{"id":"https://openalex.org/W7225379944","doi":"https://doi.org/10.5281/zenodo.24023093","title":"Directional Consensus Mapping: Zero-Shot Optimization Trajectory Alignment for Pre-Training Data Selection","display_name":"Directional Consensus Mapping: Zero-Shot Optimization Trajectory Alignment for Pre-Training Data Selection","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225379944","doi":"https://doi.org/10.5281/zenodo.24023093"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24023093","doi":"https://doi.org/10.5281/zenodo.24023093","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24023093","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":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24023093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101396609","display_name":"Shashank Jain","orcid":"https://orcid.org/0000-0002-8022-4762","observed_orcids":["https://orcid.org/0000-0002-8022-4762"]},"institutions":[{"id":"https://openalex.org/I197809005","display_name":"University of Campania \"Luigi Vanvitelli\"","ror":"https://ror.org/02kqnpp86","country_code":"IT","type":"education","lineage":["https://openalex.org/I197809005"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"JAIN, SHASHANK","raw_affiliation_strings":["University of Campania \"Luigi Vanvitelli\""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Campania \"Luigi Vanvitelli\"","institution_ids":["https://openalex.org/I197809005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101396609"],"corresponding_institution_ids":["https://openalex.org/I197809005"],"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":0.9398999810218811,"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":0.9398999810218811,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03200000151991844,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0071000000461936,"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/large-language-models","display_name":"large language models","score":0.652999997138977},{"id":"https://openalex.org/keywords/gradient-alignment","display_name":"gradient alignment","score":0.49799999594688416},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.5799999833106995},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"cosine similarity","score":0.4169999957084656},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.6370000243186951},{"id":"https://openalex.org/keywords/multimodal-data","display_name":"multimodal data","score":0.414000004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652999997138977},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4138999879360199},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40209999680519104},{"id":"https://openalex.org/C2776562905","wikidata":"https://www.wikidata.org/wiki/Q306610","display_name":"Hypersphere","level":2,"score":0.38600000739097595},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37610000371932983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37139999866485596},{"id":"https://openalex.org/C80156102","wikidata":"https://www.wikidata.org/wiki/Q788036","display_name":"Resolver","level":3,"score":0.3702000081539154},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C82668687","wikidata":"https://www.wikidata.org/wiki/Q3046456","display_name":"Earth mover's distance","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C5349765","wikidata":"https://www.wikidata.org/wiki/Q5282866","display_name":"Distance matrices in phylogeny","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.3425000011920929},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C138187205","wikidata":"https://www.wikidata.org/wiki/Q131251","display_name":"Tangent","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.26919999718666077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24023093","doi":"https://doi.org/10.5281/zenodo.24023093","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24023093","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":"Preprint"},{"id":"doi:10.5281/zenodo.24023094","doi":"https://doi.org/10.5281/zenodo.24023094","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24023094","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":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24023093","doi":"https://doi.org/10.5281/zenodo.24023093","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24023093","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":"Preprint"},"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/W4416045136","https://openalex.org/W7166848025","https://openalex.org/W4412887907","https://openalex.org/W7106304326","https://openalex.org/W4412889002","https://openalex.org/W4403619024","https://openalex.org/W4414981092","https://openalex.org/W4416123692","https://openalex.org/W7169836405","https://openalex.org/W4417170870"],"abstract_inverted_index":{"Selecting":[0],"high-quality,":[1],"task-aligned":[2],"pre-training":[3,76],"data":[4,16,77],"is":[5,53],"critical":[6],"for":[7],"training":[8],"foundation":[9],"Large":[10],"Language":[11],"Models":[12],"(LLMs).":[13],"Current":[14],"automated":[15],"curation":[17],"frameworks":[18],"rely":[19],"on":[20,42,131],"heuristic":[21],"proxies\u2014specifically":[22],"token-level":[23],"unigram":[24],"KL-divergence":[25],"(e.g.,":[26,33],"DSIR)":[27],"or":[28],"frozen":[29],"representation-space":[30],"distance":[31,49],"metrics":[32],"SemDeDup).":[34],"We":[35],"demonstrate":[36],"that":[37,74],"these":[38],"geometric":[39],"proxies":[40],"fail":[41],"multimodal":[43],"and":[44,100,121,190],"structurally":[45],"heterogeneous":[46],"distributions":[47],"because":[48],"in":[50],"activation":[51],"space":[52,84],"uncoupled":[54],"from":[55,183],"the":[56,81,93,102,112,122],"optimization":[57,72],"loss":[58],"manifold.":[59],"In":[60,127],"this":[61],"technical":[62],"report,":[63],"we":[64],"propose":[65],"Directional":[66],"Consensus":[67],"Mapping":[68],"(DCM):":[69],"a":[70,154],"first-principles":[71],"framework":[73],"determines":[75],"suitability":[78],"directly":[79],"within":[80],"parameter":[82],"tangent":[83],"at":[85],"initialization":[86],"(W_0).":[87],"By":[88],"projecting":[89],"per-sample":[90],"gradients":[91],"onto":[92],"unit":[94],"hypersphere":[95],"(\"one":[96],"sample,":[97],"one":[98],"vote\")":[99],"computing":[101],"directional":[103],"consensus":[104],"vector":[105],"field":[106],"across":[107,141],"network":[108],"layers,":[109],"DCM":[110,152,167],"isolates":[111],"pure":[113],"angular":[114],"alignment":[115],"(cosine":[116],"similarity)":[117],"between":[118],"candidate":[119],"updates":[120],"target":[123],"benchmark":[124],"descent":[125],"trajectory.":[126],"preliminary":[128],"empirical":[129],"benchmarks":[130],"an":[132],"untrained":[133],"1.2-billion-parameter":[134],"transformer":[135],"(Llama-3.2-1B,":[136],"probing":[137],"973,144,064":[138],"reasoning":[139,177],"parameters)":[140],"six":[142],"diverse":[143],"open-source":[144],"corpora":[145],"using":[146],"only":[147],"80":[148],"samples":[149],"per":[150],"domain,":[151],"achieves":[153],"Spearman":[155],"rank":[156],"correlation":[157],"of":[158],"rho":[159],"=":[160],"+0.7143":[161],"against":[162],"ground-truth":[163],"downstream":[164],"loss.":[165],"Crucially,":[166],"naturally":[168],"resolves":[169],"catastrophic":[170],"formatting":[171],"magnitude":[172],"bias,":[173],"accurately":[174],"isolating":[175],"mathematical":[176],"signals":[178],"(cos":[179,186,193],"theta":[180,187,194],"~":[181,188,195],"0.39\u20130.43)":[182],"unaligned":[184],"dialogue":[185],"0.19)":[189],"syntax-heavy":[191],"code":[192],"0.06).":[196]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}