{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MKW3USEJGFESA6RY6H3YT4JP7M","short_pith_number":"pith:MKW3USEJ","canonical_record":{"source":{"id":"1804.11130","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-30T11:41:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"38b4462a5177989ba26f68d07cef4092a510adead072308036147b4d7b76ce42","abstract_canon_sha256":"e92012636e6189d4f8c845b9b29a8c37eff6412c8defb5c336137d38f763a342"},"schema_version":"1.0"},"canonical_sha256":"62adba48893149207a38f1f789f12ffb0e9c80be8759c7bd22ab526de99ca55f","source":{"kind":"arxiv","id":"1804.11130","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.11130","created_at":"2026-05-17T23:52:18Z"},{"alias_kind":"arxiv_version","alias_value":"1804.11130v4","created_at":"2026-05-17T23:52:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11130","created_at":"2026-05-17T23:52:18Z"},{"alias_kind":"pith_short_12","alias_value":"MKW3USEJGFES","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MKW3USEJGFESA6RY","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MKW3USEJ","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MKW3USEJGFESA6RY6H3YT4JP7M","target":"record","payload":{"canonical_record":{"source":{"id":"1804.11130","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-30T11:41:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"38b4462a5177989ba26f68d07cef4092a510adead072308036147b4d7b76ce42","abstract_canon_sha256":"e92012636e6189d4f8c845b9b29a8c37eff6412c8defb5c336137d38f763a342"},"schema_version":"1.0"},"canonical_sha256":"62adba48893149207a38f1f789f12ffb0e9c80be8759c7bd22ab526de99ca55f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:18.415413Z","signature_b64":"vtv9fJFAvU1bjPK0rNKqTl1no5XLoJjE2ct69OiEe+6fehiITpFsclZUTyZYiyHwqRt/2cniQHGj8L0/1QUyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62adba48893149207a38f1f789f12ffb0e9c80be8759c7bd22ab526de99ca55f","last_reissued_at":"2026-05-17T23:52:18.414726Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:18.414726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.11130","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LhstU3vbui17f9WgKel2oVU3JvrkUcV4N7MEEZ8m9M/NK7OL0zWYrZRuyZMIhtQzrXG7G6O4y6hYodDVChjKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:27:17.967984Z"},"content_sha256":"2375a467c4c4ad02e0c6f3871e790685eab355308a2739e44f004b9ef2033ea7","schema_version":"1.0","event_id":"sha256:2375a467c4c4ad02e0c6f3871e790685eab355308a2739e44f004b9ef2033ea7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MKW3USEJGFESA6RY6H3YT4JP7M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Competitive Training of Mixtures of Independent Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Damien Vincent, Francesco Locatello, Gunnar R\\\"atsch, Ilya Tolstikhin, Sylvain Gelly","submitted_at":"2018-04-30T11:41:48Z","abstract_excerpt":"A common assumption in causal modeling posits that the data is generated by a set of independent mechanisms, and algorithms should aim to recover this structure. Standard unsupervised learning, however, is often concerned with training a single model to capture the overall distribution or aspects thereof. Inspired by clustering approaches, we consider mixtures of implicit generative models that ``disentangle'' the independent generative mechanisms underlying the data. Relying on an additional set of discriminators, we propose a competitive training procedure in which the models only need to ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11130","kind":"arxiv","version":4},"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":"2026-05-17T23:52:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G92l5u0e5HjgSlpcsg+GK8ZErCPZjhEJ0rdft+zWW6Eh6Ki9+/1v7mrKIWTpwnBBgY6ZAEbXvXF2NvLEqlIXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:27:17.968338Z"},"content_sha256":"e92fcf4a37d6f86b329c95e5a50b1cf76d979001e99b66d2dcc401b4f046c1aa","schema_version":"1.0","event_id":"sha256:e92fcf4a37d6f86b329c95e5a50b1cf76d979001e99b66d2dcc401b4f046c1aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MKW3USEJGFESA6RY6H3YT4JP7M/bundle.json","state_url":"https://pith.science/pith/MKW3USEJGFESA6RY6H3YT4JP7M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MKW3USEJGFESA6RY6H3YT4JP7M/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":"2026-05-31T18:27:17Z","links":{"resolver":"https://pith.science/pith/MKW3USEJGFESA6RY6H3YT4JP7M","bundle":"https://pith.science/pith/MKW3USEJGFESA6RY6H3YT4JP7M/bundle.json","state":"https://pith.science/pith/MKW3USEJGFESA6RY6H3YT4JP7M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MKW3USEJGFESA6RY6H3YT4JP7M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MKW3USEJGFESA6RY6H3YT4JP7M","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":"e92012636e6189d4f8c845b9b29a8c37eff6412c8defb5c336137d38f763a342","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-30T11:41:48Z","title_canon_sha256":"38b4462a5177989ba26f68d07cef4092a510adead072308036147b4d7b76ce42"},"schema_version":"1.0","source":{"id":"1804.11130","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.11130","created_at":"2026-05-17T23:52:18Z"},{"alias_kind":"arxiv_version","alias_value":"1804.11130v4","created_at":"2026-05-17T23:52:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11130","created_at":"2026-05-17T23:52:18Z"},{"alias_kind":"pith_short_12","alias_value":"MKW3USEJGFES","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MKW3USEJGFESA6RY","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MKW3USEJ","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:e92fcf4a37d6f86b329c95e5a50b1cf76d979001e99b66d2dcc401b4f046c1aa","target":"graph","created_at":"2026-05-17T23:52:18Z","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":"A common assumption in causal modeling posits that the data is generated by a set of independent mechanisms, and algorithms should aim to recover this structure. Standard unsupervised learning, however, is often concerned with training a single model to capture the overall distribution or aspects thereof. Inspired by clustering approaches, we consider mixtures of implicit generative models that ``disentangle'' the independent generative mechanisms underlying the data. Relying on an additional set of discriminators, we propose a competitive training procedure in which the models only need to ca","authors_text":"Bernhard Sch\\\"olkopf, Damien Vincent, Francesco Locatello, Gunnar R\\\"atsch, Ilya Tolstikhin, Sylvain Gelly","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-30T11:41:48Z","title":"Competitive Training of Mixtures of Independent Deep Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11130","kind":"arxiv","version":4},"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":"sha256:2375a467c4c4ad02e0c6f3871e790685eab355308a2739e44f004b9ef2033ea7","target":"record","created_at":"2026-05-17T23:52:18Z","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":"e92012636e6189d4f8c845b9b29a8c37eff6412c8defb5c336137d38f763a342","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-30T11:41:48Z","title_canon_sha256":"38b4462a5177989ba26f68d07cef4092a510adead072308036147b4d7b76ce42"},"schema_version":"1.0","source":{"id":"1804.11130","kind":"arxiv","version":4}},"canonical_sha256":"62adba48893149207a38f1f789f12ffb0e9c80be8759c7bd22ab526de99ca55f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62adba48893149207a38f1f789f12ffb0e9c80be8759c7bd22ab526de99ca55f","first_computed_at":"2026-05-17T23:52:18.414726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:18.414726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vtv9fJFAvU1bjPK0rNKqTl1no5XLoJjE2ct69OiEe+6fehiITpFsclZUTyZYiyHwqRt/2cniQHGj8L0/1QUyBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:18.415413Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.11130","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2375a467c4c4ad02e0c6f3871e790685eab355308a2739e44f004b9ef2033ea7","sha256:e92fcf4a37d6f86b329c95e5a50b1cf76d979001e99b66d2dcc401b4f046c1aa"],"state_sha256":"8f1b0086671c68060e16648ed672ca11124f3d5f1594a3e55dbb935c91c9f579"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nbh6isY2bXu1FtoBTsFv8t8Ts8V2usjCX8zAwFwvKgTNlDQ7GIIL3s9oq44kK2XwHfR2apX39MMs5sRFqsK0Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:27:17.970260Z","bundle_sha256":"58b824de3dccfa41ab7a0773d243096321ea3aa7e9cfec50bbd81c65d499101f"}}