{"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/evaluate-performance","entry":"evaluate_performance","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":3,"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":3,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"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":"2607.19312","paper":"/paper/arxiv-2607-19312","title":"Staypoint Detection from Noisy Trajectory Data [Experiment Paper]","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"amirih/staypoint","path":"code/approaches/alex.py","file_url":"https://github.com/amirih/staypoint/blob/HEAD/code/approaches/alex.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4133c2aa8768e631","mcp_get_code":{"code_sha256":"4133c2aa8768e631"}},{"arxiv_id":"2408.13654","paper":"/paper/symbolic-working-memory-enhances-language","title":"Symbolic Working Memory Enhances Language Models for Complex Rule Application","date":"2024-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"siyuanwangw/ruleapplication","path":"Src/evaluate.py","file_url":"https://github.com/siyuanwangw/ruleapplication/blob/HEAD/Src/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bf4cfef1d50731f1","mcp_get_code":{"code_sha256":"bf4cfef1d50731f1"}},{"arxiv_id":"2407.08770","paper":"/paper/model-surgery-modulating-llm-s-behavior-via","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","date":"2024-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucywang720/model-surgery","path":"train/run_pplm_discrim_train.py","file_url":"https://github.com/lucywang720/model-surgery/blob/HEAD/train/run_pplm_discrim_train.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c1515ec6a041a7e6","mcp_get_code":{"code_sha256":"c1515ec6a041a7e6"}},{"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":"evaluate.py","file_url":"https://github.com/Aiden0526/SymbCoT/blob/HEAD/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"175a1319fe2df65c","mcp_get_code":{"code_sha256":"175a1319fe2df65c"}},{"arxiv_id":"2312.11754","paper":"/paper/a-bayesian-spatial-model-to-correct-under","title":"A Bayesian Spatial Model to Correct Under-Reporting in Urban Crowdsourcing","date":"2023-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gsagostini/networks_underreporting","path":"d03_src/evaluate_utils.py","file_url":"https://github.com/gsagostini/networks_underreporting/blob/HEAD/d03_src/evaluate_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2196c5ac030bd5c6","mcp_get_code":{"code_sha256":"2196c5ac030bd5c6"}},{"arxiv_id":"2306.07261","paper":"/paper/unprocessing-seven-years-of-algorithmic","title":"Unprocessing Seven Years of Algorithmic Fairness","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"socialfoundations/error-parity","path":"error_parity/evaluation.py","file_url":"https://github.com/socialfoundations/error-parity/blob/HEAD/error_parity/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39cf6fea798aec32","mcp_get_code":{"code_sha256":"39cf6fea798aec32"}},{"arxiv_id":"2206.03200","paper":"/paper/fairvfl-a-fair-vertical-federated-learning","title":"FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning","date":"2022-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taoqi98/fairvfl","path":"Adult/evaluation.py","file_url":"https://github.com/taoqi98/fairvfl/blob/HEAD/Adult/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"66e15f4aa7e87d58","mcp_get_code":{"code_sha256":"66e15f4aa7e87d58"}},{"arxiv_id":"2105.08683","paper":"/paper/learning-embeddings-from-knowledge-graphs","title":"Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes","date":"2021-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Accenture/AmpliGraph","path":"ampligraph/compat/evaluate.py","file_url":"https://github.com/Accenture/AmpliGraph/blob/HEAD/ampligraph/compat/evaluate.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":"b2164845d6c66f4a","mcp_get_code":{"code_sha256":"b2164845d6c66f4a"}},{"arxiv_id":"1912.02164","paper":"/paper/plug-and-play-language-models-a-simple","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","date":"2019-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jefflai108/6.438-final","path":"run_pplm_discrim_train.py","file_url":"https://github.com/jefflai108/6.438-final/blob/HEAD/run_pplm_discrim_train.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":"368c3700824b81fb","mcp_get_code":{"code_sha256":"368c3700824b81fb"}}]}