{"id":"https://openalex.org/W7164040274","doi":"https://doi.org/10.1145/3798129.3800914","title":"Provable Long-Range Benefits of Next-Token Prediction","display_name":"Provable Long-Range Benefits of Next-Token Prediction","publication_year":2026,"publication_date":"2026-06-09","ids":{"openalex":"https://openalex.org/W7164040274","doi":"https://doi.org/10.1145/3798129.3800914"},"language":null,"primary_location":{"id":"doi:10.1145/3798129.3800914","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3798129.3800914","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th Annual ACM Symposium on Theory of Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3798129.3800914","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100681904","display_name":"Xinyuan Cao","orcid":"https://orcid.org/0000-0002-8043-505X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinyuan Cao","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":"https://orcid.org/0009-0008-1180-3198","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101983359","display_name":"Santosh Vempala","orcid":"https://orcid.org/0000-0002-3779-433X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Santosh S. Vempala","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":"https://orcid.org/0000-0002-3779-433X","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100681904"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.96693957,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2106","last_page":"2117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.01489999983459711,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.01489999983459711,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.013000000268220901,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.011800000444054604,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2904999852180481},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.27320000529289246},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2676999866962433},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2578999996185303},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.25600001215934753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5218999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35659998655319214},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29179999232292175},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3798129.3800914","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3798129.3800914","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th Annual ACM Symposium on Theory of Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3798129.3800914","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3798129.3800914","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th Annual ACM Symposium on Theory of Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1975846642","https://openalex.org/W1976183756","https://openalex.org/W1988790447","https://openalex.org/W1998918799","https://openalex.org/W2024046085","https://openalex.org/W2070534370","https://openalex.org/W2079145130","https://openalex.org/W2135481450","https://openalex.org/W2150355110","https://openalex.org/W2160403361","https://openalex.org/W2572743863","https://openalex.org/W2963466651","https://openalex.org/W3004732066","https://openalex.org/W3096831136","https://openalex.org/W3139003361","https://openalex.org/W3150645827","https://openalex.org/W4292081273","https://openalex.org/W4390575951","https://openalex.org/W7133197563","https://openalex.org/W7133211372","https://openalex.org/W7133228647"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-10T14:10:52.464848","created_date":"2026-06-10T00:00:00"}