{"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/get-categories","entry":"get_categories","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":8,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":9,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"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":"2606.10528","paper":"/paper/arxiv-2606-10528","title":"Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"lmarena/arena-hard-auto","path":"qa_browser.py","file_url":"https://github.com/lmarena/arena-hard-auto/blob/HEAD/qa_browser.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":"31d3137625992d50","mcp_get_code":{"code_sha256":"31d3137625992d50"}},{"arxiv_id":"2412.05467","paper":"/paper/the-browsergym-ecosystem-for-web-agent","title":"The BrowserGym Ecosystem for Web Agent Research","date":"2024-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"servicenow/workarena","path":"src/browsergym/workarena/api/category.py","file_url":"https://github.com/servicenow/workarena/blob/HEAD/src/browsergym/workarena/api/category.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ce62e9936fba1098","mcp_get_code":{"code_sha256":"ce62e9936fba1098"}},{"arxiv_id":"2412.00535","paper":"/paper/fullstack-bench-evaluating-llms-as-full-stack","title":"FullStack Bench: Evaluating LLMs as Full Stack Coders","date":"2024-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/sandboxfusion","path":"sandbox/datasets/humanevoeval.py","file_url":"https://github.com/bytedance/sandboxfusion/blob/HEAD/sandbox/datasets/humanevoeval.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":"c1ac2d1e1f9e2e6d","mcp_get_code":{"code_sha256":"c1ac2d1e1f9e2e6d"}},{"arxiv_id":"2406.11939","paper":"/paper/from-crowdsourced-data-to-high-quality","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lm-sys/arena-hard","path":"qa_browser.py","file_url":"https://github.com/lm-sys/arena-hard/blob/HEAD/qa_browser.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":"31d3137625992d50","mcp_get_code":{"code_sha256":"31d3137625992d50"}},{"arxiv_id":"2406.03589","paper":"/paper/ranking-manipulation-for-conversational","title":"Ranking Manipulation for Conversational Search Engines","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"spfrommer/cse-ranking-manipulation","path":"dataset.py","file_url":"https://github.com/spfrommer/cse-ranking-manipulation/blob/HEAD/dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"690bec63359f91e1","mcp_get_code":{"code_sha256":"690bec63359f91e1"}},{"arxiv_id":"2406.01506","paper":"/paper/the-geometry-of-categorical-and-hierarchical","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kihopark/llm_categorical_hierarchical_representations","path":"hierarchical/category.py","file_url":"https://github.com/kihopark/llm_categorical_hierarchical_representations/blob/HEAD/hierarchical/category.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c0cefa4cb672ea6f","mcp_get_code":{"code_sha256":"c0cefa4cb672ea6f"}},{"arxiv_id":"2110.15943","paper":"/paper/metaicl-learning-to-learn-in-context","title":"MetaICL: Learning to Learn In Context","date":"2021-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sambanova/generative_data_prep","path":"generative_data_prep/__main__.py","file_url":"https://github.com/sambanova/generative_data_prep/blob/HEAD/generative_data_prep/__main__.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":"bee73fe11d137291","mcp_get_code":{"code_sha256":"bee73fe11d137291"}},{"arxiv_id":"2104.07713","paper":"/paper/contrastive-learning-with-stronger-1","title":"Contrastive Learning with Stronger Augmentations","date":"2021-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maple-research-lab/CLSA","path":"VOC_CLF/utils.py","file_url":"https://github.com/maple-research-lab/CLSA/blob/HEAD/VOC_CLF/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d5de38f848a793c8","mcp_get_code":{"code_sha256":"d5de38f848a793c8"}},{"arxiv_id":"1904.06487","paper":"/paper/semi-supervised-domain-adaptation-via-minimax","title":"Semi-supervised Domain Adaptation via Minimax Entropy","date":"2019-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PrasannaPulakurthi/SPM","path":"utils.py","file_url":"https://github.com/PrasannaPulakurthi/SPM/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":"84a015f614f2cea5","mcp_get_code":{"code_sha256":"84a015f614f2cea5"}}]}