{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AAVPQNHDD4CBGDUVJM63QFXQMJ","short_pith_number":"pith:AAVPQNHD","schema_version":"1.0","canonical_sha256":"002af834e31f04130e954b3db816f06248bfeda55e01426cec1364e62c3a44fc","source":{"kind":"arxiv","id":"1905.13195","version":2},"attestation_state":"computed","paper":{"title":"Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Gal Novik, Raanan Y. Rohekar, Shami Nisimov, Yaniv Gurwicz","submitted_at":"2019-05-30T17:36:19Z","abstract_excerpt":"Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal distribution or other distribution encouraging sparsity. However, this prior is agnostic to the generative process of the input data, which might lead to unwarranted generalization for out-of-distribution tested data. We suggest the presence of a confounder for the relation between the input data and the discriminative function given the target label. We propose an app"},"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":"1905.13195","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2019-05-30T17:36:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8290947fe018cad1cafbb2f25fe84c44f451d7af6a3e53bf255ffe989d209b93","abstract_canon_sha256":"9b74ae98dd3fe06f52c8c36983e6b28328d555e98113931e5aff3984139afcaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:05.752259Z","signature_b64":"ktDy5D9Eo8l0TjuInA1UXaKsWrkvy2zUOLEikYbT8jR+8g2RGEEQE+RPmQtGTv4wTkSd9fpA2x4D5R+IqIBbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"002af834e31f04130e954b3db816f06248bfeda55e01426cec1364e62c3a44fc","last_reissued_at":"2026-07-05T00:15:05.751800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:05.751800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Gal Novik, Raanan Y. Rohekar, Shami Nisimov, Yaniv Gurwicz","submitted_at":"2019-05-30T17:36:19Z","abstract_excerpt":"Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal distribution or other distribution encouraging sparsity. However, this prior is agnostic to the generative process of the input data, which might lead to unwarranted generalization for out-of-distribution tested data. We suggest the presence of a confounder for the relation between the input data and the discriminative function given the target label. We propose an app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13195","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.13195/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1905.13195","created_at":"2026-07-05T00:15:05.751858+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13195v2","created_at":"2026-07-05T00:15:05.751858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13195","created_at":"2026-07-05T00:15:05.751858+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAVPQNHDD4CB","created_at":"2026-07-05T00:15:05.751858+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAVPQNHDD4CBGDUV","created_at":"2026-07-05T00:15:05.751858+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAVPQNHD","created_at":"2026-07-05T00:15:05.751858+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/AAVPQNHDD4CBGDUVJM63QFXQMJ","json":"https://pith.science/pith/AAVPQNHDD4CBGDUVJM63QFXQMJ.json","graph_json":"https://pith.science/api/pith-number/AAVPQNHDD4CBGDUVJM63QFXQMJ/graph.json","events_json":"https://pith.science/api/pith-number/AAVPQNHDD4CBGDUVJM63QFXQMJ/events.json","paper":"https://pith.science/paper/AAVPQNHD"},"agent_actions":{"view_html":"https://pith.science/pith/AAVPQNHDD4CBGDUVJM63QFXQMJ","download_json":"https://pith.science/pith/AAVPQNHDD4CBGDUVJM63QFXQMJ.json","view_paper":"https://pith.science/paper/AAVPQNHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13195&json=true","fetch_graph":"https://pith.science/api/pith-number/AAVPQNHDD4CBGDUVJM63QFXQMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AAVPQNHDD4CBGDUVJM63QFXQMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAVPQNHDD4CBGDUVJM63QFXQMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAVPQNHDD4CBGDUVJM63QFXQMJ/action/storage_attestation","attest_author":"https://pith.science/pith/AAVPQNHDD4CBGDUVJM63QFXQMJ/action/author_attestation","sign_citation":"https://pith.science/pith/AAVPQNHDD4CBGDUVJM63QFXQMJ/action/citation_signature","submit_replication":"https://pith.science/pith/AAVPQNHDD4CBGDUVJM63QFXQMJ/action/replication_record"}},"created_at":"2026-07-05T00:15:05.751858+00:00","updated_at":"2026-07-05T00:15:05.751858+00:00"}