{"data":{"slug":"tiered-extraction","term":"Tiered Extraction","bucket":"data","definition":"Three quality tiers of paper extraction: light (title + abstract), standard (sections + figures), exhaustive (full text + tables).","short_definition":"Three quality tiers of paper extraction: light (title + abstract), standard (sections + figures), exhaustive (full text + tables).","long_definition":"Tiered Extraction picks how deeply a paper is parsed. Light gets the title, abstract, and metadata; standard adds sections, figures, and claims; exhaustive does full text, tables, and formulas. The tier a paper lands in drives the quality of its score, its claims, and its evidence pack.","related_terms":["corpus-engine","paper-pack"],"related_term_routes":[{"slug":"corpus-engine","term":"Corpus Engine","route":"/resources/glossary/corpus-engine"},{"slug":"paper-pack","term":"Paper Pack","route":"/resources/glossary/paper-pack"}],"canonical_route":"/resources/glossary/tiered-extraction","api_route":"/api/v1/resources/glossary/tiered-extraction","jsonld_id":"https://sciencetostartup.com/resources/glossary/tiered-extraction","variants":[],"tldr":"Three quality tiers of paper extraction: light (title + abstract), standard (sections + figures), exhaustive (full text + tables).","key_points":[],"quality_tier":null,"citation_count":null,"source_state":"curated_static","source_module":"apps/web/data/glossary/terms.ts","definition_sections":{"schema_version":1,"intro":"Tiered Extraction picks how deeply a paper is parsed. Light gets the title, abstract, and metadata; standard adds sections, figures, and claims; exhaustive does full text, tables, and formulas. The tier a paper lands in drives the quality of its score, its claims, and its evidence pack.","sections":[{"title":"Definition","items":[{"subtitle":"Tiered Extraction","text":"Tiered Extraction picks how deeply a paper is parsed. Light gets the title, abstract, and metadata; standard adds sections, figures, and claims; exhaustive does full text, tables, and formulas. The tier a paper lands in drives the quality of its score, its claims, and its evidence pack."}]},{"title":"Related vocabulary","items":[{"subtitle":"Corpus Engine","text":"The full ingestion-enrichment-publish pipeline. Daily Modal jobs at 20:05, 20:30, 21:00 UTC."},{"subtitle":"Paper Pack","text":"The compact citation-grade envelope for one paper. Title, abstract, score, flags, one-liner, time-to-MVP. Sized for agent context (under 6144 bytes)."}]}],"cited_arxiv_ids":[]}},"meta":{"canonical_route":"/resources/glossary/tiered-extraction","api_route":"/api/v1/resources/glossary/tiered-extraction","source":{"label":"curated glossary catalog","source_state":"curated_static","source_module":"apps/web/data/glossary/terms.ts","method_version":"public_glossary_curated_terms_v2","freshness":{"status":"versioned","observed_at":null,"fresh_until":null,"reason":"Git-versioned curated catalog; daily ingestion freshness windows do not apply.","reason_code":"git_versioned_curated_catalog"},"source_count":111,"bucket_count":7,"buckets":["scoring","surfaces","agents","distribution","data","foresight","buildability"]}}}