{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:TMNNZOGDLVMH2T6HYCM7VHQURJ","short_pith_number":"pith:TMNNZOGD","canonical_record":{"source":{"id":"1705.09199","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-25T14:32:26Z","cross_cats_sorted":[],"title_canon_sha256":"2eee7edf7c8614bbdc2e5cb9f75ec1af3a3bdb93cb9af12db4c81618feff37e8","abstract_canon_sha256":"103457a72622131ef551269cda48cfaa1d44e361d15df9ef9c2a96c0febd184c"},"schema_version":"1.0"},"canonical_sha256":"9b1adcb8c35d587d4fc7c099fa9e148a56964dac1d232dceed3c3009435019f5","source":{"kind":"arxiv","id":"1705.09199","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.09199","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"1705.09199v3","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09199","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"TMNNZOGDLVMH","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TMNNZOGDLVMH2T6H","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TMNNZOGD","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:TMNNZOGDLVMH2T6HYCM7VHQURJ","target":"record","payload":{"canonical_record":{"source":{"id":"1705.09199","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-25T14:32:26Z","cross_cats_sorted":[],"title_canon_sha256":"2eee7edf7c8614bbdc2e5cb9f75ec1af3a3bdb93cb9af12db4c81618feff37e8","abstract_canon_sha256":"103457a72622131ef551269cda48cfaa1d44e361d15df9ef9c2a96c0febd184c"},"schema_version":"1.0"},"canonical_sha256":"9b1adcb8c35d587d4fc7c099fa9e148a56964dac1d232dceed3c3009435019f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:50.688892Z","signature_b64":"4r+Op0YX+k9m/Br/vwNAk8BxXPKPXl0HzIbkZz8UBV2JU9lTJubS21dr0qHGxrrsHlneM/1emlXoPZoypNb+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b1adcb8c35d587d4fc7c099fa9e148a56964dac1d232dceed3c3009435019f5","last_reissued_at":"2026-05-18T00:32:50.688372Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:50.688372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.09199","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XXTYHD4scfLvRnsV/n4eHz3kTC9rPBQKMrPKGj2w5PYTt2A2fP4HGXRC0KysXTWn+PmfQQYSxLKjCHzcmOdQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:28:54.774967Z"},"content_sha256":"657d5572fb1ae4afc88319508f089a7938d0d9066e01897b2ed819cbb2d01975","schema_version":"1.0","event_id":"sha256:657d5572fb1ae4afc88319508f089a7938d0d9066e01897b2ed819cbb2d01975"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:TMNNZOGDLVMH2T6HYCM7VHQURJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Ambrish Rawat, Mathieu Sinn","submitted_at":"2017-05-25T14:32:26Z","abstract_excerpt":"Generative Adversarial Networks (GANs) have become a widely popular framework for generative modelling of high-dimensional datasets. However their training is well-known to be difficult. This work presents a rigorous statistical analysis of GANs providing straight-forward explanations for common training pathologies such as vanishing gradients. Furthermore, it proposes a new training objective, Kernel GANs, and demonstrates its practical effectiveness on large-scale real-world data sets. A key element in the analysis is the distinction between training with respect to the (unknown) data distri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09199","kind":"arxiv","version":3},"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":"2026-05-18T00:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ANM/x2jVDXSoWbn/vVHXsdwOIGnAxxaxMG/oLsJqFZKICx9zHocjL9CtQ1E73klRcp2r4W+13dTX8JCyDdmcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:28:54.775450Z"},"content_sha256":"fc9ce584f341a81df3ae63ffc8c0822ba415fcf3890110434e32bc5d0fe248f5","schema_version":"1.0","event_id":"sha256:fc9ce584f341a81df3ae63ffc8c0822ba415fcf3890110434e32bc5d0fe248f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TMNNZOGDLVMH2T6HYCM7VHQURJ/bundle.json","state_url":"https://pith.science/pith/TMNNZOGDLVMH2T6HYCM7VHQURJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TMNNZOGDLVMH2T6HYCM7VHQURJ/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":"2026-05-26T20:28:54Z","links":{"resolver":"https://pith.science/pith/TMNNZOGDLVMH2T6HYCM7VHQURJ","bundle":"https://pith.science/pith/TMNNZOGDLVMH2T6HYCM7VHQURJ/bundle.json","state":"https://pith.science/pith/TMNNZOGDLVMH2T6HYCM7VHQURJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TMNNZOGDLVMH2T6HYCM7VHQURJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:TMNNZOGDLVMH2T6HYCM7VHQURJ","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":"103457a72622131ef551269cda48cfaa1d44e361d15df9ef9c2a96c0febd184c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-25T14:32:26Z","title_canon_sha256":"2eee7edf7c8614bbdc2e5cb9f75ec1af3a3bdb93cb9af12db4c81618feff37e8"},"schema_version":"1.0","source":{"id":"1705.09199","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.09199","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"1705.09199v3","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09199","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"TMNNZOGDLVMH","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TMNNZOGDLVMH2T6H","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TMNNZOGD","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:fc9ce584f341a81df3ae63ffc8c0822ba415fcf3890110434e32bc5d0fe248f5","target":"graph","created_at":"2026-05-18T00:32:50Z","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":"Generative Adversarial Networks (GANs) have become a widely popular framework for generative modelling of high-dimensional datasets. However their training is well-known to be difficult. This work presents a rigorous statistical analysis of GANs providing straight-forward explanations for common training pathologies such as vanishing gradients. Furthermore, it proposes a new training objective, Kernel GANs, and demonstrates its practical effectiveness on large-scale real-world data sets. A key element in the analysis is the distinction between training with respect to the (unknown) data distri","authors_text":"Ambrish Rawat, Mathieu Sinn","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-25T14:32:26Z","title":"Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09199","kind":"arxiv","version":3},"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":"sha256:657d5572fb1ae4afc88319508f089a7938d0d9066e01897b2ed819cbb2d01975","target":"record","created_at":"2026-05-18T00:32:50Z","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":"103457a72622131ef551269cda48cfaa1d44e361d15df9ef9c2a96c0febd184c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-25T14:32:26Z","title_canon_sha256":"2eee7edf7c8614bbdc2e5cb9f75ec1af3a3bdb93cb9af12db4c81618feff37e8"},"schema_version":"1.0","source":{"id":"1705.09199","kind":"arxiv","version":3}},"canonical_sha256":"9b1adcb8c35d587d4fc7c099fa9e148a56964dac1d232dceed3c3009435019f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b1adcb8c35d587d4fc7c099fa9e148a56964dac1d232dceed3c3009435019f5","first_computed_at":"2026-05-18T00:32:50.688372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:50.688372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4r+Op0YX+k9m/Br/vwNAk8BxXPKPXl0HzIbkZz8UBV2JU9lTJubS21dr0qHGxrrsHlneM/1emlXoPZoypNb+AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:50.688892Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.09199","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:657d5572fb1ae4afc88319508f089a7938d0d9066e01897b2ed819cbb2d01975","sha256:fc9ce584f341a81df3ae63ffc8c0822ba415fcf3890110434e32bc5d0fe248f5"],"state_sha256":"792c41d55ee194076e712568952b8507738ffa929379a524f4913ac109a3f268"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cd1BFUNBbPRZ4itaEtDfb0TGFu6OO/JvlOQQcqCtAR35UKy7kWNi9J7Hn73/ElL8ZIp9ZrgBfiiU+KbEOM+VAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T20:28:54.778990Z","bundle_sha256":"4d8b5e38bf80802a3adc12c797c6dea217609e6301773a3808def1a0ff78cc52"}}