{"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/generate-completion","entry":"generate_completion","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":1,"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":5,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":4},"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":"2602.03876","paper":"/paper/arxiv-2602-03876","title":"GOPO: Policy Optimization using Ranked Rewards","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"friendshipkim/gopo","path":"generate/generate_completions.py","file_url":"https://github.com/friendshipkim/gopo/blob/HEAD/generate/generate_completions.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":"f7346acce8a48a37","mcp_get_code":{"code_sha256":"f7346acce8a48a37"}},{"arxiv_id":"2503.06580","paper":"/paper/agent-models-internalizing-chain-of-action","title":"Agent models: Internalizing Chain-of-Action Generation into Reasoning models","date":"2025-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adam-bjtu/autocoa","path":"models/vllm_server.py","file_url":"https://github.com/adam-bjtu/autocoa/blob/HEAD/models/vllm_server.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c89ca5a383e7a0bc","mcp_get_code":{"code_sha256":"c89ca5a383e7a0bc"}},{"arxiv_id":"2407.16237","paper":"/paper/origen-enhancing-rtl-code-generation-with","title":"OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pku-liang/origen","path":"evaluation/generate_lora.py","file_url":"https://github.com/pku-liang/origen/blob/HEAD/evaluation/generate_lora.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"91cb46c66865a133","mcp_get_code":{"code_sha256":"91cb46c66865a133"}},{"arxiv_id":"2406.04531","paper":"/paper/testeval-benchmarking-large-language-models","title":"TESTEVAL: Benchmarking Large Language Models for Test Case Generation","date":null,"month_inferred_from_arxiv_id":"2024-06","title_source":"archive","repo":"llm4softwaretesting/testeval","path":"gen_linecov_cot_hf.py","file_url":"https://github.com/llm4softwaretesting/testeval/blob/HEAD/gen_linecov_cot_hf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"092972ae0ca5e520","mcp_get_code":{"code_sha256":"092972ae0ca5e520"}},{"arxiv_id":"2306.05685","paper":"/paper/judging-llm-as-a-judge-with-mt-bench-and-1","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","date":"2023-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"formulamonks/llm-benchmarker-suite","path":"eval_levels/large_language_model.py","file_url":"https://github.com/formulamonks/llm-benchmarker-suite/blob/HEAD/eval_levels/large_language_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"93e8875d6f69828c","mcp_get_code":{"code_sha256":"93e8875d6f69828c"}}]}