{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4DYCERBSMZB4YWMYZWVNRDMM3M","short_pith_number":"pith:4DYCERBS","schema_version":"1.0","canonical_sha256":"e0f02244326643cc5998cdaad88d8cdb1e0485528939d44dbd19a09c491a8eed","source":{"kind":"arxiv","id":"2006.06465","version":1},"attestation_state":"computed","paper":{"title":"DNF-Net: A Neural Architecture for Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ami Abutbul, Gal Elidan, Liran Katzir, Ran El-Yaniv","submitted_at":"2020-06-11T14:21:45Z","abstract_excerpt":"A challenging open question in deep learning is how to handle tabular data. Unlike domains such as image and natural language processing, where deep architectures prevail, there is still no widely accepted neural architecture that dominates tabular data. As a step toward bridging this gap, we present DNF-Net a novel generic architecture whose inductive bias elicits models whose structure corresponds to logical Boolean formulas in disjunctive normal form (DNF) over affine soft-threshold decision terms. In addition, DNF-Net promotes localized decisions that are taken over small subsets of the fe"},"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":"2006.06465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T14:21:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a0070882cef2dcc76b8de540d5a1de327cc1a2a61c240002b123708ef872467","abstract_canon_sha256":"01cbf9ddcce84e907ac32fcaab6865a004f0c29d4c4461242d98d5e0a9defcb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:34.083221Z","signature_b64":"PnbtYfA1mzlEBLV6v6UqMuUaBkC6xp8qZACqXHA0RbVjQuD0pGI3oqqJqHBDQGGZ4oOPnJ/3vs3SaaZVNMMGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0f02244326643cc5998cdaad88d8cdb1e0485528939d44dbd19a09c491a8eed","last_reissued_at":"2026-07-05T01:09:34.082766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:34.082766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DNF-Net: A Neural Architecture for Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ami Abutbul, Gal Elidan, Liran Katzir, Ran El-Yaniv","submitted_at":"2020-06-11T14:21:45Z","abstract_excerpt":"A challenging open question in deep learning is how to handle tabular data. Unlike domains such as image and natural language processing, where deep architectures prevail, there is still no widely accepted neural architecture that dominates tabular data. As a step toward bridging this gap, we present DNF-Net a novel generic architecture whose inductive bias elicits models whose structure corresponds to logical Boolean formulas in disjunctive normal form (DNF) over affine soft-threshold decision terms. In addition, DNF-Net promotes localized decisions that are taken over small subsets of the fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06465","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/2006.06465/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":"2006.06465","created_at":"2026-07-05T01:09:34.082821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.06465v1","created_at":"2026-07-05T01:09:34.082821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06465","created_at":"2026-07-05T01:09:34.082821+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DYCERBSMZB4","created_at":"2026-07-05T01:09:34.082821+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DYCERBSMZB4YWMY","created_at":"2026-07-05T01:09:34.082821+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DYCERBS","created_at":"2026-07-05T01:09:34.082821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07756","citing_title":"The Importance of Encoder Choice:A Tabular-Image Study","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13392","citing_title":"ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13392","citing_title":"ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DYCERBSMZB4YWMYZWVNRDMM3M","json":"https://pith.science/pith/4DYCERBSMZB4YWMYZWVNRDMM3M.json","graph_json":"https://pith.science/api/pith-number/4DYCERBSMZB4YWMYZWVNRDMM3M/graph.json","events_json":"https://pith.science/api/pith-number/4DYCERBSMZB4YWMYZWVNRDMM3M/events.json","paper":"https://pith.science/paper/4DYCERBS"},"agent_actions":{"view_html":"https://pith.science/pith/4DYCERBSMZB4YWMYZWVNRDMM3M","download_json":"https://pith.science/pith/4DYCERBSMZB4YWMYZWVNRDMM3M.json","view_paper":"https://pith.science/paper/4DYCERBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.06465&json=true","fetch_graph":"https://pith.science/api/pith-number/4DYCERBSMZB4YWMYZWVNRDMM3M/graph.json","fetch_events":"https://pith.science/api/pith-number/4DYCERBSMZB4YWMYZWVNRDMM3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DYCERBSMZB4YWMYZWVNRDMM3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DYCERBSMZB4YWMYZWVNRDMM3M/action/storage_attestation","attest_author":"https://pith.science/pith/4DYCERBSMZB4YWMYZWVNRDMM3M/action/author_attestation","sign_citation":"https://pith.science/pith/4DYCERBSMZB4YWMYZWVNRDMM3M/action/citation_signature","submit_replication":"https://pith.science/pith/4DYCERBSMZB4YWMYZWVNRDMM3M/action/replication_record"}},"created_at":"2026-07-05T01:09:34.082821+00:00","updated_at":"2026-07-05T01:09:34.082821+00:00"}