{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CBKWNLIAXB76E3LMOAAGWMRD4F","short_pith_number":"pith:CBKWNLIA","schema_version":"1.0","canonical_sha256":"105566ad00b87fe26d6c70006b3223e1467ad66e644965fa1e3d0075e6f4f4dd","source":{"kind":"arxiv","id":"1711.09784","version":1},"attestation_state":"computed","paper":{"title":"Distilling a Neural Network Into a Soft Decision Tree","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Geoffrey Hinton, Nicholas Frosst","submitted_at":"2017-11-27T15:50:50Z","abstract_excerpt":"Deep neural networks have proved to be a very effective way to perform classification tasks. They excel when the input data is high dimensional, the relationship between the input and the output is complicated, and the number of labeled training examples is large. But it is hard to explain why a learned network makes a particular classification decision on a particular test case. This is due to their reliance on distributed hierarchical representations. If we could take the knowledge acquired by the neural net and express the same knowledge in a model that relies on hierarchical decisions inst"},"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":"1711.09784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-27T15:50:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4c34c7b2641c73f82a00daa03224a088334c6c8426d30e0a5376599e8e2a4466","abstract_canon_sha256":"b98f7af4c1cd485cdce1a313d6a14b92747a4995d2300b05407f758676248aa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:34.474810Z","signature_b64":"5HUQ84DQyHPdbyG4CHwJJk8h9/NdijZKxDNE/c/MVHshQmyTfezk6sIIW67AezBFVqa7ZBaauoaXsZS8yPGVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"105566ad00b87fe26d6c70006b3223e1467ad66e644965fa1e3d0075e6f4f4dd","last_reissued_at":"2026-05-18T00:29:34.474210Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:34.474210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling a Neural Network Into a Soft Decision Tree","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Geoffrey Hinton, Nicholas Frosst","submitted_at":"2017-11-27T15:50:50Z","abstract_excerpt":"Deep neural networks have proved to be a very effective way to perform classification tasks. They excel when the input data is high dimensional, the relationship between the input and the output is complicated, and the number of labeled training examples is large. But it is hard to explain why a learned network makes a particular classification decision on a particular test case. This is due to their reliance on distributed hierarchical representations. If we could take the knowledge acquired by the neural net and express the same knowledge in a model that relies on hierarchical decisions inst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09784","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":""},"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":"1711.09784","created_at":"2026-05-18T00:29:34.474329+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.09784v1","created_at":"2026-05-18T00:29:34.474329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09784","created_at":"2026-05-18T00:29:34.474329+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBKWNLIAXB76","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBKWNLIAXB76E3LM","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBKWNLIA","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2411.12173","citing_title":"SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06374","citing_title":"What does it mean to understand a neural network?","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22740","citing_title":"Ternary Decision Trees with Locally-Adaptive Uncertainty Zones","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19299","citing_title":"Cross-Paradigm Knowledge Distillation: A Comprehensive Study of Bidirectional Transfer Between Random Forests and Deep Neural Networks for Big Data Applications","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21166","citing_title":"The Ratchet Effect in Silico through Interaction-Driven Cumulative Intelligence in Large Language Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2509.21677","citing_title":"Prophecy: Inferring Formal Properties from Neuron Activations","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14280","citing_title":"TILT: Target-induced loss tilting under covariate shift","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11841","citing_title":"Minimax Rates and Spectral Distillation for Tree Ensembles","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25315","citing_title":"SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07837","citing_title":"Approximation-Free Differentiable Oblique Decision Trees","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBKWNLIAXB76E3LMOAAGWMRD4F","json":"https://pith.science/pith/CBKWNLIAXB76E3LMOAAGWMRD4F.json","graph_json":"https://pith.science/api/pith-number/CBKWNLIAXB76E3LMOAAGWMRD4F/graph.json","events_json":"https://pith.science/api/pith-number/CBKWNLIAXB76E3LMOAAGWMRD4F/events.json","paper":"https://pith.science/paper/CBKWNLIA"},"agent_actions":{"view_html":"https://pith.science/pith/CBKWNLIAXB76E3LMOAAGWMRD4F","download_json":"https://pith.science/pith/CBKWNLIAXB76E3LMOAAGWMRD4F.json","view_paper":"https://pith.science/paper/CBKWNLIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.09784&json=true","fetch_graph":"https://pith.science/api/pith-number/CBKWNLIAXB76E3LMOAAGWMRD4F/graph.json","fetch_events":"https://pith.science/api/pith-number/CBKWNLIAXB76E3LMOAAGWMRD4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBKWNLIAXB76E3LMOAAGWMRD4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBKWNLIAXB76E3LMOAAGWMRD4F/action/storage_attestation","attest_author":"https://pith.science/pith/CBKWNLIAXB76E3LMOAAGWMRD4F/action/author_attestation","sign_citation":"https://pith.science/pith/CBKWNLIAXB76E3LMOAAGWMRD4F/action/citation_signature","submit_replication":"https://pith.science/pith/CBKWNLIAXB76E3LMOAAGWMRD4F/action/replication_record"}},"created_at":"2026-05-18T00:29:34.474329+00:00","updated_at":"2026-05-18T00:29:34.474329+00:00"}