{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UQSF74FFST75COBOYTCYK5IZV2","short_pith_number":"pith:UQSF74FF","canonical_record":{"source":{"id":"1802.04374","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-12T21:49:07Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"b696d3e221e1d1ca6245e3815fcb73e7baaee92f529de4373966e34f1acb9320","abstract_canon_sha256":"8c4a1c2e3bdb7b0fb352dace3cbbb76a1e4d863ed5cdccfdfd24430f27dfe78a"},"schema_version":"1.0"},"canonical_sha256":"a4245ff0a594ffd1382ec4c5857519ae9251825203eb7a9f03efe108fe8ceb3d","source":{"kind":"arxiv","id":"1802.04374","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04374","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04374v4","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04374","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"UQSF74FFST75","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UQSF74FFST75COBO","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UQSF74FF","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UQSF74FFST75COBOYTCYK5IZV2","target":"record","payload":{"canonical_record":{"source":{"id":"1802.04374","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-12T21:49:07Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"b696d3e221e1d1ca6245e3815fcb73e7baaee92f529de4373966e34f1acb9320","abstract_canon_sha256":"8c4a1c2e3bdb7b0fb352dace3cbbb76a1e4d863ed5cdccfdfd24430f27dfe78a"},"schema_version":"1.0"},"canonical_sha256":"a4245ff0a594ffd1382ec4c5857519ae9251825203eb7a9f03efe108fe8ceb3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:59.976014Z","signature_b64":"YUd8XDNinm3P4xAxHMAhUOTC16fJCkcXQB8bzh4WiC5u+Xj9UNU/dJuX3AYuE5VJn+na8dQkyBaEcNZ1Y99kCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4245ff0a594ffd1382ec4c5857519ae9251825203eb7a9f03efe108fe8ceb3d","last_reissued_at":"2026-05-18T00:10:59.975194Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:59.975194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.04374","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":"2026-05-18T00:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZRvpweDdSSVmeYOgNpvrh0TEXORWKTIF4IN755AoNWxyOozLI2XfGBMqU+g050vCTz/hqYRnHUOh5QWiImPICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T05:24:04.413004Z"},"content_sha256":"f9502d11ac15e6a633ecefb6c6d1a4809540ef5601278702b616f0cb60070f6d","schema_version":"1.0","event_id":"sha256:f9502d11ac15e6a633ecefb6c6d1a4809540ef5601278702b616f0cb60070f6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UQSF74FFST75COBOYTCYK5IZV2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tempered Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Arash Mehrjou, Bernhard Sch\\\"olkopf, Giambattista Parascandolo, Mehdi S. M. Sajjadi","submitted_at":"2018-02-12T21:49:07Z","abstract_excerpt":"Generative adversarial networks (GANs) have been shown to produce realistic samples from high-dimensional distributions, but training them is considered hard. A possible explanation for training instabilities is the inherent imbalance between the networks: While the discriminator is trained directly on both real and fake samples, the generator only has control over the fake samples it produces since the real data distribution is fixed by the choice of a given dataset. We propose a simple modification that gives the generator control over the real samples which leads to a tempered learning proc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04374","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":"2026-05-18T00:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2YDvuNy+ReP2V/MyV8Jbw+NX8c6Osxwzb2bzG/cTGYpSMoRiHKvcPVlX/v+FmAwJNUrM4vIoIxynwDSFve+TAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T05:24:04.413631Z"},"content_sha256":"f746c59ef96c7e0fe06f75eaf139d50ef1a4f6946aae90e34fa50a7883797628","schema_version":"1.0","event_id":"sha256:f746c59ef96c7e0fe06f75eaf139d50ef1a4f6946aae90e34fa50a7883797628"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UQSF74FFST75COBOYTCYK5IZV2/bundle.json","state_url":"https://pith.science/pith/UQSF74FFST75COBOYTCYK5IZV2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UQSF74FFST75COBOYTCYK5IZV2/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":"2026-05-19T05:24:04Z","links":{"resolver":"https://pith.science/pith/UQSF74FFST75COBOYTCYK5IZV2","bundle":"https://pith.science/pith/UQSF74FFST75COBOYTCYK5IZV2/bundle.json","state":"https://pith.science/pith/UQSF74FFST75COBOYTCYK5IZV2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UQSF74FFST75COBOYTCYK5IZV2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UQSF74FFST75COBOYTCYK5IZV2","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":"8c4a1c2e3bdb7b0fb352dace3cbbb76a1e4d863ed5cdccfdfd24430f27dfe78a","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-12T21:49:07Z","title_canon_sha256":"b696d3e221e1d1ca6245e3815fcb73e7baaee92f529de4373966e34f1acb9320"},"schema_version":"1.0","source":{"id":"1802.04374","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04374","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04374v4","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04374","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"UQSF74FFST75","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UQSF74FFST75COBO","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UQSF74FF","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:f746c59ef96c7e0fe06f75eaf139d50ef1a4f6946aae90e34fa50a7883797628","target":"graph","created_at":"2026-05-18T00:10:59Z","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 been shown to produce realistic samples from high-dimensional distributions, but training them is considered hard. A possible explanation for training instabilities is the inherent imbalance between the networks: While the discriminator is trained directly on both real and fake samples, the generator only has control over the fake samples it produces since the real data distribution is fixed by the choice of a given dataset. We propose a simple modification that gives the generator control over the real samples which leads to a tempered learning proc","authors_text":"Arash Mehrjou, Bernhard Sch\\\"olkopf, Giambattista Parascandolo, Mehdi S. M. Sajjadi","cross_cats":["cs.CR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-12T21:49:07Z","title":"Tempered Adversarial Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04374","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:f9502d11ac15e6a633ecefb6c6d1a4809540ef5601278702b616f0cb60070f6d","target":"record","created_at":"2026-05-18T00:10:59Z","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":"8c4a1c2e3bdb7b0fb352dace3cbbb76a1e4d863ed5cdccfdfd24430f27dfe78a","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-12T21:49:07Z","title_canon_sha256":"b696d3e221e1d1ca6245e3815fcb73e7baaee92f529de4373966e34f1acb9320"},"schema_version":"1.0","source":{"id":"1802.04374","kind":"arxiv","version":4}},"canonical_sha256":"a4245ff0a594ffd1382ec4c5857519ae9251825203eb7a9f03efe108fe8ceb3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4245ff0a594ffd1382ec4c5857519ae9251825203eb7a9f03efe108fe8ceb3d","first_computed_at":"2026-05-18T00:10:59.975194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:59.975194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YUd8XDNinm3P4xAxHMAhUOTC16fJCkcXQB8bzh4WiC5u+Xj9UNU/dJuX3AYuE5VJn+na8dQkyBaEcNZ1Y99kCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:59.976014Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04374","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9502d11ac15e6a633ecefb6c6d1a4809540ef5601278702b616f0cb60070f6d","sha256:f746c59ef96c7e0fe06f75eaf139d50ef1a4f6946aae90e34fa50a7883797628"],"state_sha256":"6e118e0f12bfb95273ef0ab6c59ca4dda8b880c9945f688d98d1324adb921bce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q2xb9ev0UeDNfiEx1kraqHZWw7YcuVXJajtSMYilxDsI0o9GRiNQldEsaPWojOy9TjDvam1TRDVVpKivH4VbBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T05:24:04.415751Z","bundle_sha256":"fc58d0a2f5035d5ff4c053c2eab055f3188688c3ff520e6e4980d2b134dc062c"}}