{"database": "team-science", "table": "paper", "rows": [["openalex:W3006320872", null, "W3006320872", null, null, null, null, null, "UniViLM: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation.", 2020, "arXiv (Cornell University)", "Computer Science", "https://openalex.org/fields/17", "http://export.arxiv.org/pdf/2002.06353", "2026-09-02T02:37:09Z", "openalex"]], "columns": ["lom_id", "doi", "openalex", "s2_paper_id", "arxiv", "pmid", "pmcid", "acl", "title", "year", "venue", "primary_field", "primary_field_id", "oa_url", "ingested_ts", "source"], "primary_keys": ["lom_id"], "primary_key_values": ["openalex:W3006320872"], "units": {}, "query_ms": 0.6987415254116058, "source": "TeamScience Space repository", "source_url": "https://commons.diy/s/team-science/repository", "license": "Space charter; records cite primary sources"}