{"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/batch-data","entry":"batch_data","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":20,"n_papers_ran":10,"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":3,"n_samples_fingerprinted":1,"n_places":21,"n_places_pointer_only":14,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"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":"2604.18124","paper":"/paper/arxiv-2604-18124","title":"TLoRA: Task-aware Low Rank Adaptation of Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Rambo-Yi/TLora","path":"evaluate/code/gen_vllm.py","file_url":"https://github.com/Rambo-Yi/TLora/blob/HEAD/evaluate/code/gen_vllm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d49412b3a690206e","mcp_get_code":{"code_sha256":"d49412b3a690206e"}},{"arxiv_id":"2502.04667","paper":"/paper/unveiling-the-mechanisms-of-explicit-cot","title":"Unveiling the Mechanisms of Explicit CoT Training: How CoT Enhances Reasoning Generalization","date":"2025-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chen123ctrls/t-cotmechanism","path":"RealisticDataVerification/utils/gen_vllm.py","file_url":"https://github.com/chen123ctrls/t-cotmechanism/blob/HEAD/RealisticDataVerification/utils/gen_vllm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d49412b3a690206e","mcp_get_code":{"code_sha256":"d49412b3a690206e"}},{"arxiv_id":"2410.09344","paper":"/paper/dare-the-extreme-revisiting-delta-parameter","title":"DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vengdeng/darex","path":"find_q_decoder.py","file_url":"https://github.com/vengdeng/darex/blob/HEAD/find_q_decoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d49a90d96daf66f7","mcp_get_code":{"code_sha256":"d49a90d96daf66f7"}},{"arxiv_id":"2410.09344","paper":"/paper/dare-the-extreme-revisiting-delta-parameter","title":"DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vengdeng/darex","path":"utils/evaluate_llms_utils.py","file_url":"https://github.com/vengdeng/darex/blob/HEAD/utils/evaluate_llms_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d49412b3a690206e","mcp_get_code":{"code_sha256":"d49412b3a690206e"}},{"arxiv_id":"2408.04556","paper":"/paper/bias-aware-low-rank-adaptation-mitigating","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","date":"2024-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cyp-jlu-ai/ba-lora","path":"inference/gsm8k_inference.py","file_url":"https://github.com/cyp-jlu-ai/ba-lora/blob/HEAD/inference/gsm8k_inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c20985938875f5f","mcp_get_code":{"code_sha256":"5c20985938875f5f"}},{"arxiv_id":"2408.03092","paper":"/paper/extend-model-merging-from-fine-tuned-to-pre","title":"Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement","date":"2024-08-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yule-BUAA/MergeLLM","path":"utils/evaluate_llms_utils.py","file_url":"https://github.com/yule-BUAA/MergeLLM/blob/HEAD/utils/evaluate_llms_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d49412b3a690206e","mcp_get_code":{"code_sha256":"d49412b3a690206e"}},{"arxiv_id":"2406.18629","paper":"/paper/step-dpo-step-wise-preference-optimization","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/step-dpo","path":"eval_math.py","file_url":"https://github.com/dvlab-research/step-dpo/blob/HEAD/eval_math.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"66b3b5450182da3a","mcp_get_code":{"code_sha256":"66b3b5450182da3a"}},{"arxiv_id":"2406.14024","paper":"/paper/the-reason-behind-good-or-bad-towards-a","title":"LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback","date":"2024-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kbsdjames/math-minos","path":"evaluation/eval_gsm8k.py","file_url":"https://github.com/kbsdjames/math-minos/blob/HEAD/evaluation/eval_gsm8k.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"66b3b5450182da3a","mcp_get_code":{"code_sha256":"66b3b5450182da3a"}},{"arxiv_id":"2406.11617","paper":"/paper/della-merging-reducing-interference-in-model","title":"DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"declare-lab/della","path":"utils/evaluate_llms_utils.py","file_url":"https://github.com/declare-lab/della/blob/HEAD/utils/evaluate_llms_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d49412b3a690206e","mcp_get_code":{"code_sha256":"d49412b3a690206e"}},{"arxiv_id":"2406.09044","paper":"/paper/milora-harnessing-minor-singular-components","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"graphpku/pissa","path":"utils/gen_vllm.py","file_url":"https://github.com/graphpku/pissa/blob/HEAD/utils/gen_vllm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d49412b3a690206e","mcp_get_code":{"code_sha256":"d49412b3a690206e"}},{"arxiv_id":"2406.08903","paper":"/paper/delta-come-training-free-delta-compression","title":"Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"66b3b5450182da3a","mcp_get_code":{"code_sha256":"66b3b5450182da3a"}},{"arxiv_id":"2405.15179","paper":"/paper/vb-lora-extreme-parameter-efficient-fine","title":"VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leo-yangli/VB-LoRA","path":"math_instruction_tuning/instruction_tuning_eval/MATH_eval.py","file_url":"https://github.com/leo-yangli/VB-LoRA/blob/HEAD/math_instruction_tuning/instruction_tuning_eval/MATH_eval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"66b3b5450182da3a","mcp_get_code":{"code_sha256":"66b3b5450182da3a"}},{"arxiv_id":"2405.14804","paper":"/paper/can-llms-solve-longer-math-word-problems","title":"Can LLMs Solve longer Math Word Problems Better?","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"66b3b5450182da3a","mcp_get_code":{"code_sha256":"66b3b5450182da3a"}},{"arxiv_id":"2405.06680","paper":"/paper/exploring-the-compositional-deficiency-of","title":"Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning","date":"2024-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tongjingqi/MathTrap","path":"eval/eval_GSM8K_category.py","file_url":"https://github.com/tongjingqi/MathTrap/blob/HEAD/eval/eval_GSM8K_category.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"66b3b5450182da3a","mcp_get_code":{"code_sha256":"66b3b5450182da3a"}},{"arxiv_id":"2404.10346","paper":"/paper/self-explore-to-avoid-the-pit-improving-the","title":"Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"66b3b5450182da3a","mcp_get_code":{"code_sha256":"66b3b5450182da3a"}},{"arxiv_id":"2311.03099","paper":"/paper/language-models-are-super-mario-absorbing","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","date":"2023-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yule-BUAA/MergeLM","path":"utils/evaluate_llms_utils.py","file_url":"https://github.com/yule-BUAA/MergeLM/blob/HEAD/utils/evaluate_llms_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d49412b3a690206e","mcp_get_code":{"code_sha256":"d49412b3a690206e"}},{"arxiv_id":"2309.12284","paper":"/paper/metamath-bootstrap-your-own-mathematical","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","date":"2023-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meta-math/MetaMath","path":"eval_gsm8k.py","file_url":"https://github.com/meta-math/MetaMath/blob/HEAD/eval_gsm8k.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"66b3b5450182da3a","mcp_get_code":{"code_sha256":"66b3b5450182da3a"}},{"arxiv_id":"2108.08367","paper":"/paper/so-pose-exploiting-self-occlusion-for-direct","title":"SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation","date":"2021-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THU-DA-6D-Pose-Group/GDR-Net","path":"core/gdrn_modeling/engine_utils.py","file_url":"https://github.com/THU-DA-6D-Pose-Group/GDR-Net/blob/HEAD/core/gdrn_modeling/engine_utils.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":"7d3d30f20b202337","mcp_get_code":{"code_sha256":"7d3d30f20b202337"}},{"arxiv_id":"2007.12626","paper":"/paper/summeval-re-evaluating-summarization","title":"SummEval: Re-evaluating Summarization Evaluation","date":"2020-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PrimerAI/blanc","path":"blanc/utils.py","file_url":"https://github.com/PrimerAI/blanc/blob/HEAD/blanc/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d1bb17547eab5079","mcp_get_code":{"code_sha256":"d1bb17547eab5079"}},{"arxiv_id":"1812.06127","paper":"/paper/federated-optimization-for-heterogeneous","title":"Federated Optimization in Heterogeneous Networks","date":"2018-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"litian96/FedProx","path":"utils/model_utils.py","file_url":"https://github.com/litian96/FedProx/blob/HEAD/utils/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04eb2c09a69cabcd","mcp_get_code":{"code_sha256":"04eb2c09a69cabcd"}},{"arxiv_id":"2025.emnlp-main.353","paper":null,"title":"arXiv:2025.emnlp-main.353","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"nju-websoft/GraDaSE","path":"code/utils/data.py","file_url":"https://github.com/nju-websoft/GraDaSE/blob/HEAD/code/utils/data.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":"23a86833d34c6c18","mcp_get_code":{"code_sha256":"23a86833d34c6c18"}}]}