{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MGKAMMBF6UPHM6FQ5BG6GPJSC5","short_pith_number":"pith:MGKAMMBF","canonical_record":{"source":{"id":"1806.06988","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T00:05:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d1caf150c86314cbb687a15b6d9f87f3a78703c897b0e5c93b75879b0a41e507","abstract_canon_sha256":"00d50835d5f78779b6c2c4635af9849d297ff3f234d65111cd435d3d949d2343"},"schema_version":"1.0"},"canonical_sha256":"6194063025f51e7678b0e84de33d321775bf5f9d31981b300107ceccd4598465","source":{"kind":"arxiv","id":"1806.06988","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06988","created_at":"2026-05-18T00:12:57Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06988v1","created_at":"2026-05-18T00:12:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06988","created_at":"2026-05-18T00:12:57Z"},{"alias_kind":"pith_short_12","alias_value":"MGKAMMBF6UPH","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MGKAMMBF6UPHM6FQ","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MGKAMMBF","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MGKAMMBF6UPHM6FQ5BG6GPJSC5","target":"record","payload":{"canonical_record":{"source":{"id":"1806.06988","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T00:05:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d1caf150c86314cbb687a15b6d9f87f3a78703c897b0e5c93b75879b0a41e507","abstract_canon_sha256":"00d50835d5f78779b6c2c4635af9849d297ff3f234d65111cd435d3d949d2343"},"schema_version":"1.0"},"canonical_sha256":"6194063025f51e7678b0e84de33d321775bf5f9d31981b300107ceccd4598465","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:57.843966Z","signature_b64":"UStcRsh9fasn54d5BPNhXCX+0+dLg/T32NGhwbqYy3SD/E+A1AYatm8eUnIcLmGAss7L47HTWUHXUriGNRmzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6194063025f51e7678b0e84de33d321775bf5f9d31981b300107ceccd4598465","last_reissued_at":"2026-05-18T00:12:57.843350Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:57.843350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.06988","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:12:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EB9Tup2O884oqpk9/RbkcxV/tqfZzoSq/irWXK5hMyPNkfNDWLrgxB3Ky6+2R9DmKLeKOCK9YHNG6mqhQmCIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:40:46.457037Z"},"content_sha256":"d3b86f824f8bb0d5fbc8f7f82017fcbe58ab7b081399e16658be4eff7c78d105","schema_version":"1.0","event_id":"sha256:d3b86f824f8bb0d5fbc8f7f82017fcbe58ab7b081399e16658be4eff7c78d105"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MGKAMMBF6UPHM6FQ5BG6GPJSC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Neural Decision Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Irene Garcia Morillo, Timothy M. Hospedales, Yongxin Yang","submitted_at":"2018-06-19T00:05:20Z","abstract_excerpt":"Deep neural networks have been proven powerful at processing perceptual data, such as images and audio. However for tabular data, tree-based models are more popular. A nice property of tree-based models is their natural interpretability. In this work, we present Deep Neural Decision Trees (DNDT) -- tree models realised by neural networks. A DNDT is intrinsically interpretable, as it is a tree. Yet as it is also a neural network (NN), it can be easily implemented in NN toolkits, and trained with gradient descent rather than greedy splitting. We evaluate DNDT on several tabular datasets, verify "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06988","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:12:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P9RfQs+q+JLC+03JD/DGi5faDjIyDad2mmQi3QdTI+rLH6TGXVe9k2g35j14hTeabR4azf4I3r8526PM5aGKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:40:46.457712Z"},"content_sha256":"9f04c542e6c565bb25a7d32f3709908ecfc2cb6ccc5bddd755807d2879744614","schema_version":"1.0","event_id":"sha256:9f04c542e6c565bb25a7d32f3709908ecfc2cb6ccc5bddd755807d2879744614"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MGKAMMBF6UPHM6FQ5BG6GPJSC5/bundle.json","state_url":"https://pith.science/pith/MGKAMMBF6UPHM6FQ5BG6GPJSC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MGKAMMBF6UPHM6FQ5BG6GPJSC5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T11:40:46Z","links":{"resolver":"https://pith.science/pith/MGKAMMBF6UPHM6FQ5BG6GPJSC5","bundle":"https://pith.science/pith/MGKAMMBF6UPHM6FQ5BG6GPJSC5/bundle.json","state":"https://pith.science/pith/MGKAMMBF6UPHM6FQ5BG6GPJSC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MGKAMMBF6UPHM6FQ5BG6GPJSC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MGKAMMBF6UPHM6FQ5BG6GPJSC5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"00d50835d5f78779b6c2c4635af9849d297ff3f234d65111cd435d3d949d2343","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T00:05:20Z","title_canon_sha256":"d1caf150c86314cbb687a15b6d9f87f3a78703c897b0e5c93b75879b0a41e507"},"schema_version":"1.0","source":{"id":"1806.06988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06988","created_at":"2026-05-18T00:12:57Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06988v1","created_at":"2026-05-18T00:12:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06988","created_at":"2026-05-18T00:12:57Z"},{"alias_kind":"pith_short_12","alias_value":"MGKAMMBF6UPH","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MGKAMMBF6UPHM6FQ","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MGKAMMBF","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:9f04c542e6c565bb25a7d32f3709908ecfc2cb6ccc5bddd755807d2879744614","target":"graph","created_at":"2026-05-18T00:12:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Deep neural networks have been proven powerful at processing perceptual data, such as images and audio. However for tabular data, tree-based models are more popular. A nice property of tree-based models is their natural interpretability. In this work, we present Deep Neural Decision Trees (DNDT) -- tree models realised by neural networks. A DNDT is intrinsically interpretable, as it is a tree. Yet as it is also a neural network (NN), it can be easily implemented in NN toolkits, and trained with gradient descent rather than greedy splitting. We evaluate DNDT on several tabular datasets, verify ","authors_text":"Irene Garcia Morillo, Timothy M. Hospedales, Yongxin Yang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T00:05:20Z","title":"Deep Neural Decision Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06988","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d3b86f824f8bb0d5fbc8f7f82017fcbe58ab7b081399e16658be4eff7c78d105","target":"record","created_at":"2026-05-18T00:12:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"00d50835d5f78779b6c2c4635af9849d297ff3f234d65111cd435d3d949d2343","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T00:05:20Z","title_canon_sha256":"d1caf150c86314cbb687a15b6d9f87f3a78703c897b0e5c93b75879b0a41e507"},"schema_version":"1.0","source":{"id":"1806.06988","kind":"arxiv","version":1}},"canonical_sha256":"6194063025f51e7678b0e84de33d321775bf5f9d31981b300107ceccd4598465","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6194063025f51e7678b0e84de33d321775bf5f9d31981b300107ceccd4598465","first_computed_at":"2026-05-18T00:12:57.843350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:57.843350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UStcRsh9fasn54d5BPNhXCX+0+dLg/T32NGhwbqYy3SD/E+A1AYatm8eUnIcLmGAss7L47HTWUHXUriGNRmzDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:57.843966Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.06988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3b86f824f8bb0d5fbc8f7f82017fcbe58ab7b081399e16658be4eff7c78d105","sha256:9f04c542e6c565bb25a7d32f3709908ecfc2cb6ccc5bddd755807d2879744614"],"state_sha256":"02b2b1d01662e1fc089fcd965bfe6eb89832e8dd81b9d95b774359dfdf49f271"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kyMNvyhtHKfhbBjV68NCEEXParH6jNfdl5O0eliD1cdqkx4m2YiONjt7tIHVaMnXy71cUH+gUoWVOQcC5ZktBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T11:40:46.461291Z","bundle_sha256":"f7c2c951cb752c37dd842e0ec0469d148a8c65f6580c453f3f2c1332c5f19033"}}