{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:CSBSPOMGAYA3BNID4NBH4XT5NH","short_pith_number":"pith:CSBSPOMG","canonical_record":{"source":{"id":"1705.07107","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T17:35:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"853ae4a3058fe2038923364389d2f5cfed7bf71bb8283979db4372e2ca8b30d5","abstract_canon_sha256":"05d08825b4ac1da76cd689a2c43afe394dedd5279326cb05867de2193b2704fb"},"schema_version":"1.0"},"canonical_sha256":"148327b9860601b0b503e3427e5e7d69f3935757dc2fae9604cef3b297652412","source":{"kind":"arxiv","id":"1705.07107","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07107","created_at":"2026-05-18T00:17:27Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07107v5","created_at":"2026-05-18T00:17:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07107","created_at":"2026-05-18T00:17:27Z"},{"alias_kind":"pith_short_12","alias_value":"CSBSPOMGAYA3","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CSBSPOMGAYA3BNID","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CSBSPOMG","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:CSBSPOMGAYA3BNID4NBH4XT5NH","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07107","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T17:35:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"853ae4a3058fe2038923364389d2f5cfed7bf71bb8283979db4372e2ca8b30d5","abstract_canon_sha256":"05d08825b4ac1da76cd689a2c43afe394dedd5279326cb05867de2193b2704fb"},"schema_version":"1.0"},"canonical_sha256":"148327b9860601b0b503e3427e5e7d69f3935757dc2fae9604cef3b297652412","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:27.254307Z","signature_b64":"hzMklvCEvVWDLvATz5GNv1OkfxMvmaiQ0TGB7PxPR8OwghlwC4mSKgxkLySTMM+reR2t1S7PpMXkSO0abkgMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"148327b9860601b0b503e3427e5e7d69f3935757dc2fae9604cef3b297652412","last_reissued_at":"2026-05-18T00:17:27.253577Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:27.253577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07107","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:17:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zngCf704oBH/ZjCdDwiM7N+l6Wb0Z3ZpikOAoUhJzialSbzm8mkf40483r2h0qutIxtZxB3c+Nbt38D7YpDKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T09:21:55.917782Z"},"content_sha256":"5cce07c77753d390740fa0e3f9e86dfc82b99fc0d471ac66f131813c2425b0e5","schema_version":"1.0","event_id":"sha256:5cce07c77753d390740fa0e3f9e86dfc82b99fc0d471ac66f131813c2425b0e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:CSBSPOMGAYA3BNID4NBH4XT5NH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradient Estimators for Implicit Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Richard E. Turner, Yingzhen Li","submitted_at":"2017-05-19T17:35:04Z","abstract_excerpt":"Implicit models, which allow for the generation of samples but not for point-wise evaluation of probabilities, are omnipresent in real-world problems tackled by machine learning and a hot topic of current research. Some examples include data simulators that are widely used in engineering and scientific research, generative adversarial networks (GANs) for image synthesis, and hot-off-the-press approximate inference techniques relying on implicit distributions. The majority of existing approaches to learning implicit models rely on approximating the intractable distribution or optimisation objec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07107","kind":"arxiv","version":5},"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":"2026-05-18T00:17:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GiwJ+KUGY5I9eUfVqO7qHy2ZUpIqxpKeRCt2pYsWiDp2t5k0lQMvCgF5zU2/Zjv1OHO6MWghr+Sk75afdKUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T09:21:55.918459Z"},"content_sha256":"f9e90ea2b53e3ddcab766e3e73d1fb64f9b65e35aa72b96406721c231a3ceef8","schema_version":"1.0","event_id":"sha256:f9e90ea2b53e3ddcab766e3e73d1fb64f9b65e35aa72b96406721c231a3ceef8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CSBSPOMGAYA3BNID4NBH4XT5NH/bundle.json","state_url":"https://pith.science/pith/CSBSPOMGAYA3BNID4NBH4XT5NH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CSBSPOMGAYA3BNID4NBH4XT5NH/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":"2026-06-07T09:21:55Z","links":{"resolver":"https://pith.science/pith/CSBSPOMGAYA3BNID4NBH4XT5NH","bundle":"https://pith.science/pith/CSBSPOMGAYA3BNID4NBH4XT5NH/bundle.json","state":"https://pith.science/pith/CSBSPOMGAYA3BNID4NBH4XT5NH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CSBSPOMGAYA3BNID4NBH4XT5NH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CSBSPOMGAYA3BNID4NBH4XT5NH","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":"05d08825b4ac1da76cd689a2c43afe394dedd5279326cb05867de2193b2704fb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T17:35:04Z","title_canon_sha256":"853ae4a3058fe2038923364389d2f5cfed7bf71bb8283979db4372e2ca8b30d5"},"schema_version":"1.0","source":{"id":"1705.07107","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07107","created_at":"2026-05-18T00:17:27Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07107v5","created_at":"2026-05-18T00:17:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07107","created_at":"2026-05-18T00:17:27Z"},{"alias_kind":"pith_short_12","alias_value":"CSBSPOMGAYA3","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CSBSPOMGAYA3BNID","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CSBSPOMG","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:f9e90ea2b53e3ddcab766e3e73d1fb64f9b65e35aa72b96406721c231a3ceef8","target":"graph","created_at":"2026-05-18T00:17:27Z","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":"Implicit models, which allow for the generation of samples but not for point-wise evaluation of probabilities, are omnipresent in real-world problems tackled by machine learning and a hot topic of current research. Some examples include data simulators that are widely used in engineering and scientific research, generative adversarial networks (GANs) for image synthesis, and hot-off-the-press approximate inference techniques relying on implicit distributions. The majority of existing approaches to learning implicit models rely on approximating the intractable distribution or optimisation objec","authors_text":"Richard E. Turner, Yingzhen Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T17:35:04Z","title":"Gradient Estimators for Implicit Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07107","kind":"arxiv","version":5},"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":"sha256:5cce07c77753d390740fa0e3f9e86dfc82b99fc0d471ac66f131813c2425b0e5","target":"record","created_at":"2026-05-18T00:17:27Z","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":"05d08825b4ac1da76cd689a2c43afe394dedd5279326cb05867de2193b2704fb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T17:35:04Z","title_canon_sha256":"853ae4a3058fe2038923364389d2f5cfed7bf71bb8283979db4372e2ca8b30d5"},"schema_version":"1.0","source":{"id":"1705.07107","kind":"arxiv","version":5}},"canonical_sha256":"148327b9860601b0b503e3427e5e7d69f3935757dc2fae9604cef3b297652412","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"148327b9860601b0b503e3427e5e7d69f3935757dc2fae9604cef3b297652412","first_computed_at":"2026-05-18T00:17:27.253577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:27.253577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hzMklvCEvVWDLvATz5GNv1OkfxMvmaiQ0TGB7PxPR8OwghlwC4mSKgxkLySTMM+reR2t1S7PpMXkSO0abkgMBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:27.254307Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07107","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cce07c77753d390740fa0e3f9e86dfc82b99fc0d471ac66f131813c2425b0e5","sha256:f9e90ea2b53e3ddcab766e3e73d1fb64f9b65e35aa72b96406721c231a3ceef8"],"state_sha256":"a01fd930d637ced764d173b917827717d54a50a65ecc4186e288b07b16c774e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HEzerSMEa7h+Ax6ZUVdiye5Y60u9R/seb6xxG/ZINZpwi4/yLT0ti5t+bmq0ZcAbkubO2VVOgE6uymVYFXLKDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T09:21:55.921894Z","bundle_sha256":"cc47c9ce2a435ad6c4fb016fbc377a3f39b6009ebac8c6b54cfc1cc14872c7c5"}}