{"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-scores","entry":"load_scores","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":10,"n_papers_ran":4,"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":11,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":7},"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":"2608.22817","paper":"/paper/arxiv-2608-22817","title":"Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"parssky/industrial-instruction","path":"package_benchmark_mmlu/compare.py","file_url":"https://github.com/parssky/industrial-instruction/blob/HEAD/package_benchmark_mmlu/compare.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"4637fd4e0d8e5a33","mcp_get_code":{"code_sha256":"4637fd4e0d8e5a33"}},{"arxiv_id":"2608.05025","paper":"/paper/arxiv-2608-05025","title":"Comparing SGLD and a fixed-noise Predictor-Corrector adaptation in canonical Joint Energy-Based Models on CIFAR-10","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"DmytroKnopov/jem-sampler-comparison","path":"evaluation/paired_bootstrap.py","file_url":"https://github.com/DmytroKnopov/jem-sampler-comparison/blob/HEAD/evaluation/paired_bootstrap.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"842b64fc488fb0fe","mcp_get_code":{"code_sha256":"842b64fc488fb0fe"}},{"arxiv_id":"2608.05025","paper":"/paper/arxiv-2608-05025","title":"Comparing SGLD and a fixed-noise Predictor-Corrector adaptation in canonical Joint Energy-Based Models on CIFAR-10","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"DmytroKnopov/jem-sampler-comparison","path":"evaluation/hierarchical_bootstrap.py","file_url":"https://github.com/DmytroKnopov/jem-sampler-comparison/blob/HEAD/evaluation/hierarchical_bootstrap.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5e3e432b6d99f283","mcp_get_code":{"code_sha256":"5e3e432b6d99f283"}},{"arxiv_id":"2607.13905","paper":"/paper/arxiv-2607-13905","title":"The 2 nd International StepUP Competition for Biometric Footstep Recognition: From Steps to Strides","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"AnantG5/STEP-UP","path":"code/fuse_rank_scores.py","file_url":"https://github.com/AnantG5/STEP-UP/blob/HEAD/code/fuse_rank_scores.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"73e4108feb752289","mcp_get_code":{"code_sha256":"73e4108feb752289"}},{"arxiv_id":"2605.30447","paper":"/paper/arxiv-2605-30447","title":"Calibrated Preference Learning: The Case of Label Ranking","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Advueu963/Calibrated_Preference_Learning","path":"analyze_rb_logit_diff.py","file_url":"https://github.com/Advueu963/Calibrated_Preference_Learning/blob/HEAD/analyze_rb_logit_diff.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e83ea18ca7066d9e","mcp_get_code":{"code_sha256":"e83ea18ca7066d9e"}},{"arxiv_id":"2601.00223","paper":"/paper/arxiv-2601-00223","title":"JP-TL-Bench: Anchored Pairwise LLM Evaluation for Bidirectional Japanese-English Translation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"lhl/liquid-ai-hackathon-tokyo","path":"eval/report_mt_scores.py","file_url":"https://github.com/lhl/liquid-ai-hackathon-tokyo/blob/HEAD/eval/report_mt_scores.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"65555b5705b00f44","mcp_get_code":{"code_sha256":"65555b5705b00f44"}},{"arxiv_id":"2510.17847","paper":"/paper/arxiv-2510-17847","title":"COIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"SuDIS-ZJU/CoIDO","path":"coido_scorer/stage2.py","file_url":"https://github.com/SuDIS-ZJU/CoIDO/blob/HEAD/coido_scorer/stage2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"a86c7a05bc91f15b","mcp_get_code":{"code_sha256":"a86c7a05bc91f15b"}},{"arxiv_id":"2402.14992","paper":"/paper/tinybenchmarks-evaluating-llms-with-fewer","title":"tinyBenchmarks: evaluating LLMs with fewer examples","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"felipemaiapolo/efficbench","path":"plots.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/plots.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9d2ac225248cfcc2","mcp_get_code":{"code_sha256":"9d2ac225248cfcc2"}},{"arxiv_id":"2402.12501","paper":"/paper/your-vision-language-model-itself-is-a-strong","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rayruibochen/self-filter","path":"self_filter/stage2.py","file_url":"https://github.com/rayruibochen/self-filter/blob/HEAD/self_filter/stage2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"17ea60a8bf7dc6fd","mcp_get_code":{"code_sha256":"17ea60a8bf7dc6fd"}},{"arxiv_id":"2305.14734","paper":"/paper/advancements-in-arabic-grammatical-error","title":"Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CAMeL-Lab/arabic-gec","path":"gec/stat_significance/significance.py","file_url":"https://github.com/CAMeL-Lab/arabic-gec/blob/HEAD/gec/stat_significance/significance.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b7aecf3e97533ea9","mcp_get_code":{"code_sha256":"b7aecf3e97533ea9"}},{"arxiv_id":"2304.04521","paper":"/paper/zero-shot-in-distribution-detection-in-multi","title":"GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection","date":"2023-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"atsumiyai/gl-mcm","path":"utils/file_ops.py","file_url":"https://github.com/atsumiyai/gl-mcm/blob/HEAD/utils/file_ops.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2358075eb310a541","mcp_get_code":{"code_sha256":"2358075eb310a541"}}]}