{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6AP7HGOVVS5ZXSR4BSED4GDVEE","short_pith_number":"pith:6AP7HGOV","schema_version":"1.0","canonical_sha256":"f01ff399d5acbb9bca3c0c883e1875210b6b21f0b3d28856dd719fefc1bbdda5","source":{"kind":"arxiv","id":"1812.00647","version":1},"attestation_state":"computed","paper":{"title":"Deep Hierarchical Machine: a Flexible Divide-and-Conquer Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Shichao Li, Tim Cheng, Xin Yang","submitted_at":"2018-12-03T10:34:01Z","abstract_excerpt":"We propose Deep Hierarchical Machine (DHM), a model inspired from the divide-and-conquer strategy while emphasizing representation learning ability and flexibility. A stochastic routing framework as used by recent deep neural decision/regression forests is incorporated, but we remove the need to evaluate unnecessary computation paths by utilizing a different topology and introducing a probabilistic pruning technique. We also show a specified version of DHM (DSHM) for efficiency, which inherits the sparse feature extraction process as in traditional decision tree with pixel-difference feature. "},"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":"1812.00647","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-03T10:34:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1ddac2583e804c2775c45885af6eebd74096ed89ae949299901fba70d953478f","abstract_canon_sha256":"2b0dfb3cc6c615ac1894117194de8ee3074b1b85a1c28c549861c320e12d2a43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:19.320683Z","signature_b64":"xf7ls4N/HxlMB6zLcDumVQ390lMdSj9S00KuVID5vI6O4R1LHDrtuWJzmeoX9IPTft/TIBgbLJMR5O3nuy8OAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f01ff399d5acbb9bca3c0c883e1875210b6b21f0b3d28856dd719fefc1bbdda5","last_reissued_at":"2026-05-17T23:59:19.320355Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:19.320355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Hierarchical Machine: a Flexible Divide-and-Conquer Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Shichao Li, Tim Cheng, Xin Yang","submitted_at":"2018-12-03T10:34:01Z","abstract_excerpt":"We propose Deep Hierarchical Machine (DHM), a model inspired from the divide-and-conquer strategy while emphasizing representation learning ability and flexibility. A stochastic routing framework as used by recent deep neural decision/regression forests is incorporated, but we remove the need to evaluate unnecessary computation paths by utilizing a different topology and introducing a probabilistic pruning technique. We also show a specified version of DHM (DSHM) for efficiency, which inherits the sparse feature extraction process as in traditional decision tree with pixel-difference feature. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00647","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":"1812.00647","created_at":"2026-05-17T23:59:19.320403+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.00647v1","created_at":"2026-05-17T23:59:19.320403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00647","created_at":"2026-05-17T23:59:19.320403+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AP7HGOVVS5Z","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AP7HGOVVS5ZXSR4","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AP7HGOV","created_at":"2026-05-18T12:32:08.215937+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/6AP7HGOVVS5ZXSR4BSED4GDVEE","json":"https://pith.science/pith/6AP7HGOVVS5ZXSR4BSED4GDVEE.json","graph_json":"https://pith.science/api/pith-number/6AP7HGOVVS5ZXSR4BSED4GDVEE/graph.json","events_json":"https://pith.science/api/pith-number/6AP7HGOVVS5ZXSR4BSED4GDVEE/events.json","paper":"https://pith.science/paper/6AP7HGOV"},"agent_actions":{"view_html":"https://pith.science/pith/6AP7HGOVVS5ZXSR4BSED4GDVEE","download_json":"https://pith.science/pith/6AP7HGOVVS5ZXSR4BSED4GDVEE.json","view_paper":"https://pith.science/paper/6AP7HGOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.00647&json=true","fetch_graph":"https://pith.science/api/pith-number/6AP7HGOVVS5ZXSR4BSED4GDVEE/graph.json","fetch_events":"https://pith.science/api/pith-number/6AP7HGOVVS5ZXSR4BSED4GDVEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AP7HGOVVS5ZXSR4BSED4GDVEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AP7HGOVVS5ZXSR4BSED4GDVEE/action/storage_attestation","attest_author":"https://pith.science/pith/6AP7HGOVVS5ZXSR4BSED4GDVEE/action/author_attestation","sign_citation":"https://pith.science/pith/6AP7HGOVVS5ZXSR4BSED4GDVEE/action/citation_signature","submit_replication":"https://pith.science/pith/6AP7HGOVVS5ZXSR4BSED4GDVEE/action/replication_record"}},"created_at":"2026-05-17T23:59:19.320403+00:00","updated_at":"2026-05-17T23:59:19.320403+00:00"}