{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XBK3H4IVTJEUZ62KVQ2UG3AJUQ","short_pith_number":"pith:XBK3H4IV","schema_version":"1.0","canonical_sha256":"b855b3f1159a494cfb4aac35436c09a42fb92ba41f5d880456b56fe15fbbdf96","source":{"kind":"arxiv","id":"2607.09710","version":1},"attestation_state":"computed","paper":{"title":"Manifold Constrained Tabular Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huizhi Liang, Lucy Robinson, Tian Li, Varun Ojha","submitted_at":"2026-06-23T19:11:52Z","abstract_excerpt":"Tabular classification is often governed by local, condition-triggered rules rather than smooth global patterns. However, tabular deep neural networks (DNNs) are typically built upon Euclidean representations that favor smooth variations and semantic locality. This potential geometric mismatch can make it challenging for tabular DNNs to efficiently represent the discrete, rule-partitioned structures often underlying tabular classification. To address this issue, we propose HDE-Net, a manifold-constrained DNN that enables hierarchical decision modeling in hyperbolic space. We first abstract het"},"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":"2607.09710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T19:11:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7f10cefce6511cfc55bae4560e6b7b51f912713a671e59d871a14a0d7750daff","abstract_canon_sha256":"76f3fc149276dfa0411656b55caae1301c989069516f7700817766d2893241c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:31.556344Z","signature_b64":"+feNC2uNOvGtUvV6ONXk7Ofd0oAVJfL6Rl9LjlxBe9Yt2MTNOpudubwYmH82u8/ffGQVJMfmJYNAKO/Fb7fUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b855b3f1159a494cfb4aac35436c09a42fb92ba41f5d880456b56fe15fbbdf96","last_reissued_at":"2026-07-14T00:18:31.555484Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:31.555484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Manifold Constrained Tabular Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huizhi Liang, Lucy Robinson, Tian Li, Varun Ojha","submitted_at":"2026-06-23T19:11:52Z","abstract_excerpt":"Tabular classification is often governed by local, condition-triggered rules rather than smooth global patterns. However, tabular deep neural networks (DNNs) are typically built upon Euclidean representations that favor smooth variations and semantic locality. This potential geometric mismatch can make it challenging for tabular DNNs to efficiently represent the discrete, rule-partitioned structures often underlying tabular classification. To address this issue, we propose HDE-Net, a manifold-constrained DNN that enables hierarchical decision modeling in hyperbolic space. We first abstract het"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09710","kind":"arxiv","version":1},"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/2607.09710/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":"2607.09710","created_at":"2026-07-14T00:18:31.555934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09710v1","created_at":"2026-07-14T00:18:31.555934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09710","created_at":"2026-07-14T00:18:31.555934+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBK3H4IVTJEU","created_at":"2026-07-14T00:18:31.555934+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBK3H4IVTJEUZ62K","created_at":"2026-07-14T00:18:31.555934+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBK3H4IV","created_at":"2026-07-14T00:18:31.555934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBK3H4IVTJEUZ62KVQ2UG3AJUQ","json":"https://pith.science/pith/XBK3H4IVTJEUZ62KVQ2UG3AJUQ.json","graph_json":"https://pith.science/api/pith-number/XBK3H4IVTJEUZ62KVQ2UG3AJUQ/graph.json","events_json":"https://pith.science/api/pith-number/XBK3H4IVTJEUZ62KVQ2UG3AJUQ/events.json","paper":"https://pith.science/paper/XBK3H4IV"},"agent_actions":{"view_html":"https://pith.science/pith/XBK3H4IVTJEUZ62KVQ2UG3AJUQ","download_json":"https://pith.science/pith/XBK3H4IVTJEUZ62KVQ2UG3AJUQ.json","view_paper":"https://pith.science/paper/XBK3H4IV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09710&json=true","fetch_graph":"https://pith.science/api/pith-number/XBK3H4IVTJEUZ62KVQ2UG3AJUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XBK3H4IVTJEUZ62KVQ2UG3AJUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBK3H4IVTJEUZ62KVQ2UG3AJUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBK3H4IVTJEUZ62KVQ2UG3AJUQ/action/storage_attestation","attest_author":"https://pith.science/pith/XBK3H4IVTJEUZ62KVQ2UG3AJUQ/action/author_attestation","sign_citation":"https://pith.science/pith/XBK3H4IVTJEUZ62KVQ2UG3AJUQ/action/citation_signature","submit_replication":"https://pith.science/pith/XBK3H4IVTJEUZ62KVQ2UG3AJUQ/action/replication_record"}},"created_at":"2026-07-14T00:18:31.555934+00:00","updated_at":"2026-07-14T00:18:31.555934+00:00"}