{"id":"https://openalex.org/W7202299586","doi":"https://doi.org/10.48550/arxiv.2608.10974","title":"MUSE: A Full-Text Cross-Domain Knowledge Base of Scientific Problems, Solutions, and Rationales","display_name":"MUSE: A Full-Text Cross-Domain Knowledge Base of Scientific Problems, Solutions, and Rationales","publication_year":2026,"publication_date":"2026-08-11","ids":{"openalex":"https://openalex.org/W7202299586","doi":"https://doi.org/10.48550/arxiv.2608.10974"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.10974","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10974","pdf_url":"https://arxiv.org/pdf/2608.10974","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.10974","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147016394","display_name":"Tsofia Cohen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Cohen, Tsofia","raw_affiliation_strings":["The Hebrew University of Jerusalem"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137008880","display_name":"Tom Hope","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Hope, Tom","raw_affiliation_strings":["Allen Institute for AI (Ai2) GitHub","The Hebrew University of Jerusalem"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI (Ai2) GitHub","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"The Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.4456000030040741,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.4456000030040741,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2410999983549118,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.1860000044107437,"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/scientific-problem-solving","display_name":"scientific problem solving","score":0.902999997138977},{"id":"https://openalex.org/keywords/scientific-explanation","display_name":"scientific explanation","score":0.4620000123977661},{"id":"https://openalex.org/keywords/knowledge-base-construction","display_name":"knowledge base construction","score":0.7149999737739563},{"id":"https://openalex.org/keywords/coreference-resolution","display_name":"coreference resolution","score":0.7009999752044678},{"id":"https://openalex.org/keywords/llm-training","display_name":"LLM training","score":0.675000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6262000203132629},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.6136999726295471},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5175999999046326},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4296000003814697},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.4018000066280365},{"id":"https://openalex.org/C29275276","wikidata":"https://www.wikidata.org/wiki/Q2268965","display_name":"Conceptual schema","level":3,"score":0.3944000005722046},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27480000257492065},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.10974","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10974","pdf_url":"https://arxiv.org/pdf/2608.10974","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.10974","doi":"https://doi.org/10.48550/arxiv.2608.10974","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.10974","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.10974","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10974","pdf_url":"https://arxiv.org/pdf/2608.10974","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202299586.pdf","grobid_xml":"https://content.openalex.org/works/W7202299586.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2965373594","https://openalex.org/W2978017171","https://openalex.org/W4387299660","https://openalex.org/W4387561528","https://openalex.org/W4391631327","https://openalex.org/W4414281281","https://openalex.org/W7161229779"],"related_works":["https://openalex.org/W7160284844","https://openalex.org/W4417155673","https://openalex.org/W4281727039","https://openalex.org/W7077852527","https://openalex.org/W7204894844","https://openalex.org/W2965244786","https://openalex.org/W2903164276","https://openalex.org/W2799482190","https://openalex.org/W6922272315","https://openalex.org/W7140078776"],"abstract_inverted_index":{"Scientific":[0,35],"papers":[1],"contain":[2],"fine-grained":[3],"records":[4],"of":[5,41,84],"problem":[6,105],"solving:":[7],"authors":[8],"mention":[9],"technical":[10],"obstacles":[11],"and":[12,61,65,68,94],"methods":[13,27],"that":[14,110],"were":[15,28],"used":[16],"to":[17,78],"address":[18],"them,":[19],"often":[20],"along":[21],"with":[22,52],"reasoning":[23],"on":[24,115,123],"why":[25],"those":[26],"chosen.":[29],"We":[30,46,89],"introduce":[31],"MUSE":[32],"(Mining":[33],"Underlying":[34],"Explanations),":[36],"a":[37,53,80,96,100],"full-text,":[38],"multi-domain":[39],"resource":[40],"scientific":[42,104],"Problem-Solution-Rationale":[43],"(P-S-R)":[44],"triplets.":[45,88],"curate":[47],"579":[48],"expert-annotated":[49],"full-text":[50],"paragraphs,":[51],"rich":[54],"annotation":[55,77],"schema":[56],"covering":[57],"salient":[58],"problem,":[59],"solution,":[60],"rationale":[62,111],"spans,":[63],"solves":[64],"rationale_of":[66],"links":[67],"conceptual":[69],"coreference.":[70],"A":[71],"modular":[72],"extraction":[73,92],"pipeline":[74],"scales":[75],"this":[76],"build":[79],"high-quality":[81],"knowledge":[82],"base":[83],"37K":[85],"source-grounded":[86],"P-S-R":[87],"evaluate":[90],"the":[91],"components":[93],"include":[95],"preliminary":[97],"experiment":[98],"training":[99],"rationale-supervised":[101],"LLM":[102],"for":[103],"solving.":[106],"Interestingly,":[107],"we":[108],"find":[109],"supervision":[112],"improves":[113],"performance":[114,122],"complex,":[116],"multi-constraint":[117],"problems":[118],"but":[119],"can":[120],"harm":[121],"simpler":[124],"ones.":[125]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-13T00:00:00"}