{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZWOGFSNZSHC6AKPSHPK5VA6NL3","short_pith_number":"pith:ZWOGFSNZ","canonical_record":{"source":{"id":"1901.03396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T16:29:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"98d3c392d9e259f09c7adbf60b96fa1799e40cde1db6d9f44b0a25d093467f94","abstract_canon_sha256":"876c8be0651f5a2cd352c927c889375e27db1291d932845e108e0c3f857e22bc"},"schema_version":"1.0"},"canonical_sha256":"cd9c62c9b991c5e029f23bd5da83cd5ee87ca12a6889f0b77da0b18494b860eb","source":{"kind":"arxiv","id":"1901.03396","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.03396","created_at":"2026-05-17T23:56:31Z"},{"alias_kind":"arxiv_version","alias_value":"1901.03396v1","created_at":"2026-05-17T23:56:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.03396","created_at":"2026-05-17T23:56:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZWOGFSNZSHC6","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZWOGFSNZSHC6AKPS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZWOGFSNZ","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZWOGFSNZSHC6AKPSHPK5VA6NL3","target":"record","payload":{"canonical_record":{"source":{"id":"1901.03396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T16:29:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"98d3c392d9e259f09c7adbf60b96fa1799e40cde1db6d9f44b0a25d093467f94","abstract_canon_sha256":"876c8be0651f5a2cd352c927c889375e27db1291d932845e108e0c3f857e22bc"},"schema_version":"1.0"},"canonical_sha256":"cd9c62c9b991c5e029f23bd5da83cd5ee87ca12a6889f0b77da0b18494b860eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:31.352010Z","signature_b64":"U59ql9Pbp1O7TtPl3i4Ue8NJitqO304oBefiiWr0ggleRCd3lYf85Yen5JPb7WqRYHKLAku+g01JHixynY2zAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd9c62c9b991c5e029f23bd5da83cd5ee87ca12a6889f0b77da0b18494b860eb","last_reissued_at":"2026-05-17T23:56:31.351465Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:31.351465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.03396","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LXgmDY1oSJ9VRdYoEZbLnn0GgQIlFxyDUX3L3PxGvxd0dqNQmq5xhDb6hloNGzLnh/3wJ6nwuKwBjcSocgMCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T20:00:37.252550Z"},"content_sha256":"2c1a46d2910e1cc366508a78d602688e9bbca81edaf5942c539cc1b8458ccf31","schema_version":"1.0","event_id":"sha256:2c1a46d2910e1cc366508a78d602688e9bbca81edaf5942c539cc1b8458ccf31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZWOGFSNZSHC6AKPSHPK5VA6NL3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detecting Overfitting of Deep Generative Networks via Latent Recovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frederic Jurie, Julien Rabin, Loic Simon, Ryan Webster","submitted_at":"2019-01-09T16:29:05Z","abstract_excerpt":"State of the art deep generative networks are capable of producing images with such incredible realism that they can be suspected of memorizing training images. It is why it is not uncommon to include visualizations of training set nearest neighbors, to suggest generated images are not simply memorized. We demonstrate this is not sufficient and motivates the need to study memorization/overfitting of deep generators with more scrutiny. This paper addresses this question by i) showing how simple losses are highly effective at reconstructing images for deep generators ii) analyzing the statistics"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.03396","kind":"arxiv","version":1},"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":"2026-05-17T23:56:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B2ax+YE+505jv1ehvMg17L82MmDVYVkqAs8Zy4Dr4pNpASHmTrJ6yK4B/kMORM7BWpY6lDjlCpEtRaKDOdSPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T20:00:37.252901Z"},"content_sha256":"8354c95c870847a8a472c336b49d85eb5f776e22c83174e5f238ca58adbabd8b","schema_version":"1.0","event_id":"sha256:8354c95c870847a8a472c336b49d85eb5f776e22c83174e5f238ca58adbabd8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZWOGFSNZSHC6AKPSHPK5VA6NL3/bundle.json","state_url":"https://pith.science/pith/ZWOGFSNZSHC6AKPSHPK5VA6NL3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZWOGFSNZSHC6AKPSHPK5VA6NL3/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":"2026-06-25T20:00:37Z","links":{"resolver":"https://pith.science/pith/ZWOGFSNZSHC6AKPSHPK5VA6NL3","bundle":"https://pith.science/pith/ZWOGFSNZSHC6AKPSHPK5VA6NL3/bundle.json","state":"https://pith.science/pith/ZWOGFSNZSHC6AKPSHPK5VA6NL3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZWOGFSNZSHC6AKPSHPK5VA6NL3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZWOGFSNZSHC6AKPSHPK5VA6NL3","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":"876c8be0651f5a2cd352c927c889375e27db1291d932845e108e0c3f857e22bc","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T16:29:05Z","title_canon_sha256":"98d3c392d9e259f09c7adbf60b96fa1799e40cde1db6d9f44b0a25d093467f94"},"schema_version":"1.0","source":{"id":"1901.03396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.03396","created_at":"2026-05-17T23:56:31Z"},{"alias_kind":"arxiv_version","alias_value":"1901.03396v1","created_at":"2026-05-17T23:56:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.03396","created_at":"2026-05-17T23:56:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZWOGFSNZSHC6","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZWOGFSNZSHC6AKPS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZWOGFSNZ","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:8354c95c870847a8a472c336b49d85eb5f776e22c83174e5f238ca58adbabd8b","target":"graph","created_at":"2026-05-17T23:56:31Z","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":"State of the art deep generative networks are capable of producing images with such incredible realism that they can be suspected of memorizing training images. It is why it is not uncommon to include visualizations of training set nearest neighbors, to suggest generated images are not simply memorized. We demonstrate this is not sufficient and motivates the need to study memorization/overfitting of deep generators with more scrutiny. This paper addresses this question by i) showing how simple losses are highly effective at reconstructing images for deep generators ii) analyzing the statistics","authors_text":"Frederic Jurie, Julien Rabin, Loic Simon, Ryan Webster","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T16:29:05Z","title":"Detecting Overfitting of Deep Generative Networks via Latent Recovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.03396","kind":"arxiv","version":1},"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":"sha256:2c1a46d2910e1cc366508a78d602688e9bbca81edaf5942c539cc1b8458ccf31","target":"record","created_at":"2026-05-17T23:56:31Z","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":"876c8be0651f5a2cd352c927c889375e27db1291d932845e108e0c3f857e22bc","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T16:29:05Z","title_canon_sha256":"98d3c392d9e259f09c7adbf60b96fa1799e40cde1db6d9f44b0a25d093467f94"},"schema_version":"1.0","source":{"id":"1901.03396","kind":"arxiv","version":1}},"canonical_sha256":"cd9c62c9b991c5e029f23bd5da83cd5ee87ca12a6889f0b77da0b18494b860eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd9c62c9b991c5e029f23bd5da83cd5ee87ca12a6889f0b77da0b18494b860eb","first_computed_at":"2026-05-17T23:56:31.351465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:31.351465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U59ql9Pbp1O7TtPl3i4Ue8NJitqO304oBefiiWr0ggleRCd3lYf85Yen5JPb7WqRYHKLAku+g01JHixynY2zAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:31.352010Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.03396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c1a46d2910e1cc366508a78d602688e9bbca81edaf5942c539cc1b8458ccf31","sha256:8354c95c870847a8a472c336b49d85eb5f776e22c83174e5f238ca58adbabd8b"],"state_sha256":"13069dc171e74547d76dcc8390b6c960ec4758ed3ab1fc900e6ec3a189e433b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xty4ll9qQmJWFDCBqe+2ZYFrkWjgA6t4WJAF0Z6s+xVN4CVlTJWWI0s43d4zLiKswxt3q8msR5lGrKMHtGRHBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T20:00:37.254970Z","bundle_sha256":"cc125b5a34dcc623f01ec66520546c92f8c7c03de98237cd2f0c6fef4291b2cf"}}