{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:U6R7KJSDFAIFV64QPBMZDBSNHC","short_pith_number":"pith:U6R7KJSD","schema_version":"1.0","canonical_sha256":"a7a3f5264328105afb90785991864d3895ffff9c9aeef6c21c8966bf00cd3c95","source":{"kind":"arxiv","id":"2009.02544","version":2},"attestation_state":"computed","paper":{"title":"Machine Learning Calabi-Yau Four-folds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AG","stat.ML"],"primary_cat":"hep-th","authors_text":"Andre Lukas, Yang-Hui He","submitted_at":"2020-09-05T14:54:25Z","abstract_excerpt":"Hodge numbers of Calabi-Yau manifolds depend non-trivially on the underlying manifold data and they present an interesting challenge for machine learning. In this letter we consider the data set of complete intersection Calabi-Yau four-folds, a set of about 900,000 topological types, and study supervised learning of the Hodge numbers h^1,1 and h^3,1 for these manifolds. We find that h^1,1 can be successfully learned (to 96% precision) by fully connected classifier and regressor networks. While both types of networks fail for h^3,1, we show that a more complicated two-branch network, combined w"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2009.02544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-th","submitted_at":"2020-09-05T14:54:25Z","cross_cats_sorted":["math.AG","stat.ML"],"title_canon_sha256":"8b0d4e01f78c08cfc22f52044685c69aed9b030c30d91881b15448dfbd52ec2c","abstract_canon_sha256":"a4f0aec2fd910f85e025c3b1ba6970374a6fe30dea0a2d05ed16b6b03267662c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:54.222503Z","signature_b64":"0IdqtM//z/ULMP2ZCRXJd1VoFLXD4FkLP63K1wNEimTMN3VKHcfRiCzrgB68CxnVcHv/AgjfcRgWEZmIa/khAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7a3f5264328105afb90785991864d3895ffff9c9aeef6c21c8966bf00cd3c95","last_reissued_at":"2026-07-05T02:15:54.221991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:54.221991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning Calabi-Yau Four-folds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AG","stat.ML"],"primary_cat":"hep-th","authors_text":"Andre Lukas, Yang-Hui He","submitted_at":"2020-09-05T14:54:25Z","abstract_excerpt":"Hodge numbers of Calabi-Yau manifolds depend non-trivially on the underlying manifold data and they present an interesting challenge for machine learning. In this letter we consider the data set of complete intersection Calabi-Yau four-folds, a set of about 900,000 topological types, and study supervised learning of the Hodge numbers h^1,1 and h^3,1 for these manifolds. We find that h^1,1 can be successfully learned (to 96% precision) by fully connected classifier and regressor networks. While both types of networks fail for h^3,1, we show that a more complicated two-branch network, combined w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.02544","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.02544/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2009.02544","created_at":"2026-07-05T02:15:54.222066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.02544v2","created_at":"2026-07-05T02:15:54.222066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.02544","created_at":"2026-07-05T02:15:54.222066+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6R7KJSDFAIF","created_at":"2026-07-05T02:15:54.222066+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6R7KJSDFAIFV64Q","created_at":"2026-07-05T02:15:54.222066+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6R7KJSD","created_at":"2026-07-05T02:15:54.222066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19157","citing_title":"Machine Learning Free Quotients of CICYs","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6R7KJSDFAIFV64QPBMZDBSNHC","json":"https://pith.science/pith/U6R7KJSDFAIFV64QPBMZDBSNHC.json","graph_json":"https://pith.science/api/pith-number/U6R7KJSDFAIFV64QPBMZDBSNHC/graph.json","events_json":"https://pith.science/api/pith-number/U6R7KJSDFAIFV64QPBMZDBSNHC/events.json","paper":"https://pith.science/paper/U6R7KJSD"},"agent_actions":{"view_html":"https://pith.science/pith/U6R7KJSDFAIFV64QPBMZDBSNHC","download_json":"https://pith.science/pith/U6R7KJSDFAIFV64QPBMZDBSNHC.json","view_paper":"https://pith.science/paper/U6R7KJSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.02544&json=true","fetch_graph":"https://pith.science/api/pith-number/U6R7KJSDFAIFV64QPBMZDBSNHC/graph.json","fetch_events":"https://pith.science/api/pith-number/U6R7KJSDFAIFV64QPBMZDBSNHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6R7KJSDFAIFV64QPBMZDBSNHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6R7KJSDFAIFV64QPBMZDBSNHC/action/storage_attestation","attest_author":"https://pith.science/pith/U6R7KJSDFAIFV64QPBMZDBSNHC/action/author_attestation","sign_citation":"https://pith.science/pith/U6R7KJSDFAIFV64QPBMZDBSNHC/action/citation_signature","submit_replication":"https://pith.science/pith/U6R7KJSDFAIFV64QPBMZDBSNHC/action/replication_record"}},"created_at":"2026-07-05T02:15:54.222066+00:00","updated_at":"2026-07-05T02:15:54.222066+00:00"}