{"analysis_contract_sha256":"8f01b3cdcec44c1fff7cbed239a99be37abdaabe0132d697c2756056ca41a5dd","analysis_id":"analysis.source-list-overlap-v1","calculations":[{"calculation_id":"research.count-v1","confidence":"deterministic","description":"Count retained records in a declared group.","formula":"count(records)","limitations":[],"source_fields":["normalized_spelling","source_ids"]},{"calculation_id":"research.share-v1","confidence":"deterministic","description":"Calculate a group's exact share of its declared denominator.","formula":"100 * numerator / denominator","limitations":["A share describes only this release and declared population."],"source_fields":["normalized_spelling","source_ids"]}],"charts":[{"accessible_summary":"A bar chart of the same exact counts available in the adjacent source combination table.","category_column_id":"membership_combination","chart_id":"study.source-list-overlap.combination-chart","chart_type":"bar","dataset_id":"study.source-list-overlap.combinations","heading":"Records by exact source combination","series":[{"label":"Records","value_column_id":"record_count"}],"table_id":"study.source-list-overlap.combination-table"}],"citations":[{"citation_id":"citation.dwyl","citation_kind":"dataset","data_version":null,"publisher":"dwyl","source_id":"dwyl-english-words","title":"English Words (words_alpha.txt)","url":"https://raw.githubusercontent.com/dwyl/english-words/8179fe68775df3f553ef19520db065228e65d1d3/words_alpha.txt","version":"git:8179fe68775df3f553ef19520db065228e65d1d3"},{"citation_id":"citation.enable","citation_kind":"dataset","data_version":null,"publisher":"ENABLE project","source_id":"enable","title":"ENABLE Wordlist","url":"https://www.wordgamedictionary.com/enable/download/enable.txt","version":"artifact-sha256:d3fbe8485022088fcf527edcde2fbdc18b4bbc141ac58123c9adb462e086eaf7"},{"citation_id":"citation.google-10000","citation_kind":"dataset","data_version":null,"publisher":"first20hours","source_id":"google-10000-english","title":"10000 Common Words","url":"https://raw.githubusercontent.com/first20hours/google-10000-english/bdf4c221bc120b0b7f6c3f1eff1cc1abb975f8d8/google-10000-english-usa-no-swears.txt","version":"git:bdf4c221bc120b0b7f6c3f1eff1cc1abb975f8d8"},{"citation_id":"citation.content-policy","citation_kind":"policy","data_version":null,"publisher":"The Word Index","source_id":"offensive-term-policy","title":"The Word Index content-safety exclusion policy","url":"/about/data","version":"2026.07-review-pending.2"}],"concise_result":"61.97% of the safe normalized-spelling records occur in exactly one of the three pinned spelling artifacts.","content_artifact_digest":"f62627b5bcc9577d4aa077bb66ad5832d6c83064d0aa896f532d5a3ec2ca2009","data_version":"2026.07-lexical.3","datasets":[{"columns":[{"calculation_id":null,"column_id":"row_id","label":"Row ID","role":"dimension","unit":null,"value_type":"text"},{"calculation_id":null,"column_id":"stage","label":"Population stage","role":"dimension","unit":null,"value_type":"text"},{"calculation_id":"research.count-v1","column_id":"record_count","label":"Records","role":"measure","unit":"records","value_type":"integer"}],"dataset_id":"study.source-list-overlap.population","description":"Exact record counts before and after the declared product-policy and study filters.","primary_download":false,"rows":[{"record_count":394595,"row_id":"raw","stage":"Raw lexical ledger"},{"record_count":150,"row_id":"policy-excluded","stage":"Excluded by product policy"},{"record_count":394445,"row_id":"safe","stage":"Safe normalized-spelling records"},{"record_count":394445,"row_id":"analysis","stage":"Records meeting this study's inclusion criteria"}],"title":"Study population"},{"columns":[{"calculation_id":null,"column_id":"row_id","label":"Row ID","role":"dimension","unit":null,"value_type":"text"},{"calculation_id":null,"column_id":"metric","label":"Metric","role":"dimension","unit":null,"value_type":"text"},{"calculation_id":"research.count-v1","column_id":"record_count","label":"Records","role":"measure","unit":"records","value_type":"integer"},{"calculation_id":"research.share-v1","column_id":"share_percent","label":"Share","role":"measure","unit":"percent","value_type":"decimal-string"}],"dataset_id":"study.source-list-overlap.summary","description":"Headline counts derived from the exact membership combinations.","primary_download":false,"rows":[{"metric":"Membership in exactly one spelling artifact","record_count":244455,"row_id":"exactly-one","share_percent":"61.97"},{"metric":"Membership in at least two spelling artifacts","record_count":149990,"row_id":"at-least-two","share_percent":"38.03"},{"metric":"Membership in all three spelling artifacts","record_count":8090,"row_id":"all-three","share_percent":"2.05"}],"title":"Source-overlap summary"},{"columns":[{"calculation_id":null,"column_id":"row_id","label":"Row ID","role":"dimension","unit":null,"value_type":"text"},{"calculation_id":null,"column_id":"membership_combination","label":"Exact source combination","role":"dimension","unit":null,"value_type":"text"},{"calculation_id":null,"column_id":"source_count","label":"Number of sources","role":"dimension","unit":null,"value_type":"integer"},{"calculation_id":"research.count-v1","column_id":"record_count","label":"Records","role":"measure","unit":"records","value_type":"integer"},{"calculation_id":"research.share-v1","column_id":"share_percent","label":"Share of analysis population","role":"measure","unit":"percent","value_type":"decimal-string"}],"dataset_id":"study.source-list-overlap.combinations","description":"Aggregate normalized-spelling counts for every non-empty combination of the three pinned orthographic artifacts.","primary_download":true,"rows":[{"membership_combination":"dwyl-english-words","record_count":219992,"row_id":"dwyl","share_percent":"55.77","source_count":1},{"membership_combination":"enable","record_count":23852,"row_id":"enable","share_percent":"6.05","source_count":1},{"membership_combination":"google-10000-english","record_count":611,"row_id":"google-10000-english","share_percent":"0.15","source_count":1},{"membership_combination":"dwyl-english-words + enable","record_count":140717,"row_id":"dwyl-and-enable","share_percent":"35.67","source_count":2},{"membership_combination":"dwyl-english-words + google-10000-english","record_count":1164,"row_id":"dwyl-and-google-10000-english","share_percent":"0.30","source_count":2},{"membership_combination":"enable + google-10000-english","record_count":19,"row_id":"enable-and-google-10000-english","share_percent":"0.00","source_count":2},{"membership_combination":"dwyl-english-words + enable + google-10000-english","record_count":8090,"row_id":"dwyl-and-enable-and-google-10000-english","share_percent":"2.05","source_count":3}],"title":"Exact spelling-list membership combinations"}],"description":"A reproducible comparison of exact normalized-spelling membership in three pinned source artifacts.","downloads":[{"contains":["study.source-list-overlap.population","study.source-list-overlap.summary","study.source-list-overlap.combinations"],"filename":"source-list-overlap.csv","media_type":"text/csv","sha256":"db38a161acedf4b62646a4703e7e44272db7f5a8baa43b90569a1020dd0c87d7","size_bytes":17540,"status":"available-review-pending"}],"exclusions":[{"criterion_id":"source-overlap.product-policy","description":"Exclude spellings matched by the exact first-party content-safety policy before aggregation."}],"facts":[{"calculation_id":"research.count-v1","column_id":"record_count","dataset_id":"study.source-list-overlap.population","denominator":null,"display_value":"394,445","fact_id":"study.source-list-overlap.analysis-record-count","label":"Analysis population","numerator":null,"row_id":"analysis","unit":"records","value":394445},{"calculation_id":"research.share-v1","column_id":"share_percent","dataset_id":"study.source-list-overlap.summary","denominator":394445,"display_value":"61.97%","fact_id":"study.source-list-overlap.exactly-one-share","label":"Records found in exactly one spelling artifact","numerator":244455,"row_id":"exactly-one","unit":"percent","value":"61.97"},{"calculation_id":"research.share-v1","column_id":"share_percent","dataset_id":"study.source-list-overlap.summary","denominator":394445,"display_value":"38.03%","fact_id":"study.source-list-overlap.at-least-two-share","label":"Records found in at least two spelling artifacts","numerator":149990,"row_id":"at-least-two","unit":"percent","value":"38.03"}],"inclusion_criteria":[{"criterion_id":"source-overlap.normalized-ascii","description":"Include normalized ASCII spellings retained in at least one of the three pinned orthographic sources."}],"initial_cohort":true,"lexical_build_id":"b5dc0fb56b8de890be69574e89a5505bb2ae0cb90d1033fbce6ecc35d0062d86","lexical_manifest_sha256":"caaf10ee36c0777068f015fa2544390cd9f968dc8addc083bb1b15a48b483aa9","lexical_release_timestamp":"2026-07-15T00:00:00+00:00","limitations":["The three lists have different purposes, collection methods, and scopes.","List membership does not establish common usage, dictionary status, game validity, or suitability for a task.","Normalized ASCII comparison does not evaluate senses, inflections, or regional usage.","Source redistribution and output reuse rights remain under human review."],"narrative":[{"block_id":"study.source-list-overlap.result","fact_ids":["study.source-list-overlap.exactly-one-share"],"heading":null,"interpretation_kind":"computed","paragraphs":["61.97% of the safe normalized-spelling records occur in exactly one of the three pinned spelling artifacts."]},{"block_id":"study.source-list-overlap.scope","fact_ids":[],"heading":"What this comparison establishes","interpretation_kind":"methodological","paragraphs":["A match establishes presence in an exact, versioned artifact after the declared normalization. It does not establish universal English validity, usage, dictionary consensus, or acceptance in a game."]}],"output_license":"No reuse licence asserted; source-rights review pending","output_license_url":"/about/data","population_sha256":"e72ae0cda8b6ab415216f81d1c7d529f03f4157caaf7089597e5ab852313e306","publication_status":"published","related_searches":[{"label":"Explore the compiled lexicon","relevance":"Compare source badges and frequency tiers in the interactive query tool.","url":"/words"}],"reproducibility_command":"make studies_reproduce STUDY=source-list-overlap","research_question":"How much do the pinned dwyl, ENABLE, and Google 10,000 spelling lists overlap in this lexical release?","review":{"approved_analysis_contract_digest":null,"approved_content_artifact_digest":null,"approved_content_version":null,"approved_data_version":null,"approved_lexical_build_id":null,"approved_result_sha256":null,"editorial_approval":null,"editorial_status":"pending","factual_approval":null,"factual_status":"machine-validated","legal_approval":null,"legal_status":"pending","reevaluate_on":"2026-10-13","reviewed_at":null,"reviewer":null,"search_approval":null,"search_eligibility_reason":"Machine-generated results are published noindex while editorial and source-rights review remain pending.","search_eligible":false},"schema_version":1,"slug":"source-list-overlap","sources":[{"artifact_sha256":"3ed0c94610d8bcf7c11bbb49c56aa49c7234d32b66824df91f554169e572da48","attribution":"dwyl/english-words; the repository carries an Unlicense notice, while its pinned README attributes upstream copyright to Infochimps","establishes":["source-membership","surface-spelling-as-listed"],"legal_review_status":"pending","licence_name":"Unlicense notice; upstream dataset rights unresolved","licence_url":"https://raw.githubusercontent.com/dwyl/english-words/8179fe68775df3f553ef19520db065228e65d1d3/LICENSE.md","limitations":["The pinned repository licence is the Unlicense, but the pinned README says copyright in the extracted source list remains with Infochimps. Human legal review of the upstream rights chain is required.","Do not assert a redistribution right until the Infochimps-to-dwyl rights chain has been reviewed by a human.","Dialect or scope: unspecified"],"redistribution_status":"pending","source_class":"broad-orthographic-list","source_id":"dwyl-english-words","source_version":"git:8179fe68775df3f553ef19520db065228e65d1d3","url":"https://raw.githubusercontent.com/dwyl/english-words/8179fe68775df3f553ef19520db065228e65d1d3/words_alpha.txt"},{"artifact_sha256":"d3fbe8485022088fcf527edcde2fbdc18b4bbc141ac58123c9adb462e086eaf7","attribution":"ENABLE (Enhanced North American Benchmark Lexicon); exact reuse terms are pending legal review","establishes":["source-membership","surface-spelling-as-listed"],"legal_review_status":"pending","licence_name":"Licence terms not stated by the source","licence_url":"https://www.wordgamedictionary.com/enable/","limitations":["The downloaded artifact is content-pinned by SHA-256, but it contains no licence notice and the configured source page does not state reuse terms.","The artifact is reproducibly pinned but no affirmative reuse grant has been located; redistribution approval remains pending.","Dialect or scope: North-American-oriented; exact edition metadata unavailable"],"redistribution_status":"pending","source_class":"historical-game-word-list","source_id":"enable","source_version":"artifact-sha256:d3fbe8485022088fcf527edcde2fbdc18b4bbc141ac58123c9adb462e086eaf7","url":"https://www.wordgamedictionary.com/enable/download/enable.txt"},{"artifact_sha256":"ee2d83651fbb91642bbed2bd30ead404c2cfbdfece01dacf284af6ea47795811","attribution":"first20hours/google-10000-english, derived from the Google Web Trillion Word Corpus and Peter Norvig's compilation","establishes":["source-membership","source-order"],"legal_review_status":"pending","licence_name":"No explicit licence grant in pinned repository metadata","licence_url":"https://raw.githubusercontent.com/first20hours/google-10000-english/bdf4c221bc120b0b7f6c3f1eff1cc1abb975f8d8/LICENSE.md","limitations":["The exact pinned LICENSE.md describes provenance but contains no explicit public-domain dedication or licence grant. Human review is required.","The pinned repository documents provenance but does not supply an affirmative licence grant; do not describe it as public domain.","Dialect or scope: USA no-swears variant"],"redistribution_status":"pending","source_class":"ranked-web-corpus-derived-list","source_id":"google-10000-english","source_version":"git:bdf4c221bc120b0b7f6c3f1eff1cc1abb975f8d8","url":"https://raw.githubusercontent.com/first20hours/google-10000-english/bdf4c221bc120b0b7f6c3f1eff1cc1abb975f8d8/google-10000-english-usa-no-swears.txt"},{"artifact_sha256":"ef70bc128a3ae67c23c5a4e31ec6b0ef3780e94881faa3adf9b73c2f7f684b4d","attribution":"The Word Index first-party content-safety exclusion policy","establishes":["content_filter","search_results","result_counts"],"legal_review_status":"pending","licence_name":"Reuse terms not yet approved","licence_url":null,"limitations":["This bounded policy list cannot determine whether every usage is offensive or benign."],"redistribution_status":"pending","source_class":"first-party-content-safety-policy","source_id":"offensive-term-policy","source_version":"2026.07-review-pending.2","url":"/about/data"}],"study_build_id":"b51b0db0024b63755e951e9fc5160916dab98d576b21e93920a4314c20724dd7","study_id":"study.source-list-overlap","study_version":"1.0.0","tables":[{"caption":"The exact population used by this version of the analysis.","column_ids":["stage","record_count"],"dataset_id":"study.source-list-overlap.population","heading":"Population and exclusions","note":null,"row_ids":["raw","policy-excluded","safe","analysis"],"table_id":"study.source-list-overlap.population-table"},{"caption":"Exact source-membership counts after the declared exclusions.","column_ids":["metric","record_count","share_percent"],"dataset_id":"study.source-list-overlap.summary","heading":"How often the spelling artifacts agree","note":null,"row_ids":["exactly-one","at-least-two","all-three"],"table_id":"study.source-list-overlap.summary-table"},{"caption":"Presence means membership in the named pinned artifact only.","column_ids":["membership_combination","source_count","record_count","share_percent"],"dataset_id":"study.source-list-overlap.combinations","heading":"Every exact source combination","note":null,"row_ids":["dwyl","enable","google-10000-english","dwyl-and-enable","dwyl-and-google-10000-english","enable-and-google-10000-english","dwyl-and-enable-and-google-10000-english"],"table_id":"study.source-list-overlap.combination-table"}],"title":"How three English spelling lists overlap","transformation_steps":[{"description":"Sort exact source IDs and assign each retained spelling to one mutually exclusive membership combination.","deterministic":true,"limitations":["Membership says only that the normalized spelling occurs in the pinned artifact."],"transformation_id":"source-overlap.membership-signature-v1"}],"update_history":[{"data_version":"2026.07-lexical.3","effective_date":"2026-07-15","result_sha256":"085b91080cd8c20702338ddd8ca28ccfedd8b19fc54ebd6c8966d20a89abbf9d","review_status":"machine-validated","reviewer":null,"study_version":"1.0.0","summary":"Initial reproducible aggregate release."}],"user_relevance":"The comparison shows why presence in one list is evidence of source membership, not universal English validity."}