{"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/process-batch-eval","entry":"process_batch_eval","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":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":4,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"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":"2408.16500","paper":"/paper/cogvlm2-visual-language-models-for-image-and","title":"CogVLM2: Visual Language Models for Image and Video Understanding","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/glm-4","path":"finetune/finetune.py","file_url":"https://github.com/thudm/glm-4/blob/HEAD/finetune/finetune.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":"2cc2c269bdedbd33","mcp_get_code":{"code_sha256":"2cc2c269bdedbd33"}},{"arxiv_id":"2408.16500","paper":"/paper/cogvlm2-visual-language-models-for-image-and","title":"CogVLM2: Visual Language Models for Image and Video Understanding","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/glm-4","path":"finetune/finetune_vision.py","file_url":"https://github.com/thudm/glm-4/blob/HEAD/finetune/finetune_vision.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":"e816697d6260afdd","mcp_get_code":{"code_sha256":"e816697d6260afdd"}},{"arxiv_id":"2406.12793","paper":"/paper/chatglm-a-family-of-large-language-models","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/chatglm4","path":"finetune/finetune.py","file_url":"https://github.com/thudm/chatglm4/blob/HEAD/finetune/finetune.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":"2cc2c269bdedbd33","mcp_get_code":{"code_sha256":"2cc2c269bdedbd33"}},{"arxiv_id":"2406.12793","paper":"/paper/chatglm-a-family-of-large-language-models","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/chatglm","path":"finetune_demo/finetune_hf.py","file_url":"https://github.com/thudm/chatglm/blob/HEAD/finetune_demo/finetune_hf.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":"5abe708b88a719ff","mcp_get_code":{"code_sha256":"5abe708b88a719ff"}},{"arxiv_id":"2406.12793","paper":"/paper/chatglm-a-family-of-large-language-models","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/chatglm4","path":"finetune/finetune_vision.py","file_url":"https://github.com/thudm/chatglm4/blob/HEAD/finetune/finetune_vision.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":"e816697d6260afdd","mcp_get_code":{"code_sha256":"e816697d6260afdd"}},{"arxiv_id":"2406.05925","paper":"/paper/hello-again-llm-powered-personalized-agent","title":"Hello Again! LLM-powered Personalized Agent for Long-term Dialogue","date":"2024-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leolee99/ld-agent","path":"Trainer/lora_tune.py","file_url":"https://github.com/leolee99/ld-agent/blob/HEAD/Trainer/lora_tune.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5abe708b88a719ff","mcp_get_code":{"code_sha256":"5abe708b88a719ff"}},{"arxiv_id":"2312.08914","paper":"/paper/cogagent-a-visual-language-model-for-gui","title":"CogAgent: A Visual Language Model for GUI Agents","date":"2023-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUDM/CogAgent","path":"finetune/finetune.py","file_url":"https://github.com/THUDM/CogAgent/blob/HEAD/finetune/finetune.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":"0c9a09bd7e2934b7","mcp_get_code":{"code_sha256":"0c9a09bd7e2934b7"}},{"arxiv_id":"2025.naacl-long.272","paper":null,"title":"arXiv:2025.naacl-long.272","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"leolee99/LD-Agent","path":"Trainer/lora_tune.py","file_url":"https://github.com/leolee99/LD-Agent/blob/HEAD/Trainer/lora_tune.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5abe708b88a719ff","mcp_get_code":{"code_sha256":"5abe708b88a719ff"}}]}