{"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/extract-number","entry":"extract_number","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":21,"n_papers_ran":15,"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":20,"n_samples_ran":14,"n_samples_fingerprinted":13,"n_places":22,"n_places_pointer_only":10,"by_status":{"ran_honours":4,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":10,"unverified":6},"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":"2607.28166","paper":"/paper/arxiv-2607-28166","title":"Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"ming053l/C4-dLLM","path":"c4/extract.py","file_url":"https://github.com/ming053l/C4-dLLM/blob/HEAD/c4/extract.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d9cea69389fc2c87","mcp_get_code":{"code_sha256":"d9cea69389fc2c87"}},{"arxiv_id":"2604.11048","paper":"/paper/arxiv-2604-11048","title":"A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"cjia7/DPR","path":"src/npti/eval/eval_gsm8k.py","file_url":"https://github.com/cjia7/DPR/blob/HEAD/src/npti/eval/eval_gsm8k.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"59c6ffbd98640ae2","mcp_get_code":{"code_sha256":"59c6ffbd98640ae2"}},{"arxiv_id":"2603.10243","paper":"/paper/arxiv-2603-10243","title":"GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"chili-lab/gr-sap","path":"score_dir.py","file_url":"https://github.com/chili-lab/gr-sap/blob/HEAD/score_dir.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c4c540c2c11ce5ee","mcp_get_code":{"code_sha256":"c4c540c2c11ce5ee"}},{"arxiv_id":"2511.19900","paper":"/paper/arxiv-2511-19900","title":"Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"aiming-lab/Agent0","path":"Agent0-VL/verl/evaluation/metrics.py","file_url":"https://github.com/aiming-lab/Agent0/blob/HEAD/Agent0-VL/verl/evaluation/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":"8209d8d36717864f","mcp_get_code":{"code_sha256":"8209d8d36717864f"}},{"arxiv_id":"2508.18847","paper":"/paper/arxiv-2508-18847","title":"ConfTuner: Training Large Language Models to Express Their Confidence Verbally","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"liushiliushi/ConfTuner","path":"src/llama_recipes/datasets2/gsm8k_dataset.py","file_url":"https://github.com/liushiliushi/ConfTuner/blob/HEAD/src/llama_recipes/datasets2/gsm8k_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c7a43e26bfef4042","mcp_get_code":{"code_sha256":"c7a43e26bfef4042"}},{"arxiv_id":"2505.18915","paper":"/paper/are-vision-language-models-ready-for-clinical","title":"Are Vision Language Models Ready for Clinical Diagnosis? A 3D Medical Benchmark for Tumor-centric Visual Question Answering","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Schuture/DeepTumorVQA","path":"src/deeptumorvqa/eval/metrics.py","file_url":"https://github.com/Schuture/DeepTumorVQA/blob/HEAD/src/deeptumorvqa/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":"b35d31006104e7a1","mcp_get_code":{"code_sha256":"b35d31006104e7a1"}},{"arxiv_id":"2503.22420","paper":"/paper/unveiling-the-mist-over-3d-vision-language","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","date":"2025-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beacon-3d/beacon-3d","path":"utils.py","file_url":"https://github.com/beacon-3d/beacon-3d/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"64da74993d3cde5c","mcp_get_code":{"code_sha256":"64da74993d3cde5c"}},{"arxiv_id":"2410.18514","paper":"/paper/scaling-up-masked-diffusion-models-on-text","title":"Scaling up Masked Diffusion Models on Text","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-gsai/smdm","path":"sft/finetune_mdm.py","file_url":"https://github.com/ml-gsai/smdm/blob/HEAD/sft/finetune_mdm.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bab869165fb9be5c","mcp_get_code":{"code_sha256":"bab869165fb9be5c"}},{"arxiv_id":"2409.02389","paper":"/paper/multi-modal-situated-reasoning-in-3d-scenes","title":"Multi-modal Situated Reasoning in 3D Scenes","date":"2024-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MSR3D/MSR3D","path":"evaluator/evaluate_msqa.py","file_url":"https://github.com/MSR3D/MSR3D/blob/HEAD/evaluator/evaluate_msqa.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"64da74993d3cde5c","mcp_get_code":{"code_sha256":"64da74993d3cde5c"}},{"arxiv_id":"2408.16768","paper":"/paper/sam2point-segment-any-3d-as-videos-in-zero","title":"SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziyuguo99/sam2point","path":"gen_video.py","file_url":"https://github.com/ziyuguo99/sam2point/blob/HEAD/gen_video.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4dd79d2c43d8afdb","mcp_get_code":{"code_sha256":"4dd79d2c43d8afdb"}},{"arxiv_id":"2406.17419","paper":"/paper/leave-no-document-behind-benchmarking-long","title":"Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MozerWang/Loong","path":"src/utils/metric.py","file_url":"https://github.com/MozerWang/Loong/blob/HEAD/src/utils/metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"02bbb0545f754a36","mcp_get_code":{"code_sha256":"02bbb0545f754a36"}},{"arxiv_id":"2405.18357","paper":"/paper/faithful-logical-reasoning-via-symbolic-chain","title":"Faithful Logical Reasoning via Symbolic Chain-of-Thought","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Aiden0526/SymbCoT","path":"baselines/evaluation.py","file_url":"https://github.com/Aiden0526/SymbCoT/blob/HEAD/baselines/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"471cfa8084196a13","mcp_get_code":{"code_sha256":"471cfa8084196a13"}},{"arxiv_id":"2404.19097","paper":"/paper/exploring-the-capability-of-llms-in","title":"Exploring the Capability of LLMs in Performing Low-Level Visual Analytic Tasks on SVG Data Visualizations","date":null,"month_inferred_from_arxiv_id":"2024-04","title_source":"archive","repo":"lebretou/svg_taxonomy","path":"data_generation/plot.py","file_url":"https://github.com/lebretou/svg_taxonomy/blob/HEAD/data_generation/plot.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1a6ca3848710d349","mcp_get_code":{"code_sha256":"1a6ca3848710d349"}},{"arxiv_id":"2404.19097","paper":"/paper/exploring-the-capability-of-llms-in","title":"Exploring the Capability of LLMs in Performing Low-Level Visual Analytic Tasks on SVG Data Visualizations","date":null,"month_inferred_from_arxiv_id":"2024-04","title_source":"archive","repo":"lebretou/svg_taxonomy","path":"llm/gen_prompt.py","file_url":"https://github.com/lebretou/svg_taxonomy/blob/HEAD/llm/gen_prompt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7641ccd4efe3716e","mcp_get_code":{"code_sha256":"7641ccd4efe3716e"}},{"arxiv_id":"2402.08219","paper":"/paper/bbox-adapter-lightweight-adapting-for-black","title":"BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models","date":"2024-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haotiansun14/bbox-adapter","path":"utils/scienceqa_metric.py","file_url":"https://github.com/haotiansun14/bbox-adapter/blob/HEAD/utils/scienceqa_metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb4554f77207ac70","mcp_get_code":{"code_sha256":"eb4554f77207ac70"}},{"arxiv_id":"2402.05120","paper":"/paper/more-agents-is-all-you-need","title":"More Agents Is All You Need","date":"2024-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"moreagentsisallyouneed/agentforest","path":"src/evaluation.py","file_url":"https://github.com/moreagentsisallyouneed/agentforest/blob/HEAD/src/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9d2b0534d308fb1","mcp_get_code":{"code_sha256":"f9d2b0534d308fb1"}},{"arxiv_id":"2311.18702","paper":"/paper/critiquellm-scaling-llm-as-critic-for","title":"CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/critiquellm","path":"evaluation/eval_pointwise.py","file_url":"https://github.com/thu-coai/critiquellm/blob/HEAD/evaluation/eval_pointwise.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a6e47174738c4534","mcp_get_code":{"code_sha256":"a6e47174738c4534"}},{"arxiv_id":"2311.13171","paper":"/paper/compeft-compression-for-communicating","title":"ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization","date":"2023-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"prateeky2806/compeft","path":"src/merge_utils.py","file_url":"https://github.com/prateeky2806/compeft/blob/HEAD/src/merge_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"0e04f05ef437bf17","mcp_get_code":{"code_sha256":"0e04f05ef437bf17"}},{"arxiv_id":"2310.07676","paper":"/paper/composite-backdoor-attacks-against-large","title":"Composite Backdoor Attacks Against Large Language Models","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miraclehh/cba","path":"nlp/backdoor_eval.py","file_url":"https://github.com/miraclehh/cba/blob/HEAD/nlp/backdoor_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"06a5d25fb68e1cb3","mcp_get_code":{"code_sha256":"06a5d25fb68e1cb3"}},{"arxiv_id":"2306.03241","paper":"/paper/understanding-the-effectiveness-of-early","title":"Early Weight Averaging meets High Learning Rates for LLM Pre-training","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sanyalsunny111/early_weight_avg","path":"nanoGPT2-Experiments/lawa.py","file_url":"https://github.com/sanyalsunny111/early_weight_avg/blob/HEAD/nanoGPT2-Experiments/lawa.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"75f5853321b37296","mcp_get_code":{"code_sha256":"75f5853321b37296"}},{"arxiv_id":"2305.12295","paper":"/paper/logic-lm-empowering-large-language-models","title":"Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning","date":"2023-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"teacherpeterpan/logic-llm","path":"baselines/evaluation.py","file_url":"https://github.com/teacherpeterpan/logic-llm/blob/HEAD/baselines/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"471cfa8084196a13","mcp_get_code":{"code_sha256":"471cfa8084196a13"}},{"arxiv_id":"2303.11525","paper":"/paper/sift-sparse-iso-flop-transformations-for","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","date":"2023-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CerebrasResearch/Sparse-IFT","path":"cbsparse/sparse/optimizers/utils.py","file_url":"https://github.com/CerebrasResearch/Sparse-IFT/blob/HEAD/cbsparse/sparse/optimizers/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":"9ac3b31a2048c5ee","mcp_get_code":{"code_sha256":"9ac3b31a2048c5ee"}}]}