{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4PEJF4X5RWFZFUQQEYOGTFZIOL","short_pith_number":"pith:4PEJF4X5","canonical_record":{"source":{"id":"1803.08647","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-23T03:46:12Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"114e8b44b80aa64e7eea254ba3cfb47a407cd078c57225f1d663fe261e60b5d1","abstract_canon_sha256":"fed9bcb31d08322072688bcc802b2ea3b8558c9d7d564007db33c38d830a1440"},"schema_version":"1.0"},"canonical_sha256":"e3c892f2fd8d8b92d210261c69972872db0428116982a3af0e96da66fe4e4207","source":{"kind":"arxiv","id":"1803.08647","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.08647","created_at":"2026-05-18T00:10:54Z"},{"alias_kind":"arxiv_version","alias_value":"1803.08647v2","created_at":"2026-05-18T00:10:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08647","created_at":"2026-05-18T00:10:54Z"},{"alias_kind":"pith_short_12","alias_value":"4PEJF4X5RWFZ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4PEJF4X5RWFZFUQQ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4PEJF4X5","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4PEJF4X5RWFZFUQQEYOGTFZIOL","target":"record","payload":{"canonical_record":{"source":{"id":"1803.08647","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-23T03:46:12Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"114e8b44b80aa64e7eea254ba3cfb47a407cd078c57225f1d663fe261e60b5d1","abstract_canon_sha256":"fed9bcb31d08322072688bcc802b2ea3b8558c9d7d564007db33c38d830a1440"},"schema_version":"1.0"},"canonical_sha256":"e3c892f2fd8d8b92d210261c69972872db0428116982a3af0e96da66fe4e4207","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:54.407494Z","signature_b64":"/9q0ppmf+HPCZPAmHFTaH3f9xf1MYRglG+GFTRE00SEKVj2+OfV3NfuYSSIu/WxCMxhg6TW3idDBwMvPgrCWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3c892f2fd8d8b92d210261c69972872db0428116982a3af0e96da66fe4e4207","last_reissued_at":"2026-05-18T00:10:54.406749Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:54.406749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.08647","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:10:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AGEa3MKaGtOigKKoIYKHiMVjaSeGfhmTFknUNVDcXhBznQtJk6jR7YpvYzN/qTUdyBgR37w4fpiRb+cIUEKLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:17:33.331766Z"},"content_sha256":"f63f2de6389fbf141b8579e4aa8ad9fadd14e6583c9800f15609fc40820de304","schema_version":"1.0","event_id":"sha256:f63f2de6389fbf141b8579e4aa8ad9fadd14e6583c9800f15609fc40820de304"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4PEJF4X5RWFZFUQQEYOGTFZIOL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fictitious GAN: Training GANs with Historical Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Ge, Randall Berry, Xu Chen, Ying Wu, Yin Xia","submitted_at":"2018-03-23T03:46:12Z","abstract_excerpt":"Generative adversarial networks (GANs) are powerful tools for learning generative models. In practice, the training may suffer from lack of convergence. GANs are commonly viewed as a two-player zero-sum game between two neural networks. Here, we leverage this game theoretic view to study the convergence behavior of the training process. Inspired by the fictitious play learning process, a novel training method, referred to as Fictitious GAN, is introduced. Fictitious GAN trains the deep neural networks using a mixture of historical models. Specifically, the discriminator (resp. generator) is up"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08647","kind":"arxiv","version":2},"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":"2026-05-18T00:10:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2caa/bV1pZohhC/oDqtB8SdnNP9V6yu66lnhfchj5HSFBr5IgKRSUZmwKxviu+MOd6uV6rdg2ilHFZmsH1LkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:17:33.332130Z"},"content_sha256":"c4d6ce6fc762ddbb3ba1c5e5b02567e4826f21b948614e64221facb307b603d3","schema_version":"1.0","event_id":"sha256:c4d6ce6fc762ddbb3ba1c5e5b02567e4826f21b948614e64221facb307b603d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4PEJF4X5RWFZFUQQEYOGTFZIOL/bundle.json","state_url":"https://pith.science/pith/4PEJF4X5RWFZFUQQEYOGTFZIOL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4PEJF4X5RWFZFUQQEYOGTFZIOL/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":"2026-05-30T07:17:33Z","links":{"resolver":"https://pith.science/pith/4PEJF4X5RWFZFUQQEYOGTFZIOL","bundle":"https://pith.science/pith/4PEJF4X5RWFZFUQQEYOGTFZIOL/bundle.json","state":"https://pith.science/pith/4PEJF4X5RWFZFUQQEYOGTFZIOL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4PEJF4X5RWFZFUQQEYOGTFZIOL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4PEJF4X5RWFZFUQQEYOGTFZIOL","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":"fed9bcb31d08322072688bcc802b2ea3b8558c9d7d564007db33c38d830a1440","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-23T03:46:12Z","title_canon_sha256":"114e8b44b80aa64e7eea254ba3cfb47a407cd078c57225f1d663fe261e60b5d1"},"schema_version":"1.0","source":{"id":"1803.08647","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.08647","created_at":"2026-05-18T00:10:54Z"},{"alias_kind":"arxiv_version","alias_value":"1803.08647v2","created_at":"2026-05-18T00:10:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08647","created_at":"2026-05-18T00:10:54Z"},{"alias_kind":"pith_short_12","alias_value":"4PEJF4X5RWFZ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4PEJF4X5RWFZFUQQ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4PEJF4X5","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:c4d6ce6fc762ddbb3ba1c5e5b02567e4826f21b948614e64221facb307b603d3","target":"graph","created_at":"2026-05-18T00:10:54Z","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 powerful tools for learning generative models. In practice, the training may suffer from lack of convergence. GANs are commonly viewed as a two-player zero-sum game between two neural networks. Here, we leverage this game theoretic view to study the convergence behavior of the training process. Inspired by the fictitious play learning process, a novel training method, referred to as Fictitious GAN, is introduced. Fictitious GAN trains the deep neural networks using a mixture of historical models. Specifically, the discriminator (resp. generator) is up","authors_text":"Hao Ge, Randall Berry, Xu Chen, Ying Wu, Yin Xia","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-23T03:46:12Z","title":"Fictitious GAN: Training GANs with Historical Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08647","kind":"arxiv","version":2},"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:f63f2de6389fbf141b8579e4aa8ad9fadd14e6583c9800f15609fc40820de304","target":"record","created_at":"2026-05-18T00:10:54Z","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":"fed9bcb31d08322072688bcc802b2ea3b8558c9d7d564007db33c38d830a1440","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-23T03:46:12Z","title_canon_sha256":"114e8b44b80aa64e7eea254ba3cfb47a407cd078c57225f1d663fe261e60b5d1"},"schema_version":"1.0","source":{"id":"1803.08647","kind":"arxiv","version":2}},"canonical_sha256":"e3c892f2fd8d8b92d210261c69972872db0428116982a3af0e96da66fe4e4207","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3c892f2fd8d8b92d210261c69972872db0428116982a3af0e96da66fe4e4207","first_computed_at":"2026-05-18T00:10:54.406749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:54.406749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/9q0ppmf+HPCZPAmHFTaH3f9xf1MYRglG+GFTRE00SEKVj2+OfV3NfuYSSIu/WxCMxhg6TW3idDBwMvPgrCWDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:54.407494Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.08647","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f63f2de6389fbf141b8579e4aa8ad9fadd14e6583c9800f15609fc40820de304","sha256:c4d6ce6fc762ddbb3ba1c5e5b02567e4826f21b948614e64221facb307b603d3"],"state_sha256":"249e14f9ce3b536d5c7fbbd435b23c900f1be1ae6048e7ce9ba8ada3df5abe06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ysSnHOx7wds6YsKn7T405WUZc4XlcYdposPEltFl+FcO8XJ5DV7CkJwW3Q57cjsKIbx5DzM2FzR210Ukjo8XCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:17:33.334903Z","bundle_sha256":"3ed7f6a0dc1d13e8e49bd3c0d84826d6b209d546b8e637eec0a1a27a8e39eb1a"}}