{"id":"https://openalex.org/W7214166345","doi":"https://doi.org/10.5281/zenodo.22942235","title":"Code and data for: Reading Sustainability Reports as Pages, Not Text: visual retrieval and VLM extraction of GHG metrics","display_name":"Code and data for: Reading Sustainability Reports as Pages, Not Text: visual retrieval and VLM extraction of GHG metrics","publication_year":2026,"publication_date":"2026-09-24","ids":{"openalex":"https://openalex.org/W7214166345","doi":"https://doi.org/10.5281/zenodo.22942235"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22942235","doi":"https://doi.org/10.5281/zenodo.22942235","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22942235","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":"Software"},"parent_works":[],"lineage":["https://openalex.org/W7214166345"],"child_works_count":0,"type":"software","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22942235","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140105564","display_name":"Afonso Henrique Torres Lucas","orcid":"https://orcid.org/0009-0001-4998-6005","observed_orcids":["https://orcid.org/0009-0001-4998-6005"]},"institutions":[{"id":"https://openalex.org/I4210147594","display_name":"Universidade do Estado do Amazonas","ror":"https://ror.org/04j5z3x06","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210147594"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas, Afonso","raw_affiliation_strings":["Universidade do Estado do Amazonas (UEA)"],"raw_orcid":"https://orcid.org/0009-0001-4998-6005","affiliations":[{"raw_affiliation_string":"Universidade do Estado do Amazonas (UEA)","institution_ids":["https://openalex.org/I4210147594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152655183","display_name":"Julianne Oliveira","orcid":"https://orcid.org/0009-0000-7696-4330","observed_orcids":["https://orcid.org/0009-0000-7696-4330"]},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Oliveira, Julianne","raw_affiliation_strings":["Universidade Federal do Amazonas (UFAM)"],"raw_orcid":"https://orcid.org/0009-0000-7696-4330","affiliations":[{"raw_affiliation_string":"Universidade Federal do Amazonas (UFAM)","institution_ids":["https://openalex.org/I62885914"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073131738","display_name":"ROBERTO HIGINO PEREIRA DA SILVA","orcid":"https://orcid.org/0009-0001-9998-0373","observed_orcids":["https://orcid.org/0009-0001-9998-0373"]},"institutions":[{"id":"https://openalex.org/I4210147594","display_name":"Universidade do Estado do Amazonas","ror":"https://ror.org/04j5z3x06","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210147594"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Silva, Roberto","raw_affiliation_strings":["Universidade do Estado do Amazonas (UEA)"],"raw_orcid":"https://orcid.org/0009-0001-9998-0373","affiliations":[{"raw_affiliation_string":"Universidade do Estado do Amazonas (UEA)","institution_ids":["https://openalex.org/I4210147594"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"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/T10028","display_name":"Topic Modeling","score":0.5121999979019165,"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/T10028","display_name":"Topic Modeling","score":0.5121999979019165,"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/T10115","display_name":"Corporate Social Responsibility Reporting","score":0.18479999899864197,"subfield":{"id":"https://openalex.org/subfields/1408","display_name":"Strategy and Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.05510000139474869,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sustainability-reports","display_name":"sustainability reports","score":0.9660000205039978},{"id":"https://openalex.org/keywords/greenhouse-gas-emissions","display_name":"greenhouse gas emissions","score":0.8090000152587891},{"id":"https://openalex.org/keywords/scope-1-2-and-3-emissions","display_name":"scope 1, 2 and 3 emissions","score":0.7990000247955322},{"id":"https://openalex.org/keywords/visual-information-retrieval","display_name":"visual information retrieval","score":0.8109999895095825},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8550000190734863},{"id":"https://openalex.org/keywords/document-image-analysis","display_name":"document image analysis","score":0.5080000162124634},{"id":"https://openalex.org/keywords/qwen2-5","display_name":"Qwen2.5","score":0.7149999737739563},{"id":"https://openalex.org/keywords/qdrant","display_name":"Qdrant","score":0.7519999742507935},{"id":"https://openalex.org/keywords/structured-information-extraction","display_name":"structured data extraction","score":0.5860000252723694},{"id":"https://openalex.org/keywords/corporate-sustainability-disclosure","display_name":"corporate sustainability disclosure","score":0.382999986410141}],"concepts":[{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.666100025177002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6502000093460083},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C66204764","wikidata":"https://www.wikidata.org/wiki/Q219416","display_name":"Sustainability","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.49300000071525574},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48739999532699585},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4375},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.3752000033855438},{"id":"https://openalex.org/C47737302","wikidata":"https://www.wikidata.org/wiki/Q167336","display_name":"Greenhouse gas","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33820000290870667},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25429999828338623}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5281/zenodo.22942235","doi":"https://doi.org/10.5281/zenodo.22942235","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22942235","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":"Software"},{"id":"doi:10.5281/zenodo.22942236","doi":"https://doi.org/10.5281/zenodo.22942236","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22942236","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":"Software"},{"id":"doi:10.5281/zenodo.22942394","doi":"https://doi.org/10.5281/zenodo.22942394","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22942394","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":"Software"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22942235","doi":"https://doi.org/10.5281/zenodo.22942235","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22942235","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":"Software"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.821399986743927}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7107856449","https://openalex.org/W7169863636","https://openalex.org/W7171709230","https://openalex.org/W2552116031","https://openalex.org/W6911823523","https://openalex.org/W4413766721","https://openalex.org/W7131779162","https://openalex.org/W7077871422","https://openalex.org/W6989122865","https://openalex.org/W7161146311"],"abstract_inverted_index":{"Code":[0],"and":[1,18,38,50,52,65,74],"outputs":[2],"of":[3,21,70],"the":[4,7,63,68,71,75,84],"experiment":[5],"behind":[6],"article":[8],"\"Reading":[9],"Sustainability":[10],"Reports":[11],"as":[12,28,57],"Pages,":[13],"Not":[14],"Text:":[15],"visual":[16],"retrieval":[17],"VLM":[19],"extraction":[20,66],"GHG":[22],"metrics\".":[23],"Report":[24],"pages":[25],"are":[26],"kept":[27],"images,":[29],"retrieved":[30],"with":[31],"ColQwen2.5":[32],"multi-vector":[33],"embeddings":[34],"stored":[35],"in":[36],"Qdrant,":[37],"read":[39],"by":[40,81],"a":[41],"vision-language":[42],"model":[43],"that":[44,77],"returns":[45],"Scope":[46],"1,":[47],"2":[48],"(market-":[49],"location-based)":[51],"3":[53],"emissions":[54],"for":[55],"2013-2022":[56],"structured":[58],"JSON.":[59],"The":[60],"repository":[61],"includes":[62],"ingestion":[64],"pipelines,":[67],"extractions":[69],"reported":[72],"run,":[73],"notebook":[76],"evaluates":[78],"them":[79],"cell":[80,82],"against":[83],"GIST":[85],"gold":[86],"standard":[87],"(Beck":[88],"et":[89],"al.,":[90],"2025).":[91]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-09-25T00:00:00"}