{"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/group-texts","entry":"group_texts","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":14,"n_papers_ran":9,"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":15,"n_samples_ran":10,"n_samples_fingerprinted":0,"n_places":15,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":9,"unverified":5},"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":"2601.19383","paper":"/paper/arxiv-2601-19383","title":"High-quality data augmentation for code comment classification","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"ThomBors/NLBSE2026","path":"src/utils.py","file_url":"https://github.com/ThomBors/NLBSE2026/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12e2ffa4e0472b06","mcp_get_code":{"code_sha256":"12e2ffa4e0472b06"}},{"arxiv_id":"2410.17600","paper":"/paper/graphusion-a-rag-framework-for-knowledge","title":"Graphusion: A RAG Framework for Knowledge Graph Construction with a Global Perspective","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"irenezihuili/graphusion","path":"med_bert.py","file_url":"https://github.com/irenezihuili/graphusion/blob/HEAD/med_bert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9df4eb6beaf8b924","mcp_get_code":{"code_sha256":"9df4eb6beaf8b924"}},{"arxiv_id":"2409.17990","paper":"/paper/extracting-affect-aggregates-from","title":"Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dess-mannheim/temporal-adapters","path":"train_llama3_empiricalData.py","file_url":"https://github.com/dess-mannheim/temporal-adapters/blob/HEAD/train_llama3_empiricalData.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a29da27a2682e076","mcp_get_code":{"code_sha256":"a29da27a2682e076"}},{"arxiv_id":"2409.17990","paper":"/paper/extracting-affect-aggregates-from","title":"Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dess-mannheim/temporal-adapters","path":"train_llama3_syntheticMix.py","file_url":"https://github.com/dess-mannheim/temporal-adapters/blob/HEAD/train_llama3_syntheticMix.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf2f95f177d552d9","mcp_get_code":{"code_sha256":"cf2f95f177d552d9"}},{"arxiv_id":"2409.01193","paper":"/paper/clibe-detecting-dynamic-backdoors-in","title":"CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models","date":"2024-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raytsang123/clibe","path":"discriminative_backdoors/detection/corpus.py","file_url":"https://github.com/raytsang123/clibe/blob/HEAD/discriminative_backdoors/detection/corpus.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":"af845e67b66255e7","mcp_get_code":{"code_sha256":"af845e67b66255e7"}},{"arxiv_id":"2408.16967","paper":"/paper/memlong-memory-augmented-retrieval-for-long","title":"MemLong: Memory-Augmented Retrieval for Long Text Modeling","date":"2024-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bui1dmysea/memlong","path":"eval/language_modeling/MemLong/utils.py","file_url":"https://github.com/bui1dmysea/memlong/blob/HEAD/eval/language_modeling/MemLong/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"65bc466999b923d6","mcp_get_code":{"code_sha256":"65bc466999b923d6"}},{"arxiv_id":"2407.05841","paper":"/paper/an-empirical-comparison-of-vocabulary","title":"An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models","date":"2024-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AI4Bharat/VocabAdaptation_LLM","path":"IndicMPT_inference.py","file_url":"https://github.com/AI4Bharat/VocabAdaptation_LLM/blob/HEAD/IndicMPT_inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9ec8e7e78f79e925","mcp_get_code":{"code_sha256":"9ec8e7e78f79e925"}},{"arxiv_id":"2406.11477","paper":"/paper/vocabulary-expansion-for-low-resource-cross","title":"How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gucci-j/lowres-cva","path":"preprocessing/src/main_lapt.py","file_url":"https://github.com/gucci-j/lowres-cva/blob/HEAD/preprocessing/src/main_lapt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0643ee8d0cd584bc","mcp_get_code":{"code_sha256":"0643ee8d0cd584bc"}},{"arxiv_id":"2405.16325","paper":"/paper/slope-double-pruned-sparse-plus-lazy-low-rank","title":"SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs","date":"2024-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Mohammad-Mozaffari/slope","path":"inference.py","file_url":"https://github.com/Mohammad-Mozaffari/slope/blob/HEAD/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c144743f962ecd0b","mcp_get_code":{"code_sha256":"c144743f962ecd0b"}},{"arxiv_id":"2405.14394","paper":"/paper/instruction-tuning-with-loss-over","title":"Instruction Tuning With Loss Over Instructions","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhengxiangShi/InstructionModelling","path":"src/compute_loss.py","file_url":"https://github.com/ZhengxiangShi/InstructionModelling/blob/HEAD/src/compute_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d09e0781a55d3694","mcp_get_code":{"code_sha256":"d09e0781a55d3694"}},{"arxiv_id":"2404.02204","paper":"/paper/emergent-abilities-in-reduced-scale","title":"Emergent Abilities in Reduced-Scale Generative Language Models","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"text-machine-lab/mini_gpt","path":"src/data_collation.py","file_url":"https://github.com/text-machine-lab/mini_gpt/blob/HEAD/src/data_collation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1e973bfb2c3ff69e","mcp_get_code":{"code_sha256":"1e973bfb2c3ff69e"}},{"arxiv_id":"2402.10712","paper":"/paper/an-empirical-study-on-cross-lingual","title":"An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gucci-j/llm-cva","path":"preprocessing/src/preprocess.py","file_url":"https://github.com/gucci-j/llm-cva/blob/HEAD/preprocessing/src/preprocess.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d2183c85747240d9","mcp_get_code":{"code_sha256":"d2183c85747240d9"}},{"arxiv_id":"2305.14342","paper":"/paper/sophia-a-scalable-stochastic-second-order","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kyegomez/Sophia","path":"experiments/training.py","file_url":"https://github.com/kyegomez/Sophia/blob/HEAD/experiments/training.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2382cb6829841947","mcp_get_code":{"code_sha256":"2382cb6829841947"}},{"arxiv_id":"2305.09955","paper":"/paper/cook-empowering-general-purpose-language","title":"Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models","date":"2023-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BunsenFeng/Knowledge_Card","path":"card_training.py","file_url":"https://github.com/BunsenFeng/Knowledge_Card/blob/HEAD/card_training.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c6d0a4b8c23ebfe9","mcp_get_code":{"code_sha256":"c6d0a4b8c23ebfe9"}},{"arxiv_id":"2024.findings-naacl.117","paper":null,"title":"arXiv:2024.findings-naacl.117","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"qqplot/dcpmi","path":"utils/utils.py","file_url":"https://github.com/qqplot/dcpmi/blob/HEAD/utils/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a15a1001b7f79b38","mcp_get_code":{"code_sha256":"a15a1001b7f79b38"}}]}