{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:7RDKWPW2H27INKZMHYEFJPNPRK","short_pith_number":"pith:7RDKWPW2","schema_version":"1.0","canonical_sha256":"fc46ab3eda3ebe86ab2c3e0854bdaf8a98b0142ff965b308a79a7ceff6414c07","source":{"kind":"arxiv","id":"1301.2295","version":1},"attestation_state":"computed","paper":{"title":"Recognition Networks for Approximate Inference in BN20 Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Quaid Morris","submitted_at":"2013-01-10T16:25:25Z","abstract_excerpt":"We propose using recognition networks for approximate inference inBayesian networks (BNs).  A recognition network is a multilayerperception (MLP) trained to predict posterior marginals given observedevidence in a particular BN.  The input to the MLP is a vector of thestates of the evidential nodes.  The activity of an output unit isinterpreted as a prediction of the posterior marginal of thecorresponding variable.  The MLP is trained using samples generated fromthe corresponding BN.We evaluate a recognition network that was trained to do inference ina large Bayesian network, similar in structu"},"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":"1301.2295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-10T16:25:25Z","cross_cats_sorted":[],"title_canon_sha256":"bf422a42af18abac56bc515b5b952efe83833cb53c58d26fa29719a833a271b4","abstract_canon_sha256":"8136a5c8f8d3357c9665ea7f5ff5f2fbc4d7f2e1710817f45c52209cf9a61304"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:36:45.508219Z","signature_b64":"P33FyVeIB5HC+O8jUvEeWnVMXqWKNWzhsCPo+/2/UlYE7Dosth9ElyMWvR6Ws6cdYMek/PiFj12X74lQmH1QBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc46ab3eda3ebe86ab2c3e0854bdaf8a98b0142ff965b308a79a7ceff6414c07","last_reissued_at":"2026-05-18T03:36:45.507647Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:36:45.507647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recognition Networks for Approximate Inference in BN20 Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Quaid Morris","submitted_at":"2013-01-10T16:25:25Z","abstract_excerpt":"We propose using recognition networks for approximate inference inBayesian networks (BNs).  A recognition network is a multilayerperception (MLP) trained to predict posterior marginals given observedevidence in a particular BN.  The input to the MLP is a vector of thestates of the evidential nodes.  The activity of an output unit isinterpreted as a prediction of the posterior marginal of thecorresponding variable.  The MLP is trained using samples generated fromthe corresponding BN.We evaluate a recognition network that was trained to do inference ina large Bayesian network, similar in structu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.2295","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":"1301.2295","created_at":"2026-05-18T03:36:45.507716+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.2295v1","created_at":"2026-05-18T03:36:45.507716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.2295","created_at":"2026-05-18T03:36:45.507716+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RDKWPW2H27I","created_at":"2026-05-18T12:27:36.564083+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RDKWPW2H27INKZM","created_at":"2026-05-18T12:27:36.564083+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RDKWPW2","created_at":"2026-05-18T12:27:36.564083+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/7RDKWPW2H27INKZMHYEFJPNPRK","json":"https://pith.science/pith/7RDKWPW2H27INKZMHYEFJPNPRK.json","graph_json":"https://pith.science/api/pith-number/7RDKWPW2H27INKZMHYEFJPNPRK/graph.json","events_json":"https://pith.science/api/pith-number/7RDKWPW2H27INKZMHYEFJPNPRK/events.json","paper":"https://pith.science/paper/7RDKWPW2"},"agent_actions":{"view_html":"https://pith.science/pith/7RDKWPW2H27INKZMHYEFJPNPRK","download_json":"https://pith.science/pith/7RDKWPW2H27INKZMHYEFJPNPRK.json","view_paper":"https://pith.science/paper/7RDKWPW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.2295&json=true","fetch_graph":"https://pith.science/api/pith-number/7RDKWPW2H27INKZMHYEFJPNPRK/graph.json","fetch_events":"https://pith.science/api/pith-number/7RDKWPW2H27INKZMHYEFJPNPRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RDKWPW2H27INKZMHYEFJPNPRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RDKWPW2H27INKZMHYEFJPNPRK/action/storage_attestation","attest_author":"https://pith.science/pith/7RDKWPW2H27INKZMHYEFJPNPRK/action/author_attestation","sign_citation":"https://pith.science/pith/7RDKWPW2H27INKZMHYEFJPNPRK/action/citation_signature","submit_replication":"https://pith.science/pith/7RDKWPW2H27INKZMHYEFJPNPRK/action/replication_record"}},"created_at":"2026-05-18T03:36:45.507716+00:00","updated_at":"2026-05-18T03:36:45.507716+00:00"}