{"id":"https://openalex.org/W7204586925","doi":"https://doi.org/10.5281/zenodo.22149933","title":"Samudra Manthanam: Markup-Aligned Sanskrit\u2013Russian Parallel Corpus of 148 Sources (corpus of record)","display_name":"Samudra Manthanam: Markup-Aligned Sanskrit\u2013Russian Parallel Corpus of 148 Sources (corpus of record)","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204586925","doi":"https://doi.org/10.5281/zenodo.22149933"},"language":"sa","primary_location":{"id":"doi:10.5281/zenodo.22149933","doi":"https://doi.org/10.5281/zenodo.22149933","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22149933","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22149933","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140681587","display_name":"M\u0101rcis Gas\u016bns","orcid":"https://orcid.org/0000-0003-4513-884X","observed_orcids":["https://orcid.org/0000-0003-4513-884X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gas\u016bns, M\u0101rcis","raw_affiliation_strings":["Independent scholar"],"raw_orcid":"https://orcid.org/0000-0003-4513-884X","affiliations":[{"raw_affiliation_string":"Independent scholar","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5140681587"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.014100000262260437,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10759","display_name":"Translation Studies and Practices","score":0.0052999998442828655,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.8560000061988831},{"id":"https://openalex.org/keywords/sanskrit-texts","display_name":"Sanskrit texts","score":0.6259999871253967},{"id":"https://openalex.org/keywords/russian-translation","display_name":"Russian translation","score":0.8889999985694885},{"id":"https://openalex.org/keywords/bhagavad-gita","display_name":"Bhagavad Gita","score":0.9319999814033508},{"id":"https://openalex.org/keywords/sanskrit-dictionaries","display_name":"Sanskrit dictionaries","score":0.7889999747276306},{"id":"https://openalex.org/keywords/poetry-translation","display_name":"poetry translation","score":0.6639999747276306}],"concepts":[{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.6208000183105469},{"id":"https://openalex.org/C29912816","wikidata":"https://www.wikidata.org/wiki/Q11059","display_name":"Sanskrit","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.5637000203132629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4844000041484833},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.41589999198913574},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3917999863624573},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C2776299755","wikidata":"https://www.wikidata.org/wiki/Q432449","display_name":"Carry (investment)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C120012220","wikidata":"https://www.wikidata.org/wiki/Q1754533","display_name":"Source text","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.3248000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C2779235478","wikidata":"https://www.wikidata.org/wiki/Q286576","display_name":"Register (sociolinguistics)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C194051139","wikidata":"https://www.wikidata.org/wiki/Q2629608","display_name":"Syllabic verse","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2745000123977661},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2727000117301941}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22149933","doi":"https://doi.org/10.5281/zenodo.22149933","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22149933","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22149934","doi":"https://doi.org/10.5281/zenodo.22149934","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22149934","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22149933","doi":"https://doi.org/10.5281/zenodo.22149933","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22149933","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W7168098087"],"related_works":["https://openalex.org/W7168098087","https://openalex.org/W7162785619","https://openalex.org/W4383175538","https://openalex.org/W7154569182","https://openalex.org/W7160073261","https://openalex.org/W6930698664","https://openalex.org/W7140507837","https://openalex.org/W7123471160","https://openalex.org/W7104605461","https://openalex.org/W2782166432"],"abstract_inverted_index":{"Markup-aligned":[0],"parallel":[1],"corpus":[2,142,197],"of":[3,78,120,198,209],"148":[4],"sources":[5,47],"(574,939":[6],"segment":[7],"records),":[8,49],"extracted":[9],"deterministically":[10],"from":[11,195],"the":[12,17,20,33,36,79,116,159,178,183],"source":[13,18,94],"markup":[14],"\u2014":[15,85,173],"in":[16,108,158,203,223],"HTML":[19],"Sanskrit":[21,93],"text":[22,95],"and":[23,32,69,148,165,200],"its":[24],"Russian":[25,76,100],"translation":[26],"are":[27,193],"interleaved":[28],"as":[29],"sibling":[30],"blocks,":[31],"converter":[34,166],"reads":[35],"pairing":[37],"directly;":[38],"no":[39],"statistical":[40],"alignment":[41],"is":[42,211],"run.":[43],"Composition:":[44],"119":[45],"verse":[46,61],"(208,230":[48],"15":[50],"dictionaries":[51],"(321,672),":[52],"14":[53],"prose":[54],"works":[55],"(45,037).":[56],"Headline:":[57],"78,219":[58],"clean":[59],"1:1":[60],"pairs":[62],"(78,139":[63],"live":[64],"re-count),":[65],"plus":[66],"10,009":[67],"Russian-only":[68],"80":[70],"Sanskrit-only":[71],"monolingual":[72],"segments.":[73],"Includes":[74],"11":[75],"translations":[77,101],"Bhagavadg\u012bt\u0101":[80],"(1788\u20132015)":[81],"with":[82,110,122,136],"three":[83],"commentaries":[84],"a":[86,111,204],"built-in":[87],"diachronic":[88],"register":[89],"set.":[90],"Rights":[91],"(per-layer):":[92],"public":[96,104],"domain":[97],"by":[98,152],"age;":[99],"pre-1930":[102],"editions":[103,107],"domain,":[105],"20th\u201321st-century":[106],"copyright":[109],"grey":[112],"residual,":[113],"shipped":[114],"under":[115],"project's":[117],"standing":[118],"ruling":[119],"2026-08-08":[121],"translators":[123],"documented":[124],"per":[125],"source;":[126],"imported":[127],"DCS":[128],"lemma/morphology":[129],"layer":[130],"CC":[131],"BY":[132],"4.0":[133],"(Hellwig),":[134],"redistributed":[135],"attribution;":[137],"upstream":[138,186],"code/schema/documentation":[139],"Apache-2.0.":[140],"The":[141],"texts":[143],"carry":[144],"their":[145,153],"own":[146],"rights":[147],"must":[149],"be":[150],"cited":[151],"print":[154],"editions;":[155],"full":[156],"table":[157],"data":[160],"statement":[161],"file.":[162],"Provenance:":[163],"platform":[164],"at":[167],"https://github.com/gasyoun/SamudraManthanam":[168],"(software":[169],"concept":[170],"DOI":[171,176,181],"10.5281/zenodo.21317315":[172],"cite":[174],"that":[175],"for":[177,182],"software,":[179],"this":[180,196],"corpus).":[184],"Post-report":[185],"additions":[187],"(121":[188],"files":[189],"/":[190],"199,379":[191],"records)":[192],"excluded":[194],"record":[199,210],"may":[201],"appear":[202],"future":[205],"separately-versioned":[206],"release.":[207],"Corpus":[208],"byte-stable":[212],"across":[213],"four":[214],"re-counts":[215],"(2026-06-26,":[216],"2026-07-08,":[217],"2026-07-11,":[218],"2026-08-10);":[219],"every":[220],"figure":[221],"recomputes":[222],"one":[224],"deterministic":[225],"pass.":[226]},"counts_by_year":[],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2026-08-29T00:00:00"}
