{"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-crossannotations","entry":"get_crossannotations","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":5,"n_papers_ran":0,"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":2,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":2},"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":"tatsu-lab/alpaca_eval","path":"src/alpaca_eval/analyze.py","file_url":"https://github.com/tatsu-lab/alpaca_eval/blob/HEAD/src/alpaca_eval/analyze.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":"de8a267bb7f7d4bd","mcp_get_code":{"code_sha256":"de8a267bb7f7d4bd"}},{"arxiv_id":"2502.01534","paper":"/paper/preference-leakage-a-contamination-problem-in","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","date":"2025-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"david-li0406/preference-leakage","path":"evaluation/Alpaca_Eval2/src/alpaca_eval/analyze.py","file_url":"https://github.com/david-li0406/preference-leakage/blob/HEAD/evaluation/Alpaca_Eval2/src/alpaca_eval/analyze.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"de8a267bb7f7d4bd","mcp_get_code":{"code_sha256":"de8a267bb7f7d4bd"}},{"arxiv_id":"2410.08964","paper":"/paper/language-imbalance-driven-rewarding-for","title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","date":"2024-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","path":"alpaca_eval/src/alpaca_eval/analyze.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/alpaca_eval/src/alpaca_eval/analyze.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"de8a267bb7f7d4bd","mcp_get_code":{"code_sha256":"de8a267bb7f7d4bd"}},{"arxiv_id":"2406.04692","paper":"/paper/mixture-of-agents-enhances-large-language","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"de8a267bb7f7d4bd","mcp_get_code":{"code_sha256":"de8a267bb7f7d4bd"}},{"arxiv_id":"2402.18667","paper":"/paper/fofo-a-benchmark-to-evaluate-llms-format","title":"FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforceairesearch/fofo","path":"alpaca_eval/src/alpaca_eval/analyze.py","file_url":"https://github.com/salesforceairesearch/fofo/blob/HEAD/alpaca_eval/src/alpaca_eval/analyze.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":"35e948b2f38e9582","mcp_get_code":{"code_sha256":"35e948b2f38e9582"}}]}