{"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-and-tokenize-prompt","entry":"generate_and_tokenize_prompt","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":8,"n_papers_ran":5,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":3},"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":"2410.09335","paper":"/paper/rethinking-data-selection-at-scale-random","title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiatingyu/sft-dataselection-at-scale","path":"diverse/utils.py","file_url":"https://github.com/xiatingyu/sft-dataselection-at-scale/blob/HEAD/diverse/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ea8f24a160d0f3ed","mcp_get_code":{"code_sha256":"ea8f24a160d0f3ed"}},{"arxiv_id":"2405.12915","paper":"/paper/g-dig-towards-gradient-based-diverse-and-high","title":"G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine Translation","date":"2024-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xypan0/G-DIG","path":"dataset/utils.py","file_url":"https://github.com/xypan0/G-DIG/blob/HEAD/dataset/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cdc59dd6fe0dbb68","mcp_get_code":{"code_sha256":"cdc59dd6fe0dbb68"}},{"arxiv_id":"2403.07384","paper":"/paper/smalltolarge-s2l-scalable-data-selection-for","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigml-cs-ucla/s2l","path":"utils.py","file_url":"https://github.com/bigml-cs-ucla/s2l/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ea8f24a160d0f3ed","mcp_get_code":{"code_sha256":"ea8f24a160d0f3ed"}},{"arxiv_id":"2401.08508","paper":"/paper/emollms-a-series-of-emotional-large-language","title":"EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis","date":"2024-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lzw108/emollms","path":"src/sample_generator.py","file_url":"https://github.com/lzw108/emollms/blob/HEAD/src/sample_generator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40a21adb12f75e1b","mcp_get_code":{"code_sha256":"40a21adb12f75e1b"}},{"arxiv_id":"2312.15698","paper":"/paper/repairllama-efficient-representations-and","title":"RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair","date":"2023-12-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"assert-kth/repairllama","path":"src/fft/full_finetune.py","file_url":"https://github.com/assert-kth/repairllama/blob/HEAD/src/fft/full_finetune.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"db623bc0364c5305","mcp_get_code":{"code_sha256":"db623bc0364c5305"}},{"arxiv_id":"2312.14115","paper":"/paper/lingoqa-video-question-answering-for","title":"LingoQA: Visual Question Answering for Autonomous Driving","date":"2023-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wayveai/driving-with-llms","path":"utils/training_utils.py","file_url":"https://github.com/wayveai/driving-with-llms/blob/HEAD/utils/training_utils.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":"b804c1be469fe22a","mcp_get_code":{"code_sha256":"b804c1be469fe22a"}},{"arxiv_id":"2311.08182","paper":"/paper/self-evolved-diverse-data-sampling-for","title":"Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ofa-sys/diverseevol","path":"utils.py","file_url":"https://github.com/ofa-sys/diverseevol/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ea8f24a160d0f3ed","mcp_get_code":{"code_sha256":"ea8f24a160d0f3ed"}},{"arxiv_id":"2302.13971","paper":"/paper/llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ntunlplab/traditional-chinese-alpaca","path":"code/finetune.py","file_url":"https://github.com/ntunlplab/traditional-chinese-alpaca/blob/HEAD/code/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":"ec1a43f948c4bfb1","mcp_get_code":{"code_sha256":"ec1a43f948c4bfb1"}}]}