{"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/count-lines","entry":"count_lines","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":23,"n_papers_ran":10,"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":21,"n_samples_ran":9,"n_samples_fingerprinted":3,"n_places":23,"n_places_pointer_only":4,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"unverified":12},"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":"2609.00918","paper":"/paper/arxiv-2609-00918","title":"RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"ZhongruChen/RPCBench","path":"src/step1/_step1_common.py","file_url":"https://github.com/ZhongruChen/RPCBench/blob/HEAD/src/step1/_step1_common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"113f62640daa6633","mcp_get_code":{"code_sha256":"113f62640daa6633"}},{"arxiv_id":"2609.00714","paper":"/paper/arxiv-2609-00714","title":"ChatDev 2.0: A No-Code Multi-Agent Platform for Developing Everything","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"OpenBMB/ChatDev","path":"frontend/src/count_lines.py","file_url":"https://github.com/OpenBMB/ChatDev/blob/HEAD/frontend/src/count_lines.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":"654d8bfb620330c1","mcp_get_code":{"code_sha256":"654d8bfb620330c1"}},{"arxiv_id":"2606.20993","paper":"/paper/arxiv-2606-20993","title":"Phonemes to the Rescue: Multilingual Tokenization Based on International Phonetic Alphabet","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Mikki99/ipa-tokenization","path":"src/ipa_tok/gpt2/cache.py","file_url":"https://github.com/Mikki99/ipa-tokenization/blob/HEAD/src/ipa_tok/gpt2/cache.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c645258c69182925","mcp_get_code":{"code_sha256":"c645258c69182925"}},{"arxiv_id":"2606.19121","paper":"/paper/arxiv-2606-19121","title":"Written by AI, Managed by AI: Semantic Space Control and Index Sickness Elimination Across 391 Consecutive Sessions","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"huidev2025/CSF","path":"cases/paper1/dlog/data-analysis/analyze_context_growth.py","file_url":"https://github.com/huidev2025/CSF/blob/HEAD/cases/paper1/dlog/data-analysis/analyze_context_growth.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a127f0dc8b975ae3","mcp_get_code":{"code_sha256":"a127f0dc8b975ae3"}},{"arxiv_id":"2602.17327","paper":"/paper/arxiv-2602-17327","title":"WebFAQ 2.0: A Multilingual QA Dataset with Mined Hard Negatives for Dense Retrieval","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"padas-lab-de/webfaq","path":"src/webfaq/utils.py","file_url":"https://github.com/padas-lab-de/webfaq/blob/HEAD/src/webfaq/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"48357c5d38b2da43","mcp_get_code":{"code_sha256":"48357c5d38b2da43"}},{"arxiv_id":"2602.08351","paper":"/paper/arxiv-2602-08351","title":"The Chicken and Egg Dilemma: Co-optimizing Data and Model Configurations for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"princeton-nlp/LESS","path":"less/data_selection/write_selected_data.py","file_url":"https://github.com/princeton-nlp/LESS/blob/HEAD/less/data_selection/write_selected_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"44e3cec9ab30944c","mcp_get_code":{"code_sha256":"44e3cec9ab30944c"}},{"arxiv_id":"2412.14063","paper":"/paper/rango-adaptive-retrieval-augmented-proving","title":"Rango: Adaptive Retrieval-Augmented Proving for Automated Software Verification","date":"2024-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rkthomps/coq-modeling","path":"src/data_management/jsonl_utils.py","file_url":"https://github.com/rkthomps/coq-modeling/blob/HEAD/src/data_management/jsonl_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b96a0bdb77eaf58c","mcp_get_code":{"code_sha256":"b96a0bdb77eaf58c"}},{"arxiv_id":"2406.17419","paper":"/paper/leave-no-document-behind-benchmarking-long","title":"Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MozerWang/Loong","path":"src/utils/util.py","file_url":"https://github.com/MozerWang/Loong/blob/HEAD/src/utils/util.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":"2de377da8e0f3e4b","mcp_get_code":{"code_sha256":"2de377da8e0f3e4b"}},{"arxiv_id":"2406.07302","paper":"/paper/bertaqa-how-much-do-language-models-know","title":"BertaQA: How Much Do Language Models Know About Local Culture?","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"juletx/bertaqa","path":"translate/dataset.py","file_url":"https://github.com/juletx/bertaqa/blob/HEAD/translate/dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c74ca09cfdbb61f9","mcp_get_code":{"code_sha256":"c74ca09cfdbb61f9"}},{"arxiv_id":"2405.16871","paper":"/paper/multi-behavior-generative-recommendation","title":"Multi-Behavior Generative Recommendation","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anananan116/MBGen","path":"tokenizer/utils.py","file_url":"https://github.com/anananan116/MBGen/blob/HEAD/tokenizer/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":"fce786d808bb6948","mcp_get_code":{"code_sha256":"fce786d808bb6948"}},{"arxiv_id":"2404.07677","paper":"/paper/oda-observation-driven-agent-for-integrating","title":"ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs","date":"2024-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lanjiuqing64/kgdata","path":"generate_subgraph/Wikidata/simple_wikidata_db/preprocess_utils/reader_process.py","file_url":"https://github.com/lanjiuqing64/kgdata/blob/HEAD/generate_subgraph/Wikidata/simple_wikidata_db/preprocess_utils/reader_process.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc84112f1c1a4ba1","mcp_get_code":{"code_sha256":"cc84112f1c1a4ba1"}},{"arxiv_id":"2402.14700","paper":"/paper/unveiling-linguistic-regions-in-large","title":"Unveiling Linguistic Regions in Large Language Models","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzhang0179/Unveiling-Linguistic-Regions-in-LLMs","path":"data_preprocess/preprocess-llama.py","file_url":"https://github.com/zzhang0179/Unveiling-Linguistic-Regions-in-LLMs/blob/HEAD/data_preprocess/preprocess-llama.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":"2797e4223999fe1e","mcp_get_code":{"code_sha256":"2797e4223999fe1e"}},{"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/write_selected_data.py","file_url":"https://github.com/princeton-nlp/less/blob/HEAD/less/data_selection/write_selected_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"44e3cec9ab30944c","mcp_get_code":{"code_sha256":"44e3cec9ab30944c"}},{"arxiv_id":"2311.01149","paper":"/paper/chinesewebtext-large-scale-high-quality","title":"ChineseWebText: Large-scale High-quality Chinese Web Text Extracted with Effective Evaluation Model","date":"2023-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"casia-lm/chinesewebtext","path":"preprocess.py","file_url":"https://github.com/casia-lm/chinesewebtext/blob/HEAD/preprocess.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3501fe87b4ed969d","mcp_get_code":{"code_sha256":"3501fe87b4ed969d"}},{"arxiv_id":"2308.07269","paper":"/paper/easyedit-an-easy-to-use-knowledge-editing","title":"EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/knowlm","path":"pretrain/preprocess.py","file_url":"https://github.com/zjunlp/knowlm/blob/HEAD/pretrain/preprocess.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2797e4223999fe1e","mcp_get_code":{"code_sha256":"2797e4223999fe1e"}},{"arxiv_id":"2304.09919","paper":"/paper/the-ebible-corpus-data-and-model-benchmarks","title":"The eBible Corpus: Data and Model Benchmarks for Bible Translation for Low-Resource Languages","date":"2023-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"biblenlp/ebible-experiments","path":"code/python/summarize_scores_bybook.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/summarize_scores_bybook.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"af1329ad61fa212e","mcp_get_code":{"code_sha256":"af1329ad61fa212e"}},{"arxiv_id":"2302.09210","paper":"/paper/how-good-are-gpt-models-at-machine","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","date":"2023-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/gpt-mt","path":"tools/evaluate.py","file_url":"https://github.com/microsoft/gpt-mt/blob/HEAD/tools/evaluate.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":"ea688ff779c90a0e","mcp_get_code":{"code_sha256":"ea688ff779c90a0e"}},{"arxiv_id":"2207.04672","paper":"/paper/no-language-left-behind-scaling-human-1","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","date":"2022-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ragerri/antidote-projections","path":"cross-lingual-argument-mining/correction/manual_correction/utils.py","file_url":"https://github.com/ragerri/antidote-projections/blob/HEAD/cross-lingual-argument-mining/correction/manual_correction/utils.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":"0605d52f9bcf9662","mcp_get_code":{"code_sha256":"0605d52f9bcf9662"}},{"arxiv_id":"2105.07911","paper":"/paper/sead-end-to-end-text-to-sql-generation-with","title":"SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising","date":"2021-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/WikiSQL","path":"lib/common.py","file_url":"https://github.com/salesforce/WikiSQL/blob/HEAD/lib/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"87b94f47f3de4085","mcp_get_code":{"code_sha256":"87b94f47f3de4085"}},{"arxiv_id":"2010.11125","paper":"/paper/beyond-english-centric-multilingual-machine","title":"Beyond English-Centric Multilingual Machine Translation","date":"2020-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ikergarcia1996/Easy-Translate","path":"dataset.py","file_url":"https://github.com/ikergarcia1996/Easy-Translate/blob/HEAD/dataset.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":"c1e178394d83a447","mcp_get_code":{"code_sha256":"c1e178394d83a447"}},{"arxiv_id":"1910.04744","paper":"/paper/cater-a-diagnostic-dataset-for-compositional","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","date":"2019-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rohitgirdhar/CATER","path":"baselines/video-nonlocal-net/lib/core/config.py","file_url":"https://github.com/rohitgirdhar/CATER/blob/HEAD/baselines/video-nonlocal-net/lib/core/config.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":"cb087309adc9f1cc","mcp_get_code":{"code_sha256":"cb087309adc9f1cc"}},{"arxiv_id":"1908.04003","paper":"/paper/rwr-gae-random-walk-regularization-for-graph","title":"RWR-GAE: Random Walk Regularization for Graph Auto Encoders","date":"2019-08-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MysteryVaibhav/DW-GAE","path":"deepWalk/walks.py","file_url":"https://github.com/MysteryVaibhav/DW-GAE/blob/HEAD/deepWalk/walks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f315b6b9ba82456","mcp_get_code":{"code_sha256":"7f315b6b9ba82456"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"autobotasia/vibert","path":"pre-training-vibert.py","file_url":"https://github.com/autobotasia/vibert/blob/HEAD/pre-training-vibert.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":"30699d853dda45e5","mcp_get_code":{"code_sha256":"30699d853dda45e5"}}]}