{"id":"https://openalex.org/W7163686136","doi":"https://doi.org/10.48550/arxiv.2606.06397","title":"The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning","display_name":"The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163686136","doi":"https://doi.org/10.48550/arxiv.2606.06397"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.06397","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06397","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.06397","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137930556","display_name":"Shuo Wang (143908)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138001821","display_name":"Xiangyu Wang (341093)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137951023","display_name":"Quanxin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Quanxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137981332","display_name":"Bailin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Bailin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011328645","display_name":"Bokui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Bokui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081728682","display_name":"Sizhao Huang","orcid":"https://orcid.org/0000-0002-7388-2089"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shunyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137946395","display_name":"Boyan Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Boyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137932129","display_name":"Haonan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Haonan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094095293","display_name":"Ruiyi Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Ruiyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126915868","display_name":"Zhenxiang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zhenxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137944725","display_name":"BoYu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Boyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052459660","display_name":"Zhao Kang","orcid":"https://orcid.org/0000-0003-4103-0954"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9908000230789185,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9908000230789185,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.0017999999690800905,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.5598000288009644},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5595999956130981},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4943999946117401},{"id":"https://openalex.org/keywords/statistical-relational-learning","display_name":"Statistical relational learning","score":0.4562000036239624},{"id":"https://openalex.org/keywords/curvature","display_name":"Curvature","score":0.4505000114440918},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.3662000000476837},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3596999943256378},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.671500027179718},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5598000288009644},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5595999956130981},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47780001163482666},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.4562000036239624},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4077000021934509},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.33799999952316284},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C43091099","wikidata":"https://www.wikidata.org/wiki/Q1067788","display_name":"Through-the-lens metering","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.06397","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06397","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.06397","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06397","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"evaluation":[1,90,172,193],"practices":[2],"in":[3,211],"relational":[4,203],"learning":[5,119,204],"rely":[6],"heavily":[7],"on":[8,165],"flat":[9],"leaderboards":[10],"that":[11,25,62,70,92,126,142,174],"average":[12],"performance":[13,34,68,143],"across":[14,121,139],"heterogeneous":[15],"datasets,":[16],"implicitly":[17],"assuming":[18],"a":[19,53,88,170],"uniform":[20],"underlying":[21],"structure.":[22],"We":[23,60,124,185],"show":[24],"this":[26,46,84],"assumption":[27],"introduces":[28],"systematic":[29],"bias:":[30],"it":[31],"obscures":[32],"geometry-dependent":[33,146],"variations":[35],"and":[36,98,117,178,192,198,207],"can":[37],"lead":[38],"to":[39,161,195],"misleading":[40],"conclusions":[41],"about":[42],"model":[43,58,127],"generalization.":[44],"In":[45],"work,":[47],"we":[48,86,152,168],"identify":[49,153],"intrinsic":[50],"geometry":[51],"as":[52],"key":[54],"latent":[55],"factor":[56],"governing":[57],"effectiveness.":[59],"demonstrate":[61],"conventional":[63],"aggregated":[64,183],"metrics":[65],"mask":[66],"critical":[67],"trade-offs":[69],"only":[71],"become":[72],"visible":[73],"when":[74],"datasets":[75,94,208],"are":[76,129,209],"stratified":[77],"by":[78],"their":[79],"geometric":[80],"properties.":[81],"To":[82],"address":[83],"issue,":[85],"introduce":[87],"curvature-stratified":[89,189],"framework":[91],"partitions":[93],"into":[95],"positive,":[96],"negative,":[97],"near-zero":[99],"curvature":[100,134],"regimes.":[101],"Our":[102],"benchmark":[103],"evaluates":[104],"18":[105],"representative":[106],"models":[107],"including":[108],"Graph":[109,113],"Convolutional":[110],"Networks":[111],"(GCNs),":[112],"Foundation":[114],"Models":[115],"(GFMs),":[116],"tabular":[118],"methods":[120],"14":[122],"datasets.":[123],"find":[125],"rankings":[128],"highly":[130],"stable":[131],"within":[132],"each":[133],"regime":[135],"but":[136],"shift":[137],"significantly":[138],"regimes,":[140],"indicating":[141],"is":[144],"fundamentally":[145],"rather":[147],"than":[148,181],"universally":[149],"transferable.":[150],"Notably,":[151],"regimes":[154],"where":[155],"GFMs":[156],"offer":[157],"diminishing":[158],"returns":[159],"compared":[160],"geometry-aligned":[162],"GNNs.":[163],"Based":[164],"these":[166],"findings,":[167],"propose":[169],"geometry-aware":[171],"protocol":[173],"yields":[175],"more":[176],"reliable":[177],"interpretable":[179],"comparisons":[180],"standard":[182],"benchmarks.":[184],"release":[186],"all":[187],"code,":[188],"dataset":[190],"splits,":[191],"tools":[194],"support":[196],"reproducible":[197],"rigorous":[199],"assessment":[200],"of":[201],"future":[202],"methods.":[205],"Code":[206],"provided":[210],"our":[212],"project":[213],"homepage:":[214],"https://sirbabbage.github.io/CurvBench_HOME/.":[215]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-06T00:00:00"}