{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EJNTHWVV4K53KKLPCQHCZC456B","short_pith_number":"pith:EJNTHWVV","canonical_record":{"source":{"id":"1806.07185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T12:39:11Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"80bb7686bd28d5a2fbbd0c52b8920301c2d04efecaaf942da052e5c56a6a5bce","abstract_canon_sha256":"d1fa2a1fe93a730b806e493ea04cae077de922385f58c2e5a4d2304d71466c1e"},"schema_version":"1.0"},"canonical_sha256":"225b33dab5e2bbb5296f140e2c8b9df070d547a6515194908778bc057e4924cd","source":{"kind":"arxiv","id":"1806.07185","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.07185","created_at":"2026-05-18T00:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"1806.07185v1","created_at":"2026-05-18T00:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07185","created_at":"2026-05-18T00:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"EJNTHWVV4K53","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EJNTHWVV4K53KKLP","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EJNTHWVV","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EJNTHWVV4K53KKLPCQHCZC456B","target":"record","payload":{"canonical_record":{"source":{"id":"1806.07185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T12:39:11Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"80bb7686bd28d5a2fbbd0c52b8920301c2d04efecaaf942da052e5c56a6a5bce","abstract_canon_sha256":"d1fa2a1fe93a730b806e493ea04cae077de922385f58c2e5a4d2304d71466c1e"},"schema_version":"1.0"},"canonical_sha256":"225b33dab5e2bbb5296f140e2c8b9df070d547a6515194908778bc057e4924cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:51.645724Z","signature_b64":"X+Q03oKkjl+rEopNO+NzYquqAiV/YopLOXDWfnhnz3GRI+q5eCAiYnyP/iJt6FuKOGY7BNxqRuuyBCpdIwJOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"225b33dab5e2bbb5296f140e2c8b9df070d547a6515194908778bc057e4924cd","last_reissued_at":"2026-05-18T00:12:51.645195Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:51.645195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.07185","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":"2026-05-18T00:12:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uJ7jC35wg8WA+KaVS0YgQn4DisyA5xDpiKe/pjJxI6IGkH1Njy5+6HZlt2TWHy5Eb4INygHlIfBdpwFgSctlDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:50:30.629923Z"},"content_sha256":"b4aac97e5206f8690aa26fcbffa8f8baea37617f2cc08e681d91d2f7717fc222","schema_version":"1.0","event_id":"sha256:b4aac97e5206f8690aa26fcbffa8f8baea37617f2cc08e681d91d2f7717fc222"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EJNTHWVV4K53KKLPCQHCZC456B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mixed batches and symmetric discriminators for GAN training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Corentin Tallec, Jakob Verbeek, Thomas Lucas, Yann Ollivier","submitted_at":"2018-06-19T12:39:11Z","abstract_excerpt":"Generative adversarial networks (GANs) are pow- erful generative models based on providing feed- back to a generative network via a discriminator network. However, the discriminator usually as- sesses individual samples. This prevents the dis- criminator from accessing global distributional statistics of generated samples, and often leads to mode dropping: the generator models only part of the target distribution. We propose to feed the discriminator with mixed batches of true and fake samples, and train it to predict the ratio of true samples in the batch. The latter score does not depend on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.07185","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":"2026-05-18T00:12:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x5ijbUZcHOIcfi3EsJWMsdw2hLB44LnFv8+i5P72aZ3jqmBkinD1irjVg8V5n+g1fSWHcvxSq2/enFc9UEfqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:50:30.630661Z"},"content_sha256":"45238d87933d428133cd0d62f808abb7368fb62cea152754b41076a0ecab61eb","schema_version":"1.0","event_id":"sha256:45238d87933d428133cd0d62f808abb7368fb62cea152754b41076a0ecab61eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EJNTHWVV4K53KKLPCQHCZC456B/bundle.json","state_url":"https://pith.science/pith/EJNTHWVV4K53KKLPCQHCZC456B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EJNTHWVV4K53KKLPCQHCZC456B/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":"2026-05-31T20:50:30Z","links":{"resolver":"https://pith.science/pith/EJNTHWVV4K53KKLPCQHCZC456B","bundle":"https://pith.science/pith/EJNTHWVV4K53KKLPCQHCZC456B/bundle.json","state":"https://pith.science/pith/EJNTHWVV4K53KKLPCQHCZC456B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EJNTHWVV4K53KKLPCQHCZC456B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EJNTHWVV4K53KKLPCQHCZC456B","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":"d1fa2a1fe93a730b806e493ea04cae077de922385f58c2e5a4d2304d71466c1e","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T12:39:11Z","title_canon_sha256":"80bb7686bd28d5a2fbbd0c52b8920301c2d04efecaaf942da052e5c56a6a5bce"},"schema_version":"1.0","source":{"id":"1806.07185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.07185","created_at":"2026-05-18T00:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"1806.07185v1","created_at":"2026-05-18T00:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07185","created_at":"2026-05-18T00:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"EJNTHWVV4K53","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EJNTHWVV4K53KKLP","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EJNTHWVV","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:45238d87933d428133cd0d62f808abb7368fb62cea152754b41076a0ecab61eb","target":"graph","created_at":"2026-05-18T00:12:51Z","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) are pow- erful generative models based on providing feed- back to a generative network via a discriminator network. However, the discriminator usually as- sesses individual samples. This prevents the dis- criminator from accessing global distributional statistics of generated samples, and often leads to mode dropping: the generator models only part of the target distribution. We propose to feed the discriminator with mixed batches of true and fake samples, and train it to predict the ratio of true samples in the batch. The latter score does not depend on ","authors_text":"Corentin Tallec, Jakob Verbeek, Thomas Lucas, Yann Ollivier","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T12:39:11Z","title":"Mixed batches and symmetric discriminators for GAN training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.07185","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:b4aac97e5206f8690aa26fcbffa8f8baea37617f2cc08e681d91d2f7717fc222","target":"record","created_at":"2026-05-18T00:12:51Z","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":"d1fa2a1fe93a730b806e493ea04cae077de922385f58c2e5a4d2304d71466c1e","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-19T12:39:11Z","title_canon_sha256":"80bb7686bd28d5a2fbbd0c52b8920301c2d04efecaaf942da052e5c56a6a5bce"},"schema_version":"1.0","source":{"id":"1806.07185","kind":"arxiv","version":1}},"canonical_sha256":"225b33dab5e2bbb5296f140e2c8b9df070d547a6515194908778bc057e4924cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"225b33dab5e2bbb5296f140e2c8b9df070d547a6515194908778bc057e4924cd","first_computed_at":"2026-05-18T00:12:51.645195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:51.645195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X+Q03oKkjl+rEopNO+NzYquqAiV/YopLOXDWfnhnz3GRI+q5eCAiYnyP/iJt6FuKOGY7BNxqRuuyBCpdIwJOBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:51.645724Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.07185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4aac97e5206f8690aa26fcbffa8f8baea37617f2cc08e681d91d2f7717fc222","sha256:45238d87933d428133cd0d62f808abb7368fb62cea152754b41076a0ecab61eb"],"state_sha256":"862091fb3e281b825ff9a1b8e78434f392483a78241f717b35323e1712afd77a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dv1haACFruCzwVm35QxL/g6PQtlm4MBtgbxwlCvechMGh9Is1n4mLj0qg35y1XqxhFvJArdw9/mVqjkz+NMIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T20:50:30.634668Z","bundle_sha256":"2c8e215ac3d8b48e04bb983c984646623fee9b6facd16084c796bec1942bc981"}}