{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:D56N6ON7Q6ZYZCF3JV5C3D23CY","short_pith_number":"pith:D56N6ON7","schema_version":"1.0","canonical_sha256":"1f7cdf39bf87b38c88bb4d7a2d8f5b163ddadb064a0d8dc8f417e9d4c1f8a309","source":{"kind":"arxiv","id":"1511.05622","version":4},"attestation_state":"computed","paper":{"title":"Predicting distributions with Linearizing Belief Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"David Grangier, Yann N. Dauphin","submitted_at":"2015-11-17T23:50:35Z","abstract_excerpt":"Conditional belief networks introduce stochastic binary variables in neural networks. Contrary to a classical neural network, a belief network can predict more than the expected value of the output $Y$ given the input $X$. It can predict a distribution of outputs $Y$ which is useful when an input can admit multiple outputs whose average is not necessarily a valid answer. Such networks are particularly relevant to inverse problems such as image prediction for denoising, or text to speech. However, traditional sigmoid belief networks are hard to train and are not suited to continuous problems. T"},"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":"1511.05622","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-17T23:50:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fa20a4c64303d09a7ccf4dca82c499bcb4278701ad555efe0696cab03c807b2a","abstract_canon_sha256":"c7e38f1f932619f68eb28c0294aef64908c0954be0dbb3400bbff2aa5538eae1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:57.949479Z","signature_b64":"YV2IfmljvkqOzuKm/dN+zW7HpFyN/2uHbyppf8v//5+NcbTcZS2DyrC/JS1Rz/KtHDHv04/vn4vjv0xdHFqPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f7cdf39bf87b38c88bb4d7a2d8f5b163ddadb064a0d8dc8f417e9d4c1f8a309","last_reissued_at":"2026-05-18T01:15:57.948841Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:57.948841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting distributions with Linearizing Belief Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"David Grangier, Yann N. Dauphin","submitted_at":"2015-11-17T23:50:35Z","abstract_excerpt":"Conditional belief networks introduce stochastic binary variables in neural networks. Contrary to a classical neural network, a belief network can predict more than the expected value of the output $Y$ given the input $X$. It can predict a distribution of outputs $Y$ which is useful when an input can admit multiple outputs whose average is not necessarily a valid answer. Such networks are particularly relevant to inverse problems such as image prediction for denoising, or text to speech. However, traditional sigmoid belief networks are hard to train and are not suited to continuous problems. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05622","kind":"arxiv","version":4},"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":"1511.05622","created_at":"2026-05-18T01:15:57.948930+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.05622v4","created_at":"2026-05-18T01:15:57.948930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05622","created_at":"2026-05-18T01:15:57.948930+00:00"},{"alias_kind":"pith_short_12","alias_value":"D56N6ON7Q6ZY","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"D56N6ON7Q6ZYZCF3","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"D56N6ON7","created_at":"2026-05-18T12:29:17.054201+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/D56N6ON7Q6ZYZCF3JV5C3D23CY","json":"https://pith.science/pith/D56N6ON7Q6ZYZCF3JV5C3D23CY.json","graph_json":"https://pith.science/api/pith-number/D56N6ON7Q6ZYZCF3JV5C3D23CY/graph.json","events_json":"https://pith.science/api/pith-number/D56N6ON7Q6ZYZCF3JV5C3D23CY/events.json","paper":"https://pith.science/paper/D56N6ON7"},"agent_actions":{"view_html":"https://pith.science/pith/D56N6ON7Q6ZYZCF3JV5C3D23CY","download_json":"https://pith.science/pith/D56N6ON7Q6ZYZCF3JV5C3D23CY.json","view_paper":"https://pith.science/paper/D56N6ON7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.05622&json=true","fetch_graph":"https://pith.science/api/pith-number/D56N6ON7Q6ZYZCF3JV5C3D23CY/graph.json","fetch_events":"https://pith.science/api/pith-number/D56N6ON7Q6ZYZCF3JV5C3D23CY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D56N6ON7Q6ZYZCF3JV5C3D23CY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D56N6ON7Q6ZYZCF3JV5C3D23CY/action/storage_attestation","attest_author":"https://pith.science/pith/D56N6ON7Q6ZYZCF3JV5C3D23CY/action/author_attestation","sign_citation":"https://pith.science/pith/D56N6ON7Q6ZYZCF3JV5C3D23CY/action/citation_signature","submit_replication":"https://pith.science/pith/D56N6ON7Q6ZYZCF3JV5C3D23CY/action/replication_record"}},"created_at":"2026-05-18T01:15:57.948930+00:00","updated_at":"2026-05-18T01:15:57.948930+00:00"}