{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UNMAHSVCIRGUQ7C2SOS24GRS7V","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ec6128a417783d167e0d1c7e82e4c2cbc5d4fad204a6b23f430f9df20b717f9a","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-02T17:43:19Z","title_canon_sha256":"37332a69aad95f2200a2460b7995d5047565b0b0f4de55f88d1da98f2cd41548"},"schema_version":"1.0","source":{"id":"1703.00868","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.00868","created_at":"2026-05-18T00:49:40Z"},{"alias_kind":"arxiv_version","alias_value":"1703.00868v1","created_at":"2026-05-18T00:49:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00868","created_at":"2026-05-18T00:49:40Z"},{"alias_kind":"pith_short_12","alias_value":"UNMAHSVCIRGU","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UNMAHSVCIRGUQ7C2","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UNMAHSVC","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:f53dbb35903897891f3e266cf620a2fa459e6c73e4108abeff6b489cedb5165d","target":"graph","created_at":"2026-05-18T00:49:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We draw a formal connection between using synthetic training data to optimize neural network parameters and approximate, Bayesian, model-based reasoning. In particular, training a neural network using synthetic data can be viewed as learning a proposal distribution generator for approximate inference in the synthetic-data generative model. We demonstrate this connection in a recognition task where we develop a novel Captcha-breaking architecture and train it using synthetic data, demonstrating both state-of-the-art performance and a way of computing task-specific posterior uncertainty. Using a","authors_text":"Atilim Gunes Baydin, Frank Wood, Robert Zinkov, Tuan Anh Le","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-02T17:43:19Z","title":"Using Synthetic Data to Train Neural Networks is Model-Based Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00868","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4f69768d1269b041db9d6b31a7f367375f72879b947f9cf2af371e2cffc474d6","target":"record","created_at":"2026-05-18T00:49:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ec6128a417783d167e0d1c7e82e4c2cbc5d4fad204a6b23f430f9df20b717f9a","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-02T17:43:19Z","title_canon_sha256":"37332a69aad95f2200a2460b7995d5047565b0b0f4de55f88d1da98f2cd41548"},"schema_version":"1.0","source":{"id":"1703.00868","kind":"arxiv","version":1}},"canonical_sha256":"a35803caa2444d487c5a93a5ae1a32fd4db1856991430f8a710427a4eb1849da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a35803caa2444d487c5a93a5ae1a32fd4db1856991430f8a710427a4eb1849da","first_computed_at":"2026-05-18T00:49:40.590517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:40.590517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lNTP+G1yXhMF8PJs/XLEJ5Q0/dv9JtUhO0qs7OV8Uzo/mykpCwlIkpJP/0hyVCaTMocwgjkBL5UgbzD/vfhDCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:40.591366Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.00868","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f69768d1269b041db9d6b31a7f367375f72879b947f9cf2af371e2cffc474d6","sha256:f53dbb35903897891f3e266cf620a2fa459e6c73e4108abeff6b489cedb5165d"],"state_sha256":"20ec4ee00a3c5c241117415ea9dcd219352866a58ce9684de862d42158000791"}