{"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/format-dataset","entry":"format_dataset","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":3,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":1},"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":"2608.04311","paper":"/paper/arxiv-2608-04311","title":"Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"dsgt-arc/joker-2025","path":"src/contrastive_learning.py","file_url":"https://github.com/dsgt-arc/joker-2025/blob/HEAD/src/contrastive_learning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a559c1d84a0dbdf4","mcp_get_code":{"code_sha256":"a559c1d84a0dbdf4"}},{"arxiv_id":"2404.11553","paper":"/paper/quantifying-multilingual-performance-of-large","title":"Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lizh9885/language-ranker","path":"utils.py","file_url":"https://github.com/lizh9885/language-ranker/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6dd15bd4e62653e4","mcp_get_code":{"code_sha256":"6dd15bd4e62653e4"}},{"arxiv_id":"2404.11531","paper":"/paper/pack-of-llms-model-fusion-at-test-time-via","title":"Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cmavro/packllm","path":"downstream_tasks/get_task.py","file_url":"https://github.com/cmavro/packllm/blob/HEAD/downstream_tasks/get_task.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"82fab1f6e6bddec2","mcp_get_code":{"code_sha256":"82fab1f6e6bddec2"}},{"arxiv_id":"2310.20046","paper":"/paper/which-examples-to-annotate-for-in-context","title":"Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/adaptive-in-context-learning","path":"get_task.py","file_url":"https://github.com/amazon-science/adaptive-in-context-learning/blob/HEAD/get_task.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":"82fab1f6e6bddec2","mcp_get_code":{"code_sha256":"82fab1f6e6bddec2"}},{"arxiv_id":"2212.09741","paper":"/paper/one-embedder-any-task-instruction-finetuned","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","date":"2022-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HKUNLP/instructor-embedding","path":"evaluation/prompt_retrieval/get_task.py","file_url":"https://github.com/HKUNLP/instructor-embedding/blob/HEAD/evaluation/prompt_retrieval/get_task.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":"82fab1f6e6bddec2","mcp_get_code":{"code_sha256":"82fab1f6e6bddec2"}}]}