{"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/num-parameters","entry":"num_parameters","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":6,"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":6,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":1,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"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":"2606.14971","paper":"/paper/arxiv-2606-14971","title":"FastMix: Fast Data Mixture Optimization via Gradient Descent","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"hrtan/fastmix","path":"lit_gpt/utils.py","file_url":"https://github.com/hrtan/fastmix/blob/HEAD/lit_gpt/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"367d564f9b814546","mcp_get_code":{"code_sha256":"367d564f9b814546"}},{"arxiv_id":"2408.15793","paper":"/paper/language-adaptation-on-a-tight-academic","title":"Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough","date":"2024-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"konstantinjdobler/tight-budget-llm-adaptation","path":"dlib/utils.py","file_url":"https://github.com/konstantinjdobler/tight-budget-llm-adaptation/blob/HEAD/dlib/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5109370b9cf73f69","mcp_get_code":{"code_sha256":"5109370b9cf73f69"}},{"arxiv_id":"2406.06046","paper":"/paper/mates-model-aware-data-selection-for","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cxcscmu/MATES","path":"src/lit_gpt/utils.py","file_url":"https://github.com/cxcscmu/MATES/blob/HEAD/src/lit_gpt/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cfb725c11fe2d2f7","mcp_get_code":{"code_sha256":"cfb725c11fe2d2f7"}},{"arxiv_id":"2206.07585","paper":"/paper/natgen-generative-pre-training-by","title":"NatGen: Generative pre-training by \"Naturalizing\" source code","date":"2022-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saikat107/natgen","path":"src/pretraining/pretrain.py","file_url":"https://github.com/saikat107/natgen/blob/HEAD/src/pretraining/pretrain.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f7d1b1038d973c06","mcp_get_code":{"code_sha256":"f7d1b1038d973c06"}},{"arxiv_id":"2106.12917","paper":"/paper/continuous-time-deep-glioma-growth-models","title":"Continuous-Time Deep Glioma Growth Models","date":"2021-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MIC-DKFZ/deep-glioma-growth","path":"gliomagrowth/util/util.py","file_url":"https://github.com/MIC-DKFZ/deep-glioma-growth/blob/HEAD/gliomagrowth/util/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6de6c421700a69a","mcp_get_code":{"code_sha256":"b6de6c421700a69a"}},{"arxiv_id":"1910.06379","paper":"/paper/dual-path-rnn-efficient-long-sequence","title":"Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation","date":"2019-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fgnt/padertorch","path":"padertorch/summary/model_info.py","file_url":"https://github.com/fgnt/padertorch/blob/HEAD/padertorch/summary/model_info.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61842f44f2c99c11","mcp_get_code":{"code_sha256":"61842f44f2c99c11"}}]}