{"url":"/sota/molecule-captioning-on-chebi-20","task":{"name":"Molecule Captioning","url":"/task/molecule-captioning","note":null},"dataset":{"name":"ChEBI-20","url":"/dataset/chebi-20"},"category":"Medical","categories":["Medical"],"category_note":null,"description":"Molecular description generation entails the creation of a detailed textual depiction illuminating the structure, properties, biological activity, and applications of a molecule based on its molecular descriptors. It furnishes chemists and biologists with a swift conduit to essential molecular information, thus efficiently guiding their research and experiments.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["BLEU-2","BLEU-4","METEOR","ROUGE-1","ROUGE-2","ROUGE-L","Text2Mol"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"BLEU-2":"higher","BLEU-4":"higher","METEOR":null,"ROUGE-1":"higher","ROUGE-2":"higher","ROUGE-L":"higher","Text2Mol":null}},"counts":{"rows":33,"rows_with_code":28,"rows_with_paper_page":31,"rows_dated":31,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Mol-LLM (Mistral-Instruct-v0.2)","metrics":{"BLEU-2":"73.2"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Mol-LLM (LLaMA2-Chat)","metrics":{"BLEU-2":"72.70"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"MolReFlect","metrics":{"BLEU-2":"67.6","BLEU-4":"60.8","METEOR":"68.0","ROUGE-1":"70.3","ROUGE-2":"57.1","ROUGE-L":"64.4"},"uses_additional_data":false,"paper_date":"2024-11-22","paper":"/paper/molreflect-towards-fine-grained-in-context","paper_url":"https://arxiv.org/html/2411.14721v1","paper_title":"MolReFlect: Towards Fine-grained In-Context Alignment between Molecules and Texts","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"BioT5+","metrics":{"BLEU-2":"66.6","BLEU-4":"59.1","METEOR":"68.1","ROUGE-1":"71.0","ROUGE-2":"58.4","ROUGE-L":"65.0"},"uses_additional_data":false,"paper_date":"2024-02-27","paper":"/paper/biot5-towards-generalized-biological","paper_url":"https://arxiv.org/abs/2402.17810v2","paper_title":"BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning","code":"https://github.com/QizhiPei/BioT5","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"BioT5","metrics":{"BLEU-2":"63.5","BLEU-4":"55.6","METEOR":"65.6","ROUGE-1":"69.2","ROUGE-2":"55.9","ROUGE-L":"63.3","Text2Mol":"60.3"},"uses_additional_data":false,"paper_date":"2023-10-11","paper":"/paper/biot5-enriching-cross-modal-integration-in","paper_url":"https://arxiv.org/abs/2310.07276v3","paper_title":"BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations","code":"https://github.com/QizhiPei/BioT5","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"Text+Chem T5-augm-Base","metrics":{"BLEU-2":"62.5","BLEU-4":"54.2","METEOR":"64.8","ROUGE-1":"68.2","ROUGE-2":"54.3","ROUGE-L":"62.2"},"uses_additional_data":false,"paper_date":"2023-01-29","paper":"/paper/unifying-molecular-and-textual","paper_url":"https://arxiv.org/abs/2301.12586v2","paper_title":"Unifying Molecular and Textual Representations via Multi-task Language Modelling","code":"https://github.com/gt4sd/multitask_text_and_chemistry_t5","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"XMolCap","metrics":{"BLEU-2":"62.0","BLEU-4":"53.8","METEOR":"67.8","ROUGE-1":"53.9","ROUGE-2":"61.8","ROUGE-L":"63.8"},"uses_additional_data":false,"paper_date":"2025-05-23","paper":"/paper/xmolcap-advancing-molecular-captioning","paper_url":"https://ieeexplore.ieee.org/document/11012653","paper_title":"XMolCap: Advancing Molecular Captioning through Multimodal Fusion and Explainable Graph Neural Networks","code":"https://github.com/cbbl-skku-org/XMolCap","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"MolCA, Galac1.3B","metrics":{"BLEU-2":"62.0","BLEU-4":"53.1","METEOR":"65.1","ROUGE-1":"68.1","ROUGE-2":"53.7","ROUGE-L":"61.8"},"uses_additional_data":false,"paper_date":"2023-10-19","paper":"/paper/molca-molecular-graph-language-modeling-with","paper_url":"https://arxiv.org/abs/2310.12798v4","paper_title":"MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter","code":"https://github.com/acharkq/molca","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":8,"n_samples":16,"n_pointer_only_licence":16}},{"rank_in_archive_order":9,"model":"MolCA, Galac125M","metrics":{"BLEU-2":"61.6","BLEU-4":"52.9","METEOR":"63.9","ROUGE-1":"67.4","ROUGE-2":"53.3","ROUGE-L":"61.5"},"uses_additional_data":false,"paper_date":"2023-10-19","paper":"/paper/molca-molecular-graph-language-modeling-with","paper_url":"https://arxiv.org/abs/2310.12798v4","paper_title":"MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter","code":"https://github.com/acharkq/molca","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":8,"n_samples":16,"n_pointer_only_licence":16}},{"rank_in_archive_order":10,"model":"Mol2Lang-VLM","metrics":{"BLEU-2":"61.2","BLEU-4":"52.7","METEOR":"63.3","ROUGE-1":"67.4","ROUGE-2":"53.2","ROUGE-L":"61.4","Text2Mol":"59.8"},"uses_additional_data":false,"paper_date":"2024-08-15","paper":"/paper/mol2lang-vlm-vision-and-text-guided","paper_url":"https://aclanthology.org/2024.langmol-1.12/","paper_title":"Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion","code":"https://github.com/nhattruongpham/mol-lang-bridge","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"MolReGPT (GPT-4-0314)","metrics":{"BLEU-2":"60.7","BLEU-4":"52.5","METEOR":"61.0","ROUGE-1":"63.4","ROUGE-2":"47.6","ROUGE-L":"56.2","Text2Mol":"58.5"},"uses_additional_data":false,"paper_date":"2023-06-11","paper":"/paper/empowering-molecule-discovery-for-molecule","paper_url":"https://arxiv.org/abs/2306.06615v2","paper_title":"Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective","code":"https://github.com/phenixace/molregpt","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"LaMolT5-Large","metrics":{"BLEU-2":"60.2","BLEU-4":"52.1","METEOR":"63.4","ROUGE-1":"65.5","ROUGE-2":"51.2","ROUGE-L":"59.8","Text2Mol":"59.7"},"uses_additional_data":false,"paper_date":"2025-02-10","paper":"/paper/automatic-annotation-augmentation-boosts","paper_url":"https://arxiv.org/abs/2502.06634v1","paper_title":"Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language","code":"https://github.com/zhiqiangzhongddu/la3","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"MoMu+MolT5-Large","metrics":{"BLEU-2":"59.9","BLEU-4":"51.5","METEOR":"59.7","Text2Mol":"58.2"},"uses_additional_data":false,"paper_date":"2022-09-12","paper":"/paper/a-molecular-multimodal-foundation-model","paper_url":"https://arxiv.org/abs/2209.05481v1","paper_title":"A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language","code":"https://github.com/ai-hpc-research-team/git-mol","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":2}},{"rank_in_archive_order":14,"model":"PEIT-GEN","metrics":{"BLEU-2":"59.8","BLEU-4":"53.4","METEOR":"67.6","ROUGE-1":"70.0","ROUGE-2":"58.2","ROUGE-L":"65.3"},"uses_additional_data":false,"paper_date":"2024-12-24","paper":"/paper/property-enhanced-instruction-tuning-for","paper_url":"https://arxiv.org/abs/2412.18084v4","paper_title":"Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models","code":"https://github.com/chenlong164/peit","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"MolT5-Large","metrics":{"BLEU-2":"59.4","BLEU-4":"50.8","METEOR":"61.4","ROUGE-1":"65.4","ROUGE-2":"51.0","ROUGE-L":"59.4","Text2Mol":"58.2"},"uses_additional_data":false,"paper_date":"2022-04-25","paper":"/paper/translation-between-molecules-and-natural","paper_url":"https://arxiv.org/abs/2204.11817v3","paper_title":"Translation between Molecules and Natural Language","code":"https://github.com/blender-nlp/MolT5","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"MolXPT","metrics":{"BLEU-2":"59.4","BLEU-4":"50.5","METEOR":"62.6","ROUGE-1":"66","ROUGE-2":"51.1","ROUGE-L":"59.7","Text2Mol":"59.4"},"uses_additional_data":false,"paper_date":"2023-05-18","paper":"/paper/molxpt-wrapping-molecules-with-text-for","paper_url":"https://arxiv.org/abs/2305.10688v2","paper_title":"MolXPT: Wrapping Molecules with Text for Generative Pre-training","code":"https://huggingface.co/zequnl/molxpt","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"Mol-LLM (SELFIES)","metrics":{"BLEU-2":"58.7","BLEU-4":"51.5","METEOR":"61.7","ROUGE-1":"62.7","ROUGE-2":"48.7","ROUGE-L":"57.1"},"uses_additional_data":false,"paper_date":"2025-02-05","paper":"/paper/mol-llm-generalist-molecular-llm-with","paper_url":"https://arxiv.org/abs/2502.02810v2","paper_title":"Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"MolFM-Base","metrics":{"BLEU-2":"58.5","BLEU-4":"49.8","METEOR":"60.7","ROUGE-1":"65.3","ROUGE-2":"50.8","ROUGE-L":"59.4","Text2Mol":"57.6"},"uses_additional_data":false,"paper_date":"2023-06-06","paper":"/paper/molfm-a-multimodal-molecular-foundation-model","paper_url":"https://arxiv.org/abs/2307.09484v2","paper_title":"MolFM: A Multimodal Molecular Foundation Model","code":"https://github.com/biofm/openbiomed","n_code_links":2,"syntology":null},{"rank_in_archive_order":19,"model":"Text+Chem T5-Base","metrics":{"BLEU-2":"58","BLEU-4":"49","METEOR":"60.4","ROUGE-1":"64.7","ROUGE-2":"49.8","ROUGE-L":"58.6"},"uses_additional_data":false,"paper_date":"2023-01-29","paper":"/paper/unifying-molecular-and-textual","paper_url":"https://arxiv.org/abs/2301.12586v2","paper_title":"Unifying Molecular and Textual Representations via Multi-task Language Modelling","code":"https://github.com/gt4sd/multitask_text_and_chemistry_t5","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"LaMolT5-Base","metrics":{"BLEU-2":"57.4","BLEU-4":"48.5","METEOR":"59.6","ROUGE-1":"63.4","ROUGE-2":"47.8","ROUGE-L":"56.4","Text2Mol":"59.9"},"uses_additional_data":false,"paper_date":"2025-02-10","paper":"/paper/automatic-annotation-augmentation-boosts","paper_url":"https://arxiv.org/abs/2502.06634v1","paper_title":"Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language","code":"https://github.com/zhiqiangzhongddu/la3","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"MolReGPT (GPT-3.5-turbo)","metrics":{"BLEU-2":"56.5","BLEU-4":"48.2","METEOR":"62.3","ROUGE-1":"45.0","ROUGE-2":"54.3","ROUGE-L":"58.5","Text2Mol":"56.0"},"uses_additional_data":false,"paper_date":"2023-06-11","paper":"/paper/empowering-molecule-discovery-for-molecule","paper_url":"https://arxiv.org/abs/2306.06615v2","paper_title":"Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective","code":"https://github.com/phenixace/molregpt","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"Mol-LLM","metrics":{"BLEU-2":"56.0","BLEU-4":"49.0","METEOR":"59.3","ROUGE-1":"52.4","ROUGE-2":"37.0","ROUGE-L":"46.7"},"uses_additional_data":false,"paper_date":"2025-02-05","paper":"/paper/mol-llm-generalist-molecular-llm-with","paper_url":"https://arxiv.org/abs/2502.02810v2","paper_title":"Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"Text+Chem T5-augm-Small","metrics":{"BLEU-2":"56.0","BLEU-4":"47.0","METEOR":"58.8","ROUGE-1":"63.8","ROUGE-2":"48.8","ROUGE-L":"58"},"uses_additional_data":false,"paper_date":"2023-01-29","paper":"/paper/unifying-molecular-and-textual","paper_url":"https://arxiv.org/abs/2301.12586v2","paper_title":"Unifying Molecular and Textual Representations via Multi-task Language Modelling","code":"https://github.com/gt4sd/multitask_text_and_chemistry_t5","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"Text+Chem T5-Small","metrics":{"BLEU-2":"55.3","BLEU-4":"46.2","METEOR":"58.3","ROUGE-1":"63.3","ROUGE-2":"48.1","ROUGE-L":"57.4"},"uses_additional_data":false,"paper_date":"2023-01-29","paper":"/paper/unifying-molecular-and-textual","paper_url":"https://arxiv.org/abs/2301.12586v2","paper_title":"Unifying Molecular and Textual Representations via Multi-task Language Modelling","code":"https://github.com/gt4sd/multitask_text_and_chemistry_t5","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"MoMu+MolT5-Base","metrics":{"BLEU-2":"54.9","BLEU-4":"46.2","METEOR":"57.6","Text2Mol":"55.8"},"uses_additional_data":false,"paper_date":"2022-09-12","paper":"/paper/a-molecular-multimodal-foundation-model","paper_url":"https://arxiv.org/abs/2209.05481v1","paper_title":"A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language","code":"https://github.com/ai-hpc-research-team/git-mol","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":2}},{"rank_in_archive_order":26,"model":"MolFM-Small","metrics":{"BLEU-2":"54.2","BLEU-4":"45.2","METEOR":"56.4","ROUGE-1":"62.3","ROUGE-2":"46.9","ROUGE-L":"56.2","Text2Mol":"55.7"},"uses_additional_data":false,"paper_date":"2023-06-06","paper":"/paper/molfm-a-multimodal-molecular-foundation-model","paper_url":"https://arxiv.org/abs/2307.09484v2","paper_title":"MolFM: A Multimodal Molecular Foundation Model","code":"https://github.com/biofm/openbiomed","n_code_links":2,"syntology":null},{"rank_in_archive_order":27,"model":"GAMIC (Mistral)","metrics":{"BLEU-2":"54.2","BLEU-4":"43.9","METEOR":"58.5","ROUGE-1":"61.7","ROUGE-2":"46.6","ROUGE-L":"56.1"},"uses_additional_data":false,"paper_date":"2022-07-08","paper":"/paper/graph-based-molecular-representation-learning","paper_url":"https://arxiv.org/abs/2207.04869v3","paper_title":"Graph-based Molecular Representation Learning","code":"https://github.com/zaixizhang/MGSSL","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"MolT5-Base","metrics":{"BLEU-2":"54.0","BLEU-4":"45.7","METEOR":"56.9","ROUGE-1":"63.4","ROUGE-2":"48.5","ROUGE-L":"57.8","Text2Mol":"54.7"},"uses_additional_data":false,"paper_date":"2022-04-25","paper":"/paper/translation-between-molecules-and-natural","paper_url":"https://arxiv.org/abs/2204.11817v3","paper_title":"Translation between Molecules and Natural Language","code":"https://github.com/blender-nlp/MolT5","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"LaMolT5-Small","metrics":{"BLEU-2":"53.9","BLEU-4":"44.6","METEOR":"56.6","ROUGE-1":"62.0","ROUGE-2":"46.9","ROUGE-L":"56.3","Text2Mol":"58.8"},"uses_additional_data":false,"paper_date":"2025-02-10","paper":"/paper/automatic-annotation-augmentation-boosts","paper_url":"https://arxiv.org/abs/2502.06634v1","paper_title":"Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language","code":"https://github.com/zhiqiangzhongddu/la3","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"MoMu+MolT5-Small","metrics":{"BLEU-2":"53.2","BLEU-4":"44.5","METEOR":"55.7","Text2Mol":"55.3"},"uses_additional_data":false,"paper_date":"2022-09-12","paper":"/paper/a-molecular-multimodal-foundation-model","paper_url":"https://arxiv.org/abs/2209.05481v1","paper_title":"A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language","code":"https://github.com/ai-hpc-research-team/git-mol","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":2}},{"rank_in_archive_order":31,"model":"MolT5-Small","metrics":{"BLEU-2":"51.9","BLEU-4":"43.6","METEOR":"55.1","ROUGE-1":"62.0","ROUGE-2":"46.9","ROUGE-L":"56.3","Text2Mol":"54.0"},"uses_additional_data":false,"paper_date":"2022-04-25","paper":"/paper/translation-between-molecules-and-natural","paper_url":"https://arxiv.org/abs/2204.11817v3","paper_title":"Translation between Molecules and Natural Language","code":"https://github.com/blender-nlp/MolT5","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"InstructMol-GS","metrics":{"BLEU-2":"47.5","BLEU-4":"37.1","METEOR":"50.9","ROUGE-1":"56.6","ROUGE-2":"39.4","ROUGE-L":"50.2"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/instructmol-multi-modal-integration-for","paper_url":"https://arxiv.org/abs/2311.16208v2","paper_title":"InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery","code":"https://github.com/idea-xl/instructmol","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"InstructMol-G","metrics":{"BLEU-2":"46.6","BLEU-4":"36.5","METEOR":"49.1","ROUGE-1":"54.7","ROUGE-2":"36.5","ROUGE-L":"47.9"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/instructmol-multi-modal-integration-for","paper_url":"https://arxiv.org/abs/2311.16208v2","paper_title":"InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery","code":"https://github.com/idea-xl/instructmol","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":11,"rows_with_any_sample_ran":11,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":22,"n_unverified":11,"n_samples":33,"n_pointer_only_licence":18,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":53,"n_unverified":25,"n_samples":78,"n_pointer_only_licence":38,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}