{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:V7BDBH2M3PQWDJKKYSDZB3LVNK","short_pith_number":"pith:V7BDBH2M","canonical_record":{"source":{"id":"1611.01722","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-06T02:40:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"20df9c36212137e85bf7f44b6b9de32fb621fdfe44753382956c8ab8a4da5f39","abstract_canon_sha256":"ba784b8b7b82005e32b2c44397cda054f2465727ba4275be421a215cb74f4a06"},"schema_version":"1.0"},"canonical_sha256":"afc2309f4cdbe161a54ac48790ed756a94504a66cd3325b0d5b611288d022ed6","source":{"kind":"arxiv","id":"1611.01722","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01722","created_at":"2026-05-18T00:56:37Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01722v2","created_at":"2026-05-18T00:56:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01722","created_at":"2026-05-18T00:56:37Z"},{"alias_kind":"pith_short_12","alias_value":"V7BDBH2M3PQW","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"V7BDBH2M3PQWDJKK","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"V7BDBH2M","created_at":"2026-05-18T12:30:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:V7BDBH2M3PQWDJKKYSDZB3LVNK","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01722","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-06T02:40:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"20df9c36212137e85bf7f44b6b9de32fb621fdfe44753382956c8ab8a4da5f39","abstract_canon_sha256":"ba784b8b7b82005e32b2c44397cda054f2465727ba4275be421a215cb74f4a06"},"schema_version":"1.0"},"canonical_sha256":"afc2309f4cdbe161a54ac48790ed756a94504a66cd3325b0d5b611288d022ed6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:37.513206Z","signature_b64":"zjHSEp4+asxydoSZrCwxOapANZW1tL6dfrGkCTM6zMpARAbAqEL5K9w0aZwqZVJtt905U501/Pgy08f3GosRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afc2309f4cdbe161a54ac48790ed756a94504a66cd3325b0d5b611288d022ed6","last_reissued_at":"2026-05-18T00:56:37.512606Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:37.512606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01722","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:56:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ritSqQcUcCOu5T3ezcWCOycWdU8LQIhxKvN5t7uIK21KxptgcG9UGPj63rtGr5gFfZs+2u0PdWhAzupMbJqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:28:29.622966Z"},"content_sha256":"a847e8538fe071492399c9a87cb0ad73eb3a75694903c104912004f5148ad056","schema_version":"1.0","event_id":"sha256:a847e8538fe071492399c9a87cb0ad73eb3a75694903c104912004f5148ad056"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:V7BDBH2M3PQWDJKKYSDZB3LVNK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dilin Wang, Qiang Liu","submitted_at":"2016-11-06T02:40:41Z","abstract_excerpt":"We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output changes along a Stein variational gradient that maximumly decreases the KL divergence with the target distribution. Our method works for any target distribution specified by their unnormalized density function, and can train any black-box architectures that are differentiable in terms of the parameters we want to adapt. As an application of our method, we propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01722","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:56:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UIU+2Yi9DA98M2vfsLwxwOmpu+JYYX0V3w0pLs2w2qAPmMqZwOO99vyjWCH/mDYTxFqHNGMORvAOd/IAHQGFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:28:29.623634Z"},"content_sha256":"1a4bb840f3c11dfdc70f25f8d36bbb0b5172803e5c1abd1c4b1957a0a3706acf","schema_version":"1.0","event_id":"sha256:1a4bb840f3c11dfdc70f25f8d36bbb0b5172803e5c1abd1c4b1957a0a3706acf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V7BDBH2M3PQWDJKKYSDZB3LVNK/bundle.json","state_url":"https://pith.science/pith/V7BDBH2M3PQWDJKKYSDZB3LVNK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V7BDBH2M3PQWDJKKYSDZB3LVNK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T15:28:29Z","links":{"resolver":"https://pith.science/pith/V7BDBH2M3PQWDJKKYSDZB3LVNK","bundle":"https://pith.science/pith/V7BDBH2M3PQWDJKKYSDZB3LVNK/bundle.json","state":"https://pith.science/pith/V7BDBH2M3PQWDJKKYSDZB3LVNK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V7BDBH2M3PQWDJKKYSDZB3LVNK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:V7BDBH2M3PQWDJKKYSDZB3LVNK","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":"ba784b8b7b82005e32b2c44397cda054f2465727ba4275be421a215cb74f4a06","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-06T02:40:41Z","title_canon_sha256":"20df9c36212137e85bf7f44b6b9de32fb621fdfe44753382956c8ab8a4da5f39"},"schema_version":"1.0","source":{"id":"1611.01722","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01722","created_at":"2026-05-18T00:56:37Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01722v2","created_at":"2026-05-18T00:56:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01722","created_at":"2026-05-18T00:56:37Z"},{"alias_kind":"pith_short_12","alias_value":"V7BDBH2M3PQW","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"V7BDBH2M3PQWDJKK","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"V7BDBH2M","created_at":"2026-05-18T12:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:1a4bb840f3c11dfdc70f25f8d36bbb0b5172803e5c1abd1c4b1957a0a3706acf","target":"graph","created_at":"2026-05-18T00:56:37Z","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 propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output changes along a Stein variational gradient that maximumly decreases the KL divergence with the target distribution. Our method works for any target distribution specified by their unnormalized density function, and can train any black-box architectures that are differentiable in terms of the parameters we want to adapt. As an application of our method, we propo","authors_text":"Dilin Wang, Qiang Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-06T02:40:41Z","title":"Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01722","kind":"arxiv","version":2},"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:a847e8538fe071492399c9a87cb0ad73eb3a75694903c104912004f5148ad056","target":"record","created_at":"2026-05-18T00:56:37Z","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":"ba784b8b7b82005e32b2c44397cda054f2465727ba4275be421a215cb74f4a06","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-06T02:40:41Z","title_canon_sha256":"20df9c36212137e85bf7f44b6b9de32fb621fdfe44753382956c8ab8a4da5f39"},"schema_version":"1.0","source":{"id":"1611.01722","kind":"arxiv","version":2}},"canonical_sha256":"afc2309f4cdbe161a54ac48790ed756a94504a66cd3325b0d5b611288d022ed6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afc2309f4cdbe161a54ac48790ed756a94504a66cd3325b0d5b611288d022ed6","first_computed_at":"2026-05-18T00:56:37.512606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:56:37.512606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zjHSEp4+asxydoSZrCwxOapANZW1tL6dfrGkCTM6zMpARAbAqEL5K9w0aZwqZVJtt905U501/Pgy08f3GosRDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:56:37.513206Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01722","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a847e8538fe071492399c9a87cb0ad73eb3a75694903c104912004f5148ad056","sha256:1a4bb840f3c11dfdc70f25f8d36bbb0b5172803e5c1abd1c4b1957a0a3706acf"],"state_sha256":"eb042846ec593aaa22ed9fb221d1327bde90a159c220902510e44f33258ed3e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kleeP5crv8rh3YZeu4fd3B4tm5aBFZUxtTuP2NxkZtrDhYtjDY23duqlb7yviWDFcBNqEl0J7slXW0ML8TYhAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T15:28:29.626804Z","bundle_sha256":"d210493a8d2e854e4c30cad4af50e00e967ba002f0772394575cff690b0c40ae"}}