{"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/adapter-filter","entry":"adapter_filter","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":5,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":9,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2504.11393","paper":"/paper/datadecide-how-to-predict-best-pretraining","title":"DataDecide: How to Predict Best Pretraining Data with Small Experiments","date":"2025-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/prox","path":"train/lit_gpt/adapter_v2.py","file_url":"https://github.com/gair-nlp/prox/blob/HEAD/train/lit_gpt/adapter_v2.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":"e05d85cc898c445c","mcp_get_code":{"code_sha256":"e05d85cc898c445c"}},{"arxiv_id":"2504.11393","paper":"/paper/datadecide-how-to-predict-best-pretraining","title":"DataDecide: How to Predict Best Pretraining Data with Small Experiments","date":"2025-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/prox","path":"train/lit_gpt/adapter.py","file_url":"https://github.com/gair-nlp/prox/blob/HEAD/train/lit_gpt/adapter.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":"38ffb0df89b0d01f","mcp_get_code":{"code_sha256":"38ffb0df89b0d01f"}},{"arxiv_id":"2503.15450","paper":"/paper/skyladder-better-and-faster-pretraining-via","title":"SkyLadder: Better and Faster Pretraining via Context Window Scheduling","date":"2025-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/skyladder","path":"lit_gpt/adapter_v2.py","file_url":"https://github.com/sail-sg/skyladder/blob/HEAD/lit_gpt/adapter_v2.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":"e05d85cc898c445c","mcp_get_code":{"code_sha256":"e05d85cc898c445c"}},{"arxiv_id":"2503.15450","paper":"/paper/skyladder-better-and-faster-pretraining-via","title":"SkyLadder: Better and Faster Pretraining via Context Window Scheduling","date":"2025-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/skyladder","path":"lit_gpt/adapter.py","file_url":"https://github.com/sail-sg/skyladder/blob/HEAD/lit_gpt/adapter.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":"38ffb0df89b0d01f","mcp_get_code":{"code_sha256":"38ffb0df89b0d01f"}},{"arxiv_id":"2401.10446","paper":"/paper/large-language-models-are-efficient-learners","title":"Large Language Models are Efficient Learners of Noise-Robust Speech Recognition","date":"2024-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuchen005/robustger","path":"lit_gpt/robust_ger.py","file_url":"https://github.com/yuchen005/robustger/blob/HEAD/lit_gpt/robust_ger.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fcb7aede4037cbda","mcp_get_code":{"code_sha256":"fcb7aede4037cbda"}},{"arxiv_id":"2401.02385","paper":"/paper/tinyllama-an-open-source-small-language-model","title":"TinyLlama: An Open-Source Small Language Model","date":"2024-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jzhang38/tinyllama","path":"lit_gpt/adapter_v2.py","file_url":"https://github.com/jzhang38/tinyllama/blob/HEAD/lit_gpt/adapter_v2.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":"e05d85cc898c445c","mcp_get_code":{"code_sha256":"e05d85cc898c445c"}},{"arxiv_id":"2401.02385","paper":"/paper/tinyllama-an-open-source-small-language-model","title":"TinyLlama: An Open-Source Small Language Model","date":"2024-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jzhang38/tinyllama","path":"lit_gpt/adapter.py","file_url":"https://github.com/jzhang38/tinyllama/blob/HEAD/lit_gpt/adapter.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":"38ffb0df89b0d01f","mcp_get_code":{"code_sha256":"38ffb0df89b0d01f"}},{"arxiv_id":"2025.acl-industry.15","paper":null,"title":"arXiv:2025.acl-industry.15","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Lightning-AI/litgpt","path":"litgpt/adapter.py","file_url":"https://github.com/Lightning-AI/litgpt/blob/HEAD/litgpt/adapter.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":"e15c0e4da87f1c21","mcp_get_code":{"code_sha256":"e15c0e4da87f1c21"}},{"arxiv_id":"2025.acl-industry.15","paper":null,"title":"arXiv:2025.acl-industry.15","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Lightning-AI/litgpt","path":"litgpt/adapter_v2.py","file_url":"https://github.com/Lightning-AI/litgpt/blob/HEAD/litgpt/adapter_v2.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":"b0bb742b80d352ad","mcp_get_code":{"code_sha256":"b0bb742b80d352ad"}}]}