{"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/calc-metrics","entry":"calc_metrics","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":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":9,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"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":"2607.29168","paper":"/paper/arxiv-2607-29168","title":"Authorship Verification of Transcribed German-Language Videos","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Fraunhofer-SIT/WIFS2026-TranscribedGermanAV","path":"common.py","file_url":"https://github.com/Fraunhofer-SIT/WIFS2026-TranscribedGermanAV/blob/HEAD/common.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":"af822b1447bf45aa","mcp_get_code":{"code_sha256":"af822b1447bf45aa"}},{"arxiv_id":"2605.14888","paper":"/paper/arxiv-2605-14888","title":"PROCESS-2: A Benchmark Speech Corpus for Early Cognitive Impairment Detection","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"CognoSpeak/PROCESS-2","path":"codes/PROCESS2_BASELINE_LLM.py","file_url":"https://github.com/CognoSpeak/PROCESS-2/blob/HEAD/codes/PROCESS2_BASELINE_LLM.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":"fb6dacde90d3d10b","mcp_get_code":{"code_sha256":"fb6dacde90d3d10b"}},{"arxiv_id":"2312.10890","paper":"/paper/low-latency-space-time-supersampling-for-real","title":"Low-latency Space-time Supersampling for Real-time Rendering","date":"2023-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryanhe312/STSSNet-AAAI2024","path":"utils/matlab_metric.py","file_url":"https://github.com/ryanhe312/STSSNet-AAAI2024/blob/HEAD/utils/matlab_metric.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa273a27e3ac59d7","mcp_get_code":{"code_sha256":"aa273a27e3ac59d7"}},{"arxiv_id":"2310.05885","paper":"/paper/dtpp-differentiable-joint-conditional","title":"DTPP: Differentiable Joint Conditional Prediction and Cost Evaluation for Tree Policy Planning in Autonomous Driving","date":null,"month_inferred_from_arxiv_id":"2023-10","title_source":"archive","repo":"mczhi/dtpp","path":"train_utils.py","file_url":"https://github.com/mczhi/dtpp/blob/HEAD/train_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":"992910bad800e5b8","mcp_get_code":{"code_sha256":"992910bad800e5b8"}},{"arxiv_id":"2309.12253","paper":"/paper/salsa-clrs-a-sparse-and-scalable-benchmark","title":"SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning","date":"2023-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jkminder/salsa-clrs","path":"baselines/core/metrics.py","file_url":"https://github.com/jkminder/salsa-clrs/blob/HEAD/baselines/core/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":"f241688601e43b20","mcp_get_code":{"code_sha256":"f241688601e43b20"}},{"arxiv_id":"2307.07002","paper":"/paper/classical-out-of-distribution-detection","title":"Classical Out-of-Distribution Detection Methods Benchmark in Text Classification Tasks","date":"2023-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mateuszbaransanok/TrustworthyAI","path":"trustworthyai/utils/metrics.py","file_url":"https://github.com/mateuszbaransanok/TrustworthyAI/blob/HEAD/trustworthyai/utils/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a356e503fd42cd9a","mcp_get_code":{"code_sha256":"a356e503fd42cd9a"}},{"arxiv_id":"2307.02028","paper":"/paper/ehrshot-an-ehr-benchmark-for-few-shot-1","title":"EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models","date":"2023-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"som-shahlab/ehrshot-benchmark","path":"ehrshot/7b_eval_zero_shot.py","file_url":"https://github.com/som-shahlab/ehrshot-benchmark/blob/HEAD/ehrshot/7b_eval_zero_shot.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":"e387d3515af3e462","mcp_get_code":{"code_sha256":"e387d3515af3e462"}},{"arxiv_id":"2306.06955","paper":"/paper/a-brief-review-of-hypernetworks-in-deep","title":"A Brief Review of Hypernetworks in Deep Learning","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jmdvinodjmd/HyperITE","path":"src/utils.py","file_url":"https://github.com/jmdvinodjmd/HyperITE/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b96b4b3c56d7f938","mcp_get_code":{"code_sha256":"b96b4b3c56d7f938"}},{"arxiv_id":"2002.08772","paper":"/paper/set2graph-learning-graphs-from-sets","title":"Set2Graph: Learning Graphs From Sets","date":"2020-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hadarser/SetToGraphPaper","path":"main_scripts/main_jets.py","file_url":"https://github.com/hadarser/SetToGraphPaper/blob/HEAD/main_scripts/main_jets.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3979bb6a4cc7dc13","mcp_get_code":{"code_sha256":"3979bb6a4cc7dc13"}}]}