{"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/process-text","entry":"process_text","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":21,"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":23,"n_samples_ran":11,"n_samples_fingerprinted":7,"n_places":24,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":9,"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":"2607.21936","paper":"/paper/arxiv-2607-21936","title":"Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"EvelynKimm/ARI","path":"src/data_preprocessing/utils.py","file_url":"https://github.com/EvelynKimm/ARI/blob/HEAD/src/data_preprocessing/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce507b21d8786f36","mcp_get_code":{"code_sha256":"ce507b21d8786f36"}},{"arxiv_id":"2606.20212","paper":"/paper/arxiv-2606-20212","title":"CzechDocs: A Multiway Parallel Dataset of Formatted Documents for Minority Languages in Czechia","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"cepin19/CzechDocs","path":"remove_tags.py","file_url":"https://github.com/cepin19/CzechDocs/blob/HEAD/remove_tags.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"efa71763355ca226","mcp_get_code":{"code_sha256":"efa71763355ca226"}},{"arxiv_id":"2606.00869","paper":"/paper/arxiv-2606-00869","title":"Enhancing LLM Metacognition via Cognitive Pairwise Training","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Tsinghua-dhy/CPT","path":"data_construction/1_rollout/rollout.py","file_url":"https://github.com/Tsinghua-dhy/CPT/blob/HEAD/data_construction/1_rollout/rollout.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":"13430c1445a0990c","mcp_get_code":{"code_sha256":"13430c1445a0990c"}},{"arxiv_id":"2606.00869","paper":"/paper/arxiv-2606-00869","title":"Enhancing LLM Metacognition via Cognitive Pairwise Training","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Tsinghua-dhy/CPT","path":"eval/math/eval_math.py","file_url":"https://github.com/Tsinghua-dhy/CPT/blob/HEAD/eval/math/eval_math.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":"7f580ad4df20e7bd","mcp_get_code":{"code_sha256":"7f580ad4df20e7bd"}},{"arxiv_id":"2606.00869","paper":"/paper/arxiv-2606-00869","title":"Enhancing LLM Metacognition via Cognitive Pairwise Training","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Tsinghua-dhy/CPT","path":"eval/rag/eval_rag_conflicts.py","file_url":"https://github.com/Tsinghua-dhy/CPT/blob/HEAD/eval/rag/eval_rag_conflicts.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":"ba60eead339e8791","mcp_get_code":{"code_sha256":"ba60eead339e8791"}},{"arxiv_id":"2601.12263","paper":"/paper/arxiv-2601-12263","title":"Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"glad-lab/MGEO","path":"process.py","file_url":"https://github.com/glad-lab/MGEO/blob/HEAD/process.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"80e2a549a1ab5ead","mcp_get_code":{"code_sha256":"80e2a549a1ab5ead"}},{"arxiv_id":"2601.04791","paper":"/paper/arxiv-2601-04791","title":"Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"FlowDPS-Inverse/FlowDPS","path":"util.py","file_url":"https://github.com/FlowDPS-Inverse/FlowDPS/blob/HEAD/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ad6a826eba02ae37","mcp_get_code":{"code_sha256":"ad6a826eba02ae37"}},{"arxiv_id":"2506.20803","paper":"/paper/the-ideation-execution-gap-execution-outcomes","title":"The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NoviScl/AI-Researcher","path":"ai_researcher/src/analyze_experiment_plans_semantic_similarity.py","file_url":"https://github.com/NoviScl/AI-Researcher/blob/HEAD/ai_researcher/src/analyze_experiment_plans_semantic_similarity.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2098ab2bf0e96cf0","mcp_get_code":{"code_sha256":"2098ab2bf0e96cf0"}},{"arxiv_id":"2505.17005","paper":"/paper/r1-searcher-incentivizing-the-dynamic","title":"R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RUCAIBox/R1-Searcher","path":"evaluation/eval_search_loacl.py","file_url":"https://github.com/RUCAIBox/R1-Searcher/blob/HEAD/evaluation/eval_search_loacl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"beb27b94356d1280","mcp_get_code":{"code_sha256":"beb27b94356d1280"}},{"arxiv_id":"2410.02131","paper":"/paper/c-melt-contrastive-enhanced-masked-auto","title":"Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"manhph2211/D-BETA","path":"datasets/n3s.py","file_url":"https://github.com/manhph2211/D-BETA/blob/HEAD/datasets/n3s.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"b71f1b7fa9240917","mcp_get_code":{"code_sha256":"b71f1b7fa9240917"}},{"arxiv_id":"2409.04109","paper":"/paper/can-llms-generate-novel-research-ideas-a","title":"Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers","date":"2024-09-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"simplaj/AI-Researcher-Spark","path":"ai_researcher/src/analyze_experiment_plans_semantic_similarity.py","file_url":"https://github.com/simplaj/AI-Researcher-Spark/blob/HEAD/ai_researcher/src/analyze_experiment_plans_semantic_similarity.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2098ab2bf0e96cf0","mcp_get_code":{"code_sha256":"2098ab2bf0e96cf0"}},{"arxiv_id":"2406.12809","paper":"/paper/can-large-language-models-always-solve-easy","title":"Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QwenLM/ConsisEval","path":"code_check/post_process.py","file_url":"https://github.com/QwenLM/ConsisEval/blob/HEAD/code_check/post_process.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dab90bb25f71a531","mcp_get_code":{"code_sha256":"dab90bb25f71a531"}},{"arxiv_id":"2311.09805","paper":"/paper/docmath-eval-evaluating-numerical-reasoning","title":"DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yale-nlp/docmath-eval","path":"retriever/utils/bm25_utils.py","file_url":"https://github.com/yale-nlp/docmath-eval/blob/HEAD/retriever/utils/bm25_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d21b46766ef2f4be","mcp_get_code":{"code_sha256":"d21b46766ef2f4be"}},{"arxiv_id":"2311.06411","paper":"/paper/analyzing-modular-approaches-for-visual","title":"Analyzing Modular Approaches for Visual Question Decomposition","date":"2023-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brown-palm/visual-question-decomposition","path":"src/eval/vqa.py","file_url":"https://github.com/brown-palm/visual-question-decomposition/blob/HEAD/src/eval/vqa.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"776953a4032fa9d7","mcp_get_code":{"code_sha256":"776953a4032fa9d7"}},{"arxiv_id":"2311.03057","paper":"/paper/glen-generative-retrieval-via-lexical-index","title":"GLEN: Generative Retrieval via Lexical Index Learning","date":"2023-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"castorini/docTTTTTquery","path":"convert_msmarco_passage_to_anserini.py","file_url":"https://github.com/castorini/docTTTTTquery/blob/HEAD/convert_msmarco_passage_to_anserini.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4631c7e2bb826903","mcp_get_code":{"code_sha256":"4631c7e2bb826903"}},{"arxiv_id":"2310.05620","paper":"/paper/laiw-a-chinese-legal-large-language-models","title":"LAiW: A Chinese Legal Large Language Models Benchmark","date":"2023-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dai-shen/laiw","path":"src/tasks/utils.py","file_url":"https://github.com/dai-shen/laiw/blob/HEAD/src/tasks/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"efc4c3ac590c9737","mcp_get_code":{"code_sha256":"efc4c3ac590c9737"}},{"arxiv_id":"2310.02977","paper":"/paper/t-3-bench-benchmarking-current-progress-in","title":"T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation","date":"2023-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THU-LYJ-Lab/T3Bench","path":"run_eval_alignment.py","file_url":"https://github.com/THU-LYJ-Lab/T3Bench/blob/HEAD/run_eval_alignment.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"98eabafcf4d5f942","mcp_get_code":{"code_sha256":"98eabafcf4d5f942"}},{"arxiv_id":"2309.14681","paper":"/paper/are-human-generated-demonstrations-necessary","title":"Are Human-generated Demonstrations Necessary for In-context Learning?","date":"2023-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruili33/sec","path":"check.py","file_url":"https://github.com/ruili33/sec/blob/HEAD/check.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0ebffa7d5bab521d","mcp_get_code":{"code_sha256":"0ebffa7d5bab521d"}},{"arxiv_id":"2308.10279","paper":"/paper/gpfl-simultaneously-learning-global-and","title":"GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning","date":"2023-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TsingZ0/PFL-Non-IID","path":"system/flcore/clients/clientgpfl.py","file_url":"https://github.com/TsingZ0/PFL-Non-IID/blob/HEAD/system/flcore/clients/clientgpfl.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":"bff598ba2b65008a","mcp_get_code":{"code_sha256":"bff598ba2b65008a"}},{"arxiv_id":"2106.05707","paper":"/paper/feverous-fact-extraction-and-verification","title":"FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information","date":"2021-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Raldir/FEVEROUS","path":"src/feverous/utils/wiki_element.py","file_url":"https://github.com/Raldir/FEVEROUS/blob/HEAD/src/feverous/utils/wiki_element.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":"52deef4a225ce9bf","mcp_get_code":{"code_sha256":"52deef4a225ce9bf"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cypressd1999/FYP_2021","path":"src/tasks/preprocessing_funcs.py","file_url":"https://github.com/cypressd1999/FYP_2021/blob/HEAD/src/tasks/preprocessing_funcs.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":"7b81e295d0e6fff5","mcp_get_code":{"code_sha256":"7b81e295d0e6fff5"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jpablou/Matching-The-Blanks-Ths","path":"src/tasks/preprocessing_funcs.py","file_url":"https://github.com/jpablou/Matching-The-Blanks-Ths/blob/HEAD/src/tasks/preprocessing_funcs.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":"6bf6a61197367217","mcp_get_code":{"code_sha256":"6bf6a61197367217"}},{"arxiv_id":"1605.05396","paper":"/paper/generative-adversarial-text-to-image","title":"Generative Adversarial Text to Image Synthesis","date":"2016-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Abhis-123/TextToImage","path":"datasets.py","file_url":"https://github.com/Abhis-123/TextToImage/blob/HEAD/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ca07d7ef0a1b5440","mcp_get_code":{"code_sha256":"ca07d7ef0a1b5440"}},{"arxiv_id":"2023.findings-emnlp.896","paper":null,"title":"arXiv:2023.findings-emnlp.896","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"KarelDO/BioDEX","path":"tasks/icsr_extraction/run_gpt3_for_icsr_extraction.py","file_url":"https://github.com/KarelDO/BioDEX/blob/HEAD/tasks/icsr_extraction/run_gpt3_for_icsr_extraction.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"86738d726006a0b7","mcp_get_code":{"code_sha256":"86738d726006a0b7"}}]}