{"url":"/dataset/molparser-7m","name":"MolParser-7M","full_name":null,"description_markdown":"A large scale OCSR dataset, proposed in paper “MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild“\r\nMolParser-7M contains nearly 8 million paired image-SMILES data. It should be noted that the caption of image is extended-SMILES format proposed in paper.","description_withheld":null,"homepage":"https://huggingface.co/datasets/AI4Industry/MolParser-7M","introduced_date":"2024-11-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/molparser-end-to-end-visual-recognition-of","title":"MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild","first_author":"Xi Fang","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"}],"languages":[],"variants":["MolParser-7M"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}