{"id":"https://openalex.org/W7224088106","doi":"https://doi.org/10.5281/zenodo.23727436","title":"Preregistration (part 1): Sampling rule and data split for the study 'An LLM manual for coding teacher talk moves' (TalkMoves)","display_name":"Preregistration (part 1): Sampling rule and data split for the study 'An LLM manual for coding teacher talk moves' (TalkMoves)","publication_year":2026,"publication_date":"2026-10-28","ids":{"openalex":"https://openalex.org/W7224088106","doi":"https://doi.org/10.5281/zenodo.23727436"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23727436","doi":"https://doi.org/10.5281/zenodo.23727436","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23727436","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"volume":null,"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23727436","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092902974","display_name":"Simon Filler","orcid":"https://orcid.org/0009-0008-8736-8831","observed_orcids":["https://orcid.org/0009-0008-8736-8831"]},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Filler, Simon","raw_affiliation_strings":["TU Dortmund University"],"raw_orcid":"https://orcid.org/0009-0008-8736-8831","affiliations":[{"raw_affiliation_string":"TU Dortmund University","institution_ids":["https://openalex.org/I200332995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5092902974"],"corresponding_institution_ids":["https://openalex.org/I200332995"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93594306,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.22949999570846558,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.22949999570846558,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.06909999996423721,"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/T10561","display_name":"Educational Research and Methods","score":0.06809999793767929,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7919999957084656},{"id":"https://openalex.org/keywords/sampling-rules","display_name":"sampling rules","score":0.652999997138977},{"id":"https://openalex.org/keywords/data-splits","display_name":"data splits","score":0.8999999761581421},{"id":"https://openalex.org/keywords/lesson-series","display_name":"lesson series","score":0.734000027179718}],"concepts":[{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6585999727249146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6241999864578247},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5236999988555908},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4388999938964844},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3797000050544739},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C2993010571","wikidata":"https://www.wikidata.org/wiki/Q49908","display_name":"Probability sampling","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2759999930858612},{"id":"https://openalex.org/C65499552","wikidata":"https://www.wikidata.org/wiki/Q5421061","display_name":"Experience sampling method","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25940001010894775},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23727436","doi":"https://doi.org/10.5281/zenodo.23727436","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23727436","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.5281/zenodo.23727437","doi":"https://doi.org/10.5281/zenodo.23727437","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23727437","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23727436","doi":"https://doi.org/10.5281/zenodo.23727436","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23727436","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7224119324","https://openalex.org/W7167063601","https://openalex.org/W7222887235","https://openalex.org/W7168236856","https://openalex.org/W7222088947","https://openalex.org/W7168240227","https://openalex.org/W7214542604","https://openalex.org/W7140878918","https://openalex.org/W2251460994","https://openalex.org/W6943975536"],"abstract_inverted_index":{"Sampling":[0],"rule":[1,29],"for":[2],"passages":[3],"from":[4],"the":[5,33,42,55,63],"TalkMoves":[6],"dataset":[7],"(Suresh":[8],"et":[9],"al.,":[10],"2022):":[11],"development":[12],"part":[13,16,60],"(Dev-Train),":[14],"validation":[15],"(Dev-Val),":[17],"aggregator":[18],"pool":[19],"and":[20,32,54],"locked":[21],"test":[22],"part,":[23],"assigned":[24],"by":[25],"lesson":[26],"series.":[27],"The":[28],"was":[30],"approved":[31],"draw":[34],"carried":[35],"out":[36],"on":[37],"2026-10-28":[38],"with":[39],"seed":[40],"20261028;":[41],"allocation":[43],"files":[44],"contain":[45],"only":[46],"sentence":[47],"IDs,":[48],"no":[49],"transcript":[50],"text.":[51],"Hypotheses,":[52],"conditions":[53],"analysis":[56],"plan":[57],"follow":[58],"in":[59],"2":[61],"before":[62],"main":[64],"runs.":[65]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-10-29T00:00:00"}