{"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/cal-score","entry":"cal_score","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":5,"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":9,"n_samples_ran":5,"n_samples_fingerprinted":1,"n_places":9,"n_places_pointer_only":2,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":4},"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":"2407.13998","paper":"/paper/rag-qa-arena-evaluating-domain-robustness-for","title":"RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering","date":"2024-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awslabs/rag-qa-arena","path":"code/compute_correlation.py","file_url":"https://github.com/awslabs/rag-qa-arena/blob/HEAD/code/compute_correlation.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":"f9c8fa3e82ecea98","mcp_get_code":{"code_sha256":"f9c8fa3e82ecea98"}},{"arxiv_id":"2406.16855","paper":"/paper/dreambench-a-human-aligned-benchmark-for","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuangpeng/dreambench_plus","path":"dreambench_plus/benchmarking.py","file_url":"https://github.com/yuangpeng/dreambench_plus/blob/HEAD/dreambench_plus/benchmarking.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"df3ab56ca1a39f90","mcp_get_code":{"code_sha256":"df3ab56ca1a39f90"}},{"arxiv_id":"2406.01960","paper":"/paper/certifiably-byzantine-robust-federated","title":"Certifiably Byzantine-Robust Federated Conformal Prediction","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kangmintong/rob-fcp","path":"src/fl_conformal.py","file_url":"https://github.com/kangmintong/rob-fcp/blob/HEAD/src/fl_conformal.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e144bd5eea16d6a0","mcp_get_code":{"code_sha256":"e144bd5eea16d6a0"}},{"arxiv_id":"2402.01830","paper":"/paper/peer-review-in-llms-automatic-evaluation","title":"PiCO: Peer Review in LLMs based on the Consistency Optimization","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PKU-YuanGroup/Peer-review-in-LLMs","path":"con_optimization/main_ablation.py","file_url":"https://github.com/PKU-YuanGroup/Peer-review-in-LLMs/blob/HEAD/con_optimization/main_ablation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7812a2ea4cd6d368","mcp_get_code":{"code_sha256":"7812a2ea4cd6d368"}},{"arxiv_id":"2302.01860","paper":"/paper/gladis-a-general-and-large-acronym","title":"GLADIS: A General and Large Acronym Disambiguation Benchmark","date":"2023-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tigerchen52/gladis","path":"inference/acrobert.py","file_url":"https://github.com/tigerchen52/gladis/blob/HEAD/inference/acrobert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"6739933e9af3e095","mcp_get_code":{"code_sha256":"6739933e9af3e095"}},{"arxiv_id":"2208.01230","paper":"/paper/a-multifaceted-benchmarking-of-synthetic","title":"A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Models","date":"2022-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yy6linda/synthetic-ehr-benchmarking","path":"privacy_evaluation/Synthetic_risk_model_attr.py","file_url":"https://github.com/yy6linda/synthetic-ehr-benchmarking/blob/HEAD/privacy_evaluation/Synthetic_risk_model_attr.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"50ffdcf01c471e6d","mcp_get_code":{"code_sha256":"50ffdcf01c471e6d"}},{"arxiv_id":"2207.11463","paper":"/paper/when-counting-meets-hmer-counting-aware","title":"When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition","date":"2022-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LBH1024/CAN","path":"utils.py","file_url":"https://github.com/LBH1024/CAN/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"02d543693c5cbc61","mcp_get_code":{"code_sha256":"02d543693c5cbc61"}},{"arxiv_id":"2206.06602","paper":"/paper/deep-isolation-forest-for-anomaly-detection","title":"Deep Isolation Forest for Anomaly Detection","date":"2022-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xuhongzuo/DeepOD","path":"deepod/models/tabular/dif.py","file_url":"https://github.com/xuhongzuo/DeepOD/blob/HEAD/deepod/models/tabular/dif.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"7360272baa832c6b","mcp_get_code":{"code_sha256":"7360272baa832c6b"}},{"arxiv_id":"2006.09286","paper":"/paper/on-the-computational-power-of-transformers","title":"On the Computational Power of Transformers and its Implications in Sequence Modeling","date":"2020-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"satwik77/Transformer-Computation-Analysis","path":"Transformer/src/utils/evaluate.py","file_url":"https://github.com/satwik77/Transformer-Computation-Analysis/blob/HEAD/Transformer/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":"34e826973176fc38","mcp_get_code":{"code_sha256":"34e826973176fc38"}}]}