{"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/load-raw-dataset","entry":"load_raw_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":8,"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":7,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"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":"2410.09350","paper":"/paper/generative-subgraph-retrieval-for-knowledge","title":"Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlvlab/dialoggsr","path":"utils/utils.py","file_url":"https://github.com/mlvlab/dialoggsr/blob/HEAD/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ac67481c2fa09b5","mcp_get_code":{"code_sha256":"3ac67481c2fa09b5"}},{"arxiv_id":"2408.13654","paper":"/paper/symbolic-working-memory-enhances-language","title":"Symbolic Working Memory Enhances Language Models for Complex Rule Application","date":"2024-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"siyuanwangw/ruleapplication","path":"Src/evaluate.py","file_url":"https://github.com/siyuanwangw/ruleapplication/blob/HEAD/Src/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d8e076b666a81e08","mcp_get_code":{"code_sha256":"d8e076b666a81e08"}},{"arxiv_id":"2407.15235","paper":"/paper/tagcos-task-agnostic-gradient-clustered","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","date":"2024-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"2003pro/tagcos","path":"data_selection/get_training_dataset.py","file_url":"https://github.com/2003pro/tagcos/blob/HEAD/data_selection/get_training_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"312258b87e676409","mcp_get_code":{"code_sha256":"312258b87e676409"}},{"arxiv_id":"2405.04746","paper":"/paper/svd-ae-simple-autoencoders-for-collaborative","title":"SVD-AE: Simple Autoencoders for Collaborative Filtering","date":"2024-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seoyoungh/svd-ae","path":"data.py","file_url":"https://github.com/seoyoungh/svd-ae/blob/HEAD/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55ab6b432bbbdc36","mcp_get_code":{"code_sha256":"55ab6b432bbbdc36"}},{"arxiv_id":"2403.11124","paper":"/paper/scaling-data-diversity-for-fine-tuning","title":"Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment","date":"2024-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"f2-song/scalingalignment","path":"data_preprocess/split.py","file_url":"https://github.com/f2-song/scalingalignment/blob/HEAD/data_preprocess/split.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"814d25f588e5f6e9","mcp_get_code":{"code_sha256":"814d25f588e5f6e9"}},{"arxiv_id":"2402.11863","paper":"/paper/how-interpretable-are-reasoning-explanations","title":"How Interpretable are Reasoning Explanations from Prompting Large Language Models?","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wj210/cot_interpretability","path":"utils/data_helper.py","file_url":"https://github.com/wj210/cot_interpretability/blob/HEAD/utils/data_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b2d1503e1d9306ee","mcp_get_code":{"code_sha256":"b2d1503e1d9306ee"}},{"arxiv_id":"2402.04333","paper":"/paper/less-selecting-influential-data-for-targeted","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/less","path":"less/data_selection/get_training_dataset.py","file_url":"https://github.com/princeton-nlp/less/blob/HEAD/less/data_selection/get_training_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"312258b87e676409","mcp_get_code":{"code_sha256":"312258b87e676409"}},{"arxiv_id":"2206.02626","paper":"/paper/infinite-recommendation-networks-a-data","title":"Infinite Recommendation Networks: A Data-Centric Approach","date":"2022-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"noveens/infinite_ae_cf","path":"data.py","file_url":"https://github.com/noveens/infinite_ae_cf/blob/HEAD/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a16c3bab848068f1","mcp_get_code":{"code_sha256":"a16c3bab848068f1"}}]}