{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:YWTCORK7REGCXOP33QEYE2YYEM","short_pith_number":"pith:YWTCORK7","schema_version":"1.0","canonical_sha256":"c5a627455f890c2bb9fbdc09826b18230e6b38e48208900ec880a44ed7e4d5d8","source":{"kind":"arxiv","id":"1302.3931","version":7},"attestation_state":"computed","paper":{"title":"Understanding Boltzmann Machine and Deep Learning via A Confident Information First Principle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Dawei Song, Qian Yu, Wenjie Li, Xiaozhao Zhao, Yuexian Hou","submitted_at":"2013-02-16T05:49:15Z","abstract_excerpt":"Typical dimensionality reduction methods focus on directly reducing the number of random variables while retaining maximal variations in the data. In this paper, we consider the dimensionality reduction in parameter spaces of binary multivariate distributions. We propose a general Confident-Information-First (CIF) principle to maximally preserve parameters with confident estimates and rule out unreliable or noisy parameters. Formally, the confidence of a parameter can be assessed by its Fisher information, which establishes a connection with the inverse variance of any unbiased estimate for th"},"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":"1302.3931","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2013-02-16T05:49:15Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d42b30ea26a6df8299dfe815d76c7873d992ee1055f47c1a2badc7df37f37941","abstract_canon_sha256":"bd01507aa2b1e983c6168740d74a030d06c310a7925d40e9740ee8c6776738c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:58.202715Z","signature_b64":"r0Musbon4V2qofdD2Tco2gPsCYqJcPTDerxTXICd0sM1VepjS9aXDQ1l883MKQeNd8SRlhWHoBR5lXTIWJPzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5a627455f890c2bb9fbdc09826b18230e6b38e48208900ec880a44ed7e4d5d8","last_reissued_at":"2026-05-18T03:10:58.201932Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:58.201932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Boltzmann Machine and Deep Learning via A Confident Information First Principle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Dawei Song, Qian Yu, Wenjie Li, Xiaozhao Zhao, Yuexian Hou","submitted_at":"2013-02-16T05:49:15Z","abstract_excerpt":"Typical dimensionality reduction methods focus on directly reducing the number of random variables while retaining maximal variations in the data. In this paper, we consider the dimensionality reduction in parameter spaces of binary multivariate distributions. We propose a general Confident-Information-First (CIF) principle to maximally preserve parameters with confident estimates and rule out unreliable or noisy parameters. Formally, the confidence of a parameter can be assessed by its Fisher information, which establishes a connection with the inverse variance of any unbiased estimate for th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1302.3931","kind":"arxiv","version":7},"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":"1302.3931","created_at":"2026-05-18T03:10:58.202059+00:00"},{"alias_kind":"arxiv_version","alias_value":"1302.3931v7","created_at":"2026-05-18T03:10:58.202059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1302.3931","created_at":"2026-05-18T03:10:58.202059+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWTCORK7REGC","created_at":"2026-05-18T12:28:09.283467+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWTCORK7REGCXOP3","created_at":"2026-05-18T12:28:09.283467+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWTCORK7","created_at":"2026-05-18T12:28:09.283467+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/YWTCORK7REGCXOP33QEYE2YYEM","json":"https://pith.science/pith/YWTCORK7REGCXOP33QEYE2YYEM.json","graph_json":"https://pith.science/api/pith-number/YWTCORK7REGCXOP33QEYE2YYEM/graph.json","events_json":"https://pith.science/api/pith-number/YWTCORK7REGCXOP33QEYE2YYEM/events.json","paper":"https://pith.science/paper/YWTCORK7"},"agent_actions":{"view_html":"https://pith.science/pith/YWTCORK7REGCXOP33QEYE2YYEM","download_json":"https://pith.science/pith/YWTCORK7REGCXOP33QEYE2YYEM.json","view_paper":"https://pith.science/paper/YWTCORK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1302.3931&json=true","fetch_graph":"https://pith.science/api/pith-number/YWTCORK7REGCXOP33QEYE2YYEM/graph.json","fetch_events":"https://pith.science/api/pith-number/YWTCORK7REGCXOP33QEYE2YYEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWTCORK7REGCXOP33QEYE2YYEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWTCORK7REGCXOP33QEYE2YYEM/action/storage_attestation","attest_author":"https://pith.science/pith/YWTCORK7REGCXOP33QEYE2YYEM/action/author_attestation","sign_citation":"https://pith.science/pith/YWTCORK7REGCXOP33QEYE2YYEM/action/citation_signature","submit_replication":"https://pith.science/pith/YWTCORK7REGCXOP33QEYE2YYEM/action/replication_record"}},"created_at":"2026-05-18T03:10:58.202059+00:00","updated_at":"2026-05-18T03:10:58.202059+00:00"}