{"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-perplexity-and-embedding-part-text","entry":"get_perplexity_and_embedding_part_text","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":7,"n_papers_ran":3,"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":1,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":6,"by_status":{"ran_honours":1,"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":"2505.07437","paper":"/paper/lead-iterative-data-selection-for-efficient","title":"LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning","date":"2025-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HKUSTDial/LEAD","path":"src/offline/difficulty_score.py","file_url":"https://github.com/HKUSTDial/LEAD/blob/HEAD/src/offline/difficulty_score.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"652eac296628dd5e","mcp_get_code":{"code_sha256":"652eac296628dd5e"}},{"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":"IFD/cherry_seletion/data_analysis.py","file_url":"https://github.com/xiatingyu/sft-dataselection-at-scale/blob/HEAD/IFD/cherry_seletion/data_analysis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"48b1bd5978f1385e","mcp_get_code":{"code_sha256":"48b1bd5978f1385e"}},{"arxiv_id":"2410.05725","paper":"/paper/knowledgesg-privacy-preserving-synthetic-text","title":"KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wwh0411/KnowledgeSG","path":"evaluation/ifd_gene.py","file_url":"https://github.com/wwh0411/KnowledgeSG/blob/HEAD/evaluation/ifd_gene.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"48b1bd5978f1385e","mcp_get_code":{"code_sha256":"48b1bd5978f1385e"}},{"arxiv_id":"2402.10110","paper":"/paper/selective-reflection-tuning-student-selected","title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingliiii/reflection_tuning","path":"selection_code/data_analysis.py","file_url":"https://github.com/mingliiii/reflection_tuning/blob/HEAD/selection_code/data_analysis.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"906dab8ee3c01e55","mcp_get_code":{"code_sha256":"906dab8ee3c01e55"}},{"arxiv_id":"2402.00530","paper":"/paper/superfiltering-weak-to-strong-data-filtering","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","date":"2024-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianyi-lab/superfiltering","path":"code_ifd/data_analysis.py","file_url":"https://github.com/tianyi-lab/superfiltering/blob/HEAD/code_ifd/data_analysis.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"906dab8ee3c01e55","mcp_get_code":{"code_sha256":"906dab8ee3c01e55"}},{"arxiv_id":"2310.11716","paper":"/paper/reflection-tuning-data-recycling-improves-llm","title":"Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning","date":"2023-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianyi-lab/reflection_tuning","path":"selection_code/data_analysis.py","file_url":"https://github.com/tianyi-lab/reflection_tuning/blob/HEAD/selection_code/data_analysis.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"906dab8ee3c01e55","mcp_get_code":{"code_sha256":"906dab8ee3c01e55"}},{"arxiv_id":"2308.12032","paper":"/paper/from-quantity-to-quality-boosting-llm","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","date":"2023-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianyi-lab/cherry_llm","path":"cherry_seletion/data_analysis.py","file_url":"https://github.com/tianyi-lab/cherry_llm/blob/HEAD/cherry_seletion/data_analysis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"48b1bd5978f1385e","mcp_get_code":{"code_sha256":"48b1bd5978f1385e"}}]}