{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UE37JQ35FFJRN3PQHOBT4SIE2N","short_pith_number":"pith:UE37JQ35","canonical_record":{"source":{"id":"1811.03179","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-11-07T23:14:45Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"511c857cdcac98e9b0a6fe0a98055a6391280cab19b5dbd2ec9e7599225dbce5","abstract_canon_sha256":"7d342f4797e1750d5a92acbcfe8fc4fb56ac5ec167367f19a95496628e774f66"},"schema_version":"1.0"},"canonical_sha256":"a137f4c37d295316edf03b833e4904d34e7703b6f9996257a30cedf5d89694b6","source":{"kind":"arxiv","id":"1811.03179","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03179","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03179v4","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03179","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"pith_short_12","alias_value":"UE37JQ35FFJR","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"pith_short_16","alias_value":"UE37JQ35FFJRN3PQ","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"pith_short_8","alias_value":"UE37JQ35","created_at":"2026-07-05T03:21:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UE37JQ35FFJRN3PQHOBT4SIE2N","target":"record","payload":{"canonical_record":{"source":{"id":"1811.03179","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-11-07T23:14:45Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"511c857cdcac98e9b0a6fe0a98055a6391280cab19b5dbd2ec9e7599225dbce5","abstract_canon_sha256":"7d342f4797e1750d5a92acbcfe8fc4fb56ac5ec167367f19a95496628e774f66"},"schema_version":"1.0"},"canonical_sha256":"a137f4c37d295316edf03b833e4904d34e7703b6f9996257a30cedf5d89694b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:03.662439Z","signature_b64":"vf32TEFSlU1iMCB4BMGr3EYKWD8ODgtcuVAp3Sg2Bd0I24+6NucCrk2rZKpmgSSmAGwdp6zoujIkHWenuJu7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a137f4c37d295316edf03b833e4904d34e7703b6f9996257a30cedf5d89694b6","last_reissued_at":"2026-07-05T03:21:03.661883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:03.661883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.03179","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":"2026-07-05T03:21:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6rgoQ1YrR3nXEkZzM6upYGuy2TS+0CHmIOY3v9peXB/iQy0enYFUkz3wjLkbaQIMg05Tg5CkOdwKRnKDAcRgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:53:47.203920Z"},"content_sha256":"152f54c262edf23dd80dd86fb0547f13944ccc9b2a2029329b73de34e29549b3","schema_version":"1.0","event_id":"sha256:152f54c262edf23dd80dd86fb0547f13944ccc9b2a2029329b73de34e29549b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UE37JQ35FFJRN3PQHOBT4SIE2N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Well Generative Adversarial Networks Learn Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Tengyuan Liang","submitted_at":"2018-11-07T23:14:45Z","abstract_excerpt":"This paper studies the rates of convergence for learning distributions implicitly with the adversarial framework and Generative Adversarial Networks (GANs), which subsume Wasserstein, Sobolev, MMD GAN, and Generalized/Simulated Method of Moments (GMM/SMM) as special cases. We study a wide range of parametric and nonparametric target distributions under a host of objective evaluation metrics. We investigate how to obtain valid statistical guarantees for GANs through the lens of regularization. On the nonparametric end, we derive the optimal minimax rates for distribution estimation under the ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03179","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1811.03179/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T03:21:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hw8Mzn3uMlNfvsnNttkN7d6aTwuZMbHZuhGH+LSVuTqmvRtEZ987VHNBOUE9bY35Ksi8l2NlVnjNTrOPGOEpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:53:47.204419Z"},"content_sha256":"f27ded946973cc9003af943b5170ee3d9761a2d4972a65662920e4aaba55de84","schema_version":"1.0","event_id":"sha256:f27ded946973cc9003af943b5170ee3d9761a2d4972a65662920e4aaba55de84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UE37JQ35FFJRN3PQHOBT4SIE2N/bundle.json","state_url":"https://pith.science/pith/UE37JQ35FFJRN3PQHOBT4SIE2N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UE37JQ35FFJRN3PQHOBT4SIE2N/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":"2026-08-18T20:53:47Z","links":{"resolver":"https://pith.science/pith/UE37JQ35FFJRN3PQHOBT4SIE2N","bundle":"https://pith.science/pith/UE37JQ35FFJRN3PQHOBT4SIE2N/bundle.json","state":"https://pith.science/pith/UE37JQ35FFJRN3PQHOBT4SIE2N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UE37JQ35FFJRN3PQHOBT4SIE2N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UE37JQ35FFJRN3PQHOBT4SIE2N","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":"7d342f4797e1750d5a92acbcfe8fc4fb56ac5ec167367f19a95496628e774f66","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-11-07T23:14:45Z","title_canon_sha256":"511c857cdcac98e9b0a6fe0a98055a6391280cab19b5dbd2ec9e7599225dbce5"},"schema_version":"1.0","source":{"id":"1811.03179","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03179","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03179v4","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03179","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"pith_short_12","alias_value":"UE37JQ35FFJR","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"pith_short_16","alias_value":"UE37JQ35FFJRN3PQ","created_at":"2026-07-05T03:21:03Z"},{"alias_kind":"pith_short_8","alias_value":"UE37JQ35","created_at":"2026-07-05T03:21:03Z"}],"graph_snapshots":[{"event_id":"sha256:f27ded946973cc9003af943b5170ee3d9761a2d4972a65662920e4aaba55de84","target":"graph","created_at":"2026-07-05T03:21:03Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1811.03179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies the rates of convergence for learning distributions implicitly with the adversarial framework and Generative Adversarial Networks (GANs), which subsume Wasserstein, Sobolev, MMD GAN, and Generalized/Simulated Method of Moments (GMM/SMM) as special cases. We study a wide range of parametric and nonparametric target distributions under a host of objective evaluation metrics. We investigate how to obtain valid statistical guarantees for GANs through the lens of regularization. On the nonparametric end, we derive the optimal minimax rates for distribution estimation under the ad","authors_text":"Tengyuan Liang","cross_cats":["cs.LG","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-11-07T23:14:45Z","title":"How Well Generative Adversarial Networks Learn Distributions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03179","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":"sha256:152f54c262edf23dd80dd86fb0547f13944ccc9b2a2029329b73de34e29549b3","target":"record","created_at":"2026-07-05T03:21:03Z","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":"7d342f4797e1750d5a92acbcfe8fc4fb56ac5ec167367f19a95496628e774f66","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-11-07T23:14:45Z","title_canon_sha256":"511c857cdcac98e9b0a6fe0a98055a6391280cab19b5dbd2ec9e7599225dbce5"},"schema_version":"1.0","source":{"id":"1811.03179","kind":"arxiv","version":4}},"canonical_sha256":"a137f4c37d295316edf03b833e4904d34e7703b6f9996257a30cedf5d89694b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a137f4c37d295316edf03b833e4904d34e7703b6f9996257a30cedf5d89694b6","first_computed_at":"2026-07-05T03:21:03.661883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:03.661883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vf32TEFSlU1iMCB4BMGr3EYKWD8ODgtcuVAp3Sg2Bd0I24+6NucCrk2rZKpmgSSmAGwdp6zoujIkHWenuJu7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:03.662439Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.03179","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:152f54c262edf23dd80dd86fb0547f13944ccc9b2a2029329b73de34e29549b3","sha256:f27ded946973cc9003af943b5170ee3d9761a2d4972a65662920e4aaba55de84"],"state_sha256":"238b23d11faa3125452112b6b55e3062a2fe870bf191ce43cb7484607c5de9cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q+yxXW+4PlISasS9xz95FaFsOlkOcXnKUiHI9kLdcX4wkHUI9Yi8Yp8VV/+f9Sdu2l9+h/JsTUTvQ8xf+4C2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:53:47.207940Z","bundle_sha256":"577f880e5f1b03ac8d32e27f655b7b1fee729ba0a1a01ec7193e92a4a844107e"}}