{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UD2Y6HMR42QHEZORNLQRBS7QNA","short_pith_number":"pith:UD2Y6HMR","schema_version":"1.0","canonical_sha256":"a0f58f1d91e6a07265d16ae110cbf0680512eb7f9b81685da3fcec3bc1e370a5","source":{"kind":"arxiv","id":"1802.05680","version":2},"attestation_state":"computed","paper":{"title":"Constraining the Dynamics of Deep Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Marco Lorenzi, Maurizio Filippone","submitted_at":"2018-02-15T17:54:08Z","abstract_excerpt":"We introduce a novel generative formulation of deep probabilistic models implementing \"soft\" constraints on their function dynamics. In particular, we develop a flexible methodological framework where the modeled functions and derivatives of a given order are subject to inequality or equality constraints. We then characterize the posterior distribution over model and constraint parameters through stochastic variational inference. As a result, the proposed approach allows for accurate and scalable uncertainty quantification on the predictions and on all parameters. We demonstrate the applicatio"},"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":"1802.05680","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-15T17:54:08Z","cross_cats_sorted":[],"title_canon_sha256":"867a979f72c4f4f4538110113ae13c7a6b5b1adc992dc97244d06063e4f3d855","abstract_canon_sha256":"f582f8c7f90348ffe72f5caedaab8940c2fec5ef948a783d0b344f00f5aff03d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:04.648590Z","signature_b64":"mocmqZ2AsANVj0Ppk0xxrq2P2j+5Zttsx4EXtvxFtlo7X9p2dhK9Ebxhwnxtou8EjcFPgSTiXOLD++jKitpADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f58f1d91e6a07265d16ae110cbf0680512eb7f9b81685da3fcec3bc1e370a5","last_reissued_at":"2026-05-18T00:13:04.647724Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:04.647724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constraining the Dynamics of Deep Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Marco Lorenzi, Maurizio Filippone","submitted_at":"2018-02-15T17:54:08Z","abstract_excerpt":"We introduce a novel generative formulation of deep probabilistic models implementing \"soft\" constraints on their function dynamics. In particular, we develop a flexible methodological framework where the modeled functions and derivatives of a given order are subject to inequality or equality constraints. We then characterize the posterior distribution over model and constraint parameters through stochastic variational inference. As a result, the proposed approach allows for accurate and scalable uncertainty quantification on the predictions and on all parameters. We demonstrate the applicatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05680","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":""},"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":"1802.05680","created_at":"2026-05-18T00:13:04.647889+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05680v2","created_at":"2026-05-18T00:13:04.647889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05680","created_at":"2026-05-18T00:13:04.647889+00:00"},{"alias_kind":"pith_short_12","alias_value":"UD2Y6HMR42QH","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UD2Y6HMR42QHEZOR","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UD2Y6HMR","created_at":"2026-05-18T12:32:56.356000+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/UD2Y6HMR42QHEZORNLQRBS7QNA","json":"https://pith.science/pith/UD2Y6HMR42QHEZORNLQRBS7QNA.json","graph_json":"https://pith.science/api/pith-number/UD2Y6HMR42QHEZORNLQRBS7QNA/graph.json","events_json":"https://pith.science/api/pith-number/UD2Y6HMR42QHEZORNLQRBS7QNA/events.json","paper":"https://pith.science/paper/UD2Y6HMR"},"agent_actions":{"view_html":"https://pith.science/pith/UD2Y6HMR42QHEZORNLQRBS7QNA","download_json":"https://pith.science/pith/UD2Y6HMR42QHEZORNLQRBS7QNA.json","view_paper":"https://pith.science/paper/UD2Y6HMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05680&json=true","fetch_graph":"https://pith.science/api/pith-number/UD2Y6HMR42QHEZORNLQRBS7QNA/graph.json","fetch_events":"https://pith.science/api/pith-number/UD2Y6HMR42QHEZORNLQRBS7QNA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UD2Y6HMR42QHEZORNLQRBS7QNA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UD2Y6HMR42QHEZORNLQRBS7QNA/action/storage_attestation","attest_author":"https://pith.science/pith/UD2Y6HMR42QHEZORNLQRBS7QNA/action/author_attestation","sign_citation":"https://pith.science/pith/UD2Y6HMR42QHEZORNLQRBS7QNA/action/citation_signature","submit_replication":"https://pith.science/pith/UD2Y6HMR42QHEZORNLQRBS7QNA/action/replication_record"}},"created_at":"2026-05-18T00:13:04.647889+00:00","updated_at":"2026-05-18T00:13:04.647889+00:00"}