"}},{"arxiv_id":"2311.15941","paper":"/paper/tell2design-a-dataset-for-language-guided","title":"Tell2Design: A Dataset for Language-Guided Floor Plan Generation","date":"2023-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lengsicong/tell2design","path":"T5/coreference_metrics.py","file_url":"https://github.com/lengsicong/tell2design/blob/HEAD/T5/coreference_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"2311.03748","paper":"/paper/unified-low-resource-sequence-labeling-by","title":"Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning","date":"2023-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"psunlpgroup/fish-dip","path":"augment/coreference_metrics.py","file_url":"https://github.com/psunlpgroup/fish-dip/blob/HEAD/augment/coreference_metrics.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":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"2310.13774","paper":"/paper/seq2seq-is-all-you-need-for-coreference","title":"Seq2seq is All You Need for Coreference Resolution","date":"2023-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WenzhengZhang/Seq2seqCoref","path":"metrics.py","file_url":"https://github.com/WenzhengZhang/Seq2seqCoref/blob/HEAD/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"2310.12836","paper":"/paper/knowledge-augmented-language-model","title":"Knowledge-Augmented Language Model Verification","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JinheonBaek/KALMV","path":"models/verifiers.py","file_url":"https://github.com/JinheonBaek/KALMV/blob/HEAD/models/verifiers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d8906dbc7552ff58","mcp_get_code":{"code_sha256":"d8906dbc7552ff58"}},{"arxiv_id":"2310.10443","paper":"/paper/taming-the-sigmoid-bottleneck-provably","title":"Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andreasgrv/sigmoid-bottleneck","path":"spmlbl/metrics.py","file_url":"https://github.com/andreasgrv/sigmoid-bottleneck/blob/HEAD/spmlbl/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77bf2eea0dac3863","mcp_get_code":{"code_sha256":"77bf2eea0dac3863"}},{"arxiv_id":"2310.09639","paper":"/paper/dpzero-dimension-independent-and","title":"DPZero: Private Fine-Tuning of Language Models without Backpropagation","date":"2023-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Liang137/DPZero","path":"opt/src/metrics.py","file_url":"https://github.com/Liang137/DPZero/blob/HEAD/opt/src/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b989d4bce26f77ce","mcp_get_code":{"code_sha256":"b989d4bce26f77ce"}},{"arxiv_id":"2310.01045","paper":"/paper/tool-augmented-reward-modeling","title":"Tool-Augmented Reward Modeling","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ernie-research/Tool-Augmented-Reward-Model","path":"src/utils/metrics.py","file_url":"https://github.com/ernie-research/Tool-Augmented-Reward-Model/blob/HEAD/src/utils/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d67b636c4fd9e6cb","mcp_get_code":{"code_sha256":"d67b636c4fd9e6cb"}},{"arxiv_id":"2308.07922","paper":"/paper/raven-in-context-learning-with-retrieval","title":"RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models","date":"2023-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeffhj/raven","path":"src/evaluation.py","file_url":"https://github.com/jeffhj/raven/blob/HEAD/src/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e2f0b798a3d70d2","mcp_get_code":{"code_sha256":"5e2f0b798a3d70d2"}},{"arxiv_id":"2307.01878","paper":"/paper/kdstm-neural-semi-supervised-topic-modeling","title":"KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillation","date":"2023-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yumeng5/WeSTClass","path":"model.py","file_url":"https://github.com/yumeng5/WeSTClass/blob/HEAD/model.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":"02b9090cc2f7dd5e","mcp_get_code":{"code_sha256":"02b9090cc2f7dd5e"}},{"arxiv_id":"2305.17333","paper":"/paper/fine-tuning-language-models-with-just-forward-1","title":"Fine-Tuning Language Models with Just Forward Passes","date":"2023-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/mezo","path":"large_models/metrics.py","file_url":"https://github.com/princeton-nlp/mezo/blob/HEAD/large_models/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b989d4bce26f77ce","mcp_get_code":{"code_sha256":"b989d4bce26f77ce"}},{"arxiv_id":"2211.01635","paper":"/paper/revisiting-grammatical-error-correction","title":"Revisiting Grammatical Error Correction Evaluation and Beyond","date":"2022-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pygongnlp/PT-M2","path":"metrics.py","file_url":"https://github.com/pygongnlp/PT-M2/blob/HEAD/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b8394bc429303913","mcp_get_code":{"code_sha256":"b8394bc429303913"}},{"arxiv_id":"2205.12644","paper":"/paper/lingmess-linguistically-informed-multi-expert","title":"LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution","date":"2022-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shon-otmazgin/fastcoref","path":"fastcoref/utilities/metrics.py","file_url":"https://github.com/shon-otmazgin/fastcoref/blob/HEAD/fastcoref/utilities/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"2205.10475","paper":"/paper/deepstruct-pretraining-of-language-models-for-1","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","date":"2022-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cgraywang/deepstruct","path":"src/dataset_processing/coreference_metrics.py","file_url":"https://github.com/cgraywang/deepstruct/blob/HEAD/src/dataset_processing/coreference_metrics.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":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"2202.10710","paper":"/paper/incorporating-constituent-syntax-for","title":"Incorporating Constituent Syntax for Coreference Resolution","date":"2022-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mandarjoshi90/coref","path":"metrics.py","file_url":"https://github.com/mandarjoshi90/coref/blob/HEAD/metrics.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":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"2112.05195","paper":"/paper/context-aware-health-event-prediction-via","title":"Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs","date":"2021-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luchang-cs/chet","path":"metrics.py","file_url":"https://github.com/luchang-cs/chet/blob/HEAD/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a3c98d8caff0f225","mcp_get_code":{"code_sha256":"a3c98d8caff0f225"}},{"arxiv_id":"2109.04901","paper":"/paper/document-level-entity-based-extraction-as","title":"Document-level Entity-based Extraction as Template Generation","date":"2021-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PlusLabNLP/TempGen","path":"ree_eval.py","file_url":"https://github.com/PlusLabNLP/TempGen/blob/HEAD/ree_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"2108.08435","paper":"/paper/fair-and-consistent-federated-learning","title":"Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning","date":"2021-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cuis15/FCFL","path":"FUEL/synthetic/utils.py","file_url":"https://github.com/cuis15/FCFL/blob/HEAD/FUEL/synthetic/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"63aab5e7619728e3","mcp_get_code":{"code_sha256":"63aab5e7619728e3"}},{"arxiv_id":"2106.05960","paper":"/paper/compositional-modeling-of-nonlinear-dynamical","title":"Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features","date":"2021-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tomcdonald/deep-lfm","path":"toy_demo.py","file_url":"https://github.com/tomcdonald/deep-lfm/blob/HEAD/toy_demo.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":"b759091d010c7bac","mcp_get_code":{"code_sha256":"b759091d010c7bac"}},{"arxiv_id":"2106.03598","paper":"/paper/scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"justinphan3110/SciFive","path":"biot5x/src/metrics.py","file_url":"https://github.com/justinphan3110/SciFive/blob/HEAD/biot5x/src/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12ff36b88687dd69","mcp_get_code":{"code_sha256":"12ff36b88687dd69"}},{"arxiv_id":"2006.15222","paper":"/paper/bertology-meets-biology-interpreting","title":"BERTology Meets Biology: Interpreting Attention in Protein Language Models","date":"2020-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/provis","path":"protein_attention/probing/metrics.py","file_url":"https://github.com/salesforce/provis/blob/HEAD/protein_attention/probing/metrics.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"218b4d111a904876","mcp_get_code":{"code_sha256":"218b4d111a904876"}},{"arxiv_id":"2004.09167","paper":"/paper/chexbert-combining-automatic-labelers-and","title":"CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT","date":"2020-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wjhou/icon","path":"src_retrieval/retrieval.py","file_url":"https://github.com/wjhou/icon/blob/HEAD/src_retrieval/retrieval.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":"6d01795fce054855","mcp_get_code":{"code_sha256":"6d01795fce054855"}},{"arxiv_id":"1910.13267","paper":"/paper/191013267","title":"BPE-Dropout: Simple and Effective Subword Regularization","date":"2019-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PatxiofromAlphensign/subword-nmt-mods","path":"subword_nmt/chrF.py","file_url":"https://github.com/PatxiofromAlphensign/subword-nmt-mods/blob/HEAD/subword_nmt/chrF.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b27e34636c16aac","mcp_get_code":{"code_sha256":"9b27e34636c16aac"}},{"arxiv_id":"1910.06188","paper":"/paper/q8bert-quantized-8bit-bert","title":"Q8BERT: Quantized 8Bit BERT","date":"2019-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NervanaSystems/nlp-architect","path":"nlp_architect/models/np_semantic_segmentation.py","file_url":"https://github.com/NervanaSystems/nlp-architect/blob/HEAD/nlp_architect/models/np_semantic_segmentation.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":"6a2e2df3980634be","mcp_get_code":{"code_sha256":"6a2e2df3980634be"}},{"arxiv_id":"1909.04630","paper":"/paper/meta-learning-with-implicit-gradients","title":"Meta-Learning with Implicit Gradients","date":"2019-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"spiglerg/pyMeta","path":"pyMeta/metalearners/implicit_maml.py","file_url":"https://github.com/spiglerg/pyMeta/blob/HEAD/pyMeta/metalearners/implicit_maml.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"878503c8b4732592","mcp_get_code":{"code_sha256":"878503c8b4732592"}},{"arxiv_id":"1907.10529","paper":"/paper/spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amore-upf/masked-coreference","path":"metrics.py","file_url":"https://github.com/amore-upf/masked-coreference/blob/HEAD/metrics.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":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"1906.06532","paper":"/paper/attributed-graph-clustering-a-deep","title":"Attributed Graph Clustering: A Deep Attentional Embedding Approach","date":"2019-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GraphEoM/GSCAN","path":"gscan/evaluation.py","file_url":"https://github.com/GraphEoM/GSCAN/blob/HEAD/gscan/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"681f6a5cb5d508f9","mcp_get_code":{"code_sha256":"681f6a5cb5d508f9"}},{"arxiv_id":"1906.02505","paper":"/paper/fine-grained-entity-typing-in-hyperbolic","title":"Fine-Grained Entity Typing in Hyperbolic Space","date":"2019-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlpAThits/figet-hyperbolic-space","path":"figet/evaluate.py","file_url":"https://github.com/nlpAThits/figet-hyperbolic-space/blob/HEAD/figet/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b9f6dc91f68b705d","mcp_get_code":{"code_sha256":"b9f6dc91f68b705d"}},{"arxiv_id":"1905.09550","paper":"/paper/revisiting-graph-neural-networks-all-we-have","title":"Revisiting Graph Neural Networks: All We Have is Low-Pass Filters","date":"2019-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gear/gfnn","path":"metrics.py","file_url":"https://github.com/gear/gfnn/blob/HEAD/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc1fd8ffd02dab36","mcp_get_code":{"code_sha256":"cc1fd8ffd02dab36"}},{"arxiv_id":"1902.07153","paper":"/paper/simplifying-graph-convolutional-networks","title":"Simplifying Graph Convolutional Networks","date":"2019-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Tiiiger/SGC","path":"metrics.py","file_url":"https://github.com/Tiiiger/SGC/blob/HEAD/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc1fd8ffd02dab36","mcp_get_code":{"code_sha256":"cc1fd8ffd02dab36"}},{"arxiv_id":"1902.00146","paper":"/paper/agnostic-federated-learning","title":"Agnostic Federated Learning","date":"2019-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fairfl/FUEL","path":"FUEL/synthetic/utils.py","file_url":"https://github.com/fairfl/FUEL/blob/HEAD/FUEL/synthetic/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"63aab5e7619728e3","mcp_get_code":{"code_sha256":"63aab5e7619728e3"}},{"arxiv_id":"1810.09050","paper":"/paper/a-comparison-of-five-multiple-instance","title":"A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling","date":null,"month_inferred_from_arxiv_id":"2018-10","title_source":"archive","repo":"MaigoAkisame/cmu-thesis","path":"code/audioset/util_f1.py","file_url":"https://github.com/MaigoAkisame/cmu-thesis/blob/HEAD/code/audioset/util_f1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12e77c4861731d4f","mcp_get_code":{"code_sha256":"12e77c4861731d4f"}},{"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":"ilhamfp/indonesian-text-classification-multilingual","path":"src/model-full.py","file_url":"https://github.com/ilhamfp/indonesian-text-classification-multilingual/blob/HEAD/src/model-full.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bee3340c9aa9a937","mcp_get_code":{"code_sha256":"bee3340c9aa9a937"}},{"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":"haydlite/sparse-bert-ner","path":"old_version/tf_metrics.py","file_url":"https://github.com/haydlite/sparse-bert-ner/blob/HEAD/old_version/tf_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"68aa9e92f48080b5","mcp_get_code":{"code_sha256":"68aa9e92f48080b5"}},{"arxiv_id":"1806.06871","paper":"/paper/continuous-variable-quantum-neural-networks","title":"Continuous-variable quantum neural networks","date":"2018-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XanaduAI/quantum-neural-networks","path":"function_fitting/function_fitting.py","file_url":"https://github.com/XanaduAI/quantum-neural-networks/blob/HEAD/function_fitting/function_fitting.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b0a15e13b70f03ba","mcp_get_code":{"code_sha256":"b0a15e13b70f03ba"}},{"arxiv_id":"1804.05392","paper":"/paper/higher-order-coreference-resolution-with","title":"Higher-order Coreference Resolution with Coarse-to-fine Inference","date":"2018-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kentonl/e2e-coref","path":"metrics.py","file_url":"https://github.com/kentonl/e2e-coref/blob/HEAD/metrics.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":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"1803.03211","paper":"/paper/phasenet-a-deep-neural-network-based-seismic","title":"PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method","date":null,"month_inferred_from_arxiv_id":"2018-03","title_source":"archive","repo":"SeisNN/SeisNN","path":"seisblue/model/EqT_utils.py","file_url":"https://github.com/SeisNN/SeisNN/blob/HEAD/seisblue/model/EqT_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9bf3507fe4dfd4d7","mcp_get_code":{"code_sha256":"9bf3507fe4dfd4d7"}},{"arxiv_id":"1802.08301","paper":"/paper/content-based-citation-recommendation","title":"Content-Based Citation Recommendation","date":"2018-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/citeomatic","path":"citeomatic/eval_metrics.py","file_url":"https://github.com/allenai/citeomatic/blob/HEAD/citeomatic/eval_metrics.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":"9bffd8f716f06256","mcp_get_code":{"code_sha256":"9bffd8f716f06256"}},{"arxiv_id":"2025.emnlp-main.292","paper":null,"title":"arXiv:2025.emnlp-main.292","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"RUC-NLPIR/OmniEval","path":"utils/evaluation.py","file_url":"https://github.com/RUC-NLPIR/OmniEval/blob/HEAD/utils/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5e2f0b798a3d70d2","mcp_get_code":{"code_sha256":"5e2f0b798a3d70d2"}},{"arxiv_id":"2024.acl-srw.56","paper":null,"title":"arXiv:2024.acl-srw.56","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"psuwannapich/z-coref","path":"utilities/metrics.py","file_url":"https://github.com/psuwannapich/z-coref/blob/HEAD/utilities/metrics.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":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"arxiv_id":"2021.naacl-main.125","paper":null,"title":"arXiv:2021.naacl-main.125","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Fantabulous-J/coref-HGAT","path":"metrics.py","file_url":"https://github.com/Fantabulous-J/coref-HGAT/blob/HEAD/metrics.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":"5dc251a1bb16c94f","mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}}]}