{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZR63OTFURKGU7WOZHZTKN3LW22","short_pith_number":"pith:ZR63OTFU","schema_version":"1.0","canonical_sha256":"cc7db74cb48a8d4fd9d93e66a6ed76d6956ce27f79bcbe53da512b743c418e68","source":{"kind":"arxiv","id":"1702.07360","version":2},"attestation_state":"computed","paper":{"title":"Neural Decision Trees","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Randall Balestriero","submitted_at":"2017-02-23T19:02:32Z","abstract_excerpt":"In this paper we propose a synergistic melting of neural networks and decision trees (DT) we call neural decision trees (NDT). NDT is an architecture a la decision tree where each splitting node is an independent multilayer perceptron allowing oblique decision functions or arbritrary nonlinear decision function if more than one layer is used. This way, each MLP can be seen as a node of the tree. We then show that with the weight sharing asumption among those units, we end up with a Hashing Neural Network (HNN) which is a multilayer perceptron with sigmoid activation function for the last layer"},"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":"1702.07360","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2017-02-23T19:02:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c26e5435042fc362f062c42a228c864ca4f2a0187831f94738aa5a0aa83f5e98","abstract_canon_sha256":"6e0d93eaf41c37cca863c502e74026a116e605e18dd0ea7a182055e93fefa226"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:31.344907Z","signature_b64":"Ypci25cYn8q3ozc7RS8PhZEAi/bnOtlLdRFTt0BXgD07DLovCuw0MhDVz9aG199rSljXgT1B/manKQa/OIfnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc7db74cb48a8d4fd9d93e66a6ed76d6956ce27f79bcbe53da512b743c418e68","last_reissued_at":"2026-05-18T00:49:31.343999Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:31.343999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Decision Trees","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Randall Balestriero","submitted_at":"2017-02-23T19:02:32Z","abstract_excerpt":"In this paper we propose a synergistic melting of neural networks and decision trees (DT) we call neural decision trees (NDT). NDT is an architecture a la decision tree where each splitting node is an independent multilayer perceptron allowing oblique decision functions or arbritrary nonlinear decision function if more than one layer is used. This way, each MLP can be seen as a node of the tree. We then show that with the weight sharing asumption among those units, we end up with a Hashing Neural Network (HNN) which is a multilayer perceptron with sigmoid activation function for the last layer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07360","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":""},"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":"1702.07360","created_at":"2026-05-18T00:49:31.344164+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.07360v2","created_at":"2026-05-18T00:49:31.344164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07360","created_at":"2026-05-18T00:49:31.344164+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZR63OTFURKGU","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZR63OTFURKGU7WOZ","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZR63OTFU","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.21677","citing_title":"Prophecy: Inferring Formal Properties from Neuron Activations","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZR63OTFURKGU7WOZHZTKN3LW22","json":"https://pith.science/pith/ZR63OTFURKGU7WOZHZTKN3LW22.json","graph_json":"https://pith.science/api/pith-number/ZR63OTFURKGU7WOZHZTKN3LW22/graph.json","events_json":"https://pith.science/api/pith-number/ZR63OTFURKGU7WOZHZTKN3LW22/events.json","paper":"https://pith.science/paper/ZR63OTFU"},"agent_actions":{"view_html":"https://pith.science/pith/ZR63OTFURKGU7WOZHZTKN3LW22","download_json":"https://pith.science/pith/ZR63OTFURKGU7WOZHZTKN3LW22.json","view_paper":"https://pith.science/paper/ZR63OTFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.07360&json=true","fetch_graph":"https://pith.science/api/pith-number/ZR63OTFURKGU7WOZHZTKN3LW22/graph.json","fetch_events":"https://pith.science/api/pith-number/ZR63OTFURKGU7WOZHZTKN3LW22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZR63OTFURKGU7WOZHZTKN3LW22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZR63OTFURKGU7WOZHZTKN3LW22/action/storage_attestation","attest_author":"https://pith.science/pith/ZR63OTFURKGU7WOZHZTKN3LW22/action/author_attestation","sign_citation":"https://pith.science/pith/ZR63OTFURKGU7WOZHZTKN3LW22/action/citation_signature","submit_replication":"https://pith.science/pith/ZR63OTFURKGU7WOZHZTKN3LW22/action/replication_record"}},"created_at":"2026-05-18T00:49:31.344164+00:00","updated_at":"2026-05-18T00:49:31.344164+00:00"}