{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:ZEUXVTI5PEUL6OTBR4TEZQHPKP","short_pith_number":"pith:ZEUXVTI5","canonical_record":{"source":{"id":"1610.01945","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-06T17:00:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c6c1cf3bc9b6aa3998d2eac24d420331234305b848c0eb2af69ec84670b12250","abstract_canon_sha256":"86480c754edda777bcca00201186b82dc8b996b47acead9c35d747617d0b51fa"},"schema_version":"1.0"},"canonical_sha256":"c9297acd1d7928bf3a618f264cc0ef53fe64aa69b4bed1da3a7dd340d148a1c2","source":{"kind":"arxiv","id":"1610.01945","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.01945","created_at":"2026-05-18T00:52:33Z"},{"alias_kind":"arxiv_version","alias_value":"1610.01945v3","created_at":"2026-05-18T00:52:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01945","created_at":"2026-05-18T00:52:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZEUXVTI5PEUL","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZEUXVTI5PEUL6OTB","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZEUXVTI5","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:ZEUXVTI5PEUL6OTBR4TEZQHPKP","target":"record","payload":{"canonical_record":{"source":{"id":"1610.01945","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-06T17:00:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c6c1cf3bc9b6aa3998d2eac24d420331234305b848c0eb2af69ec84670b12250","abstract_canon_sha256":"86480c754edda777bcca00201186b82dc8b996b47acead9c35d747617d0b51fa"},"schema_version":"1.0"},"canonical_sha256":"c9297acd1d7928bf3a618f264cc0ef53fe64aa69b4bed1da3a7dd340d148a1c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:33.956569Z","signature_b64":"TRDg6eX6q3W7+OchstpFBuNX/wzwmxCLXBurJc59DiQdymFSL8EdMCmNybDjtd9V+Ds53NohVCvFnXx2M5SACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9297acd1d7928bf3a618f264cc0ef53fe64aa69b4bed1da3a7dd340d148a1c2","last_reissued_at":"2026-05-18T00:52:33.956133Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:33.956133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.01945","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:52:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uiptDgkdOWeQ8D3g/wjI6McibJnt+covyEsW+iXBmD+mme0yuQJeM5kEZzzVCmZ8wBigbwKG5pyaiAbPpvn6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:50:19.091860Z"},"content_sha256":"e3261d475572c7a6ed4c8da70f8eb336040535558ccc96be716289d40d0de119","schema_version":"1.0","event_id":"sha256:e3261d475572c7a6ed4c8da70f8eb336040535558ccc96be716289d40d0de119"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:ZEUXVTI5PEUL6OTBR4TEZQHPKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Connecting Generative Adversarial Networks and Actor-Critic Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Pfau, Oriol Vinyals","submitted_at":"2016-10-06T17:00:54Z","abstract_excerpt":"Both generative adversarial networks (GAN) in unsupervised learning and actor-critic methods in reinforcement learning (RL) have gained a reputation for being difficult to optimize. Practitioners in both fields have amassed a large number of strategies to mitigate these instabilities and improve training. Here we show that GANs can be viewed as actor-critic methods in an environment where the actor cannot affect the reward. We review the strategies for stabilizing training for each class of models, both those that generalize between the two and those that are particular to that model. We also "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01945","kind":"arxiv","version":3},"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":"2026-05-18T00:52:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"coGDzNxEsT7kDeIKPt3hnxCF4a7AFL7TfVUyMthtkw24MX2Tm/zcYvwOS5P1rIFltGqiDCY9t1FaKm+nEMVECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:50:19.092217Z"},"content_sha256":"60b4fa7fc9b20f134285bb85a8fb09117fb0159e0ce5012861a2383609d98594","schema_version":"1.0","event_id":"sha256:60b4fa7fc9b20f134285bb85a8fb09117fb0159e0ce5012861a2383609d98594"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZEUXVTI5PEUL6OTBR4TEZQHPKP/bundle.json","state_url":"https://pith.science/pith/ZEUXVTI5PEUL6OTBR4TEZQHPKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZEUXVTI5PEUL6OTBR4TEZQHPKP/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":"2026-05-28T09:50:19Z","links":{"resolver":"https://pith.science/pith/ZEUXVTI5PEUL6OTBR4TEZQHPKP","bundle":"https://pith.science/pith/ZEUXVTI5PEUL6OTBR4TEZQHPKP/bundle.json","state":"https://pith.science/pith/ZEUXVTI5PEUL6OTBR4TEZQHPKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZEUXVTI5PEUL6OTBR4TEZQHPKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ZEUXVTI5PEUL6OTBR4TEZQHPKP","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":"86480c754edda777bcca00201186b82dc8b996b47acead9c35d747617d0b51fa","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-06T17:00:54Z","title_canon_sha256":"c6c1cf3bc9b6aa3998d2eac24d420331234305b848c0eb2af69ec84670b12250"},"schema_version":"1.0","source":{"id":"1610.01945","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.01945","created_at":"2026-05-18T00:52:33Z"},{"alias_kind":"arxiv_version","alias_value":"1610.01945v3","created_at":"2026-05-18T00:52:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01945","created_at":"2026-05-18T00:52:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZEUXVTI5PEUL","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZEUXVTI5PEUL6OTB","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZEUXVTI5","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:60b4fa7fc9b20f134285bb85a8fb09117fb0159e0ce5012861a2383609d98594","target":"graph","created_at":"2026-05-18T00:52:33Z","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":"Both generative adversarial networks (GAN) in unsupervised learning and actor-critic methods in reinforcement learning (RL) have gained a reputation for being difficult to optimize. Practitioners in both fields have amassed a large number of strategies to mitigate these instabilities and improve training. Here we show that GANs can be viewed as actor-critic methods in an environment where the actor cannot affect the reward. We review the strategies for stabilizing training for each class of models, both those that generalize between the two and those that are particular to that model. We also ","authors_text":"David Pfau, Oriol Vinyals","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-06T17:00:54Z","title":"Connecting Generative Adversarial Networks and Actor-Critic Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01945","kind":"arxiv","version":3},"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:e3261d475572c7a6ed4c8da70f8eb336040535558ccc96be716289d40d0de119","target":"record","created_at":"2026-05-18T00:52:33Z","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":"86480c754edda777bcca00201186b82dc8b996b47acead9c35d747617d0b51fa","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-06T17:00:54Z","title_canon_sha256":"c6c1cf3bc9b6aa3998d2eac24d420331234305b848c0eb2af69ec84670b12250"},"schema_version":"1.0","source":{"id":"1610.01945","kind":"arxiv","version":3}},"canonical_sha256":"c9297acd1d7928bf3a618f264cc0ef53fe64aa69b4bed1da3a7dd340d148a1c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9297acd1d7928bf3a618f264cc0ef53fe64aa69b4bed1da3a7dd340d148a1c2","first_computed_at":"2026-05-18T00:52:33.956133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:33.956133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TRDg6eX6q3W7+OchstpFBuNX/wzwmxCLXBurJc59DiQdymFSL8EdMCmNybDjtd9V+Ds53NohVCvFnXx2M5SACg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:33.956569Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.01945","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3261d475572c7a6ed4c8da70f8eb336040535558ccc96be716289d40d0de119","sha256:60b4fa7fc9b20f134285bb85a8fb09117fb0159e0ce5012861a2383609d98594"],"state_sha256":"b06ebb40c1b2ccefa0af43e4c7231d9aaf0835c51a2beedc542f08c5a1630684"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZTCqXFd89FbBdUvPg0tN7ibCwDoP67vOM8Qwyds5RVJJpgiKA8uzkTrj3edjC2JfpNK0l3jK+LlrSDXetrPjCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T09:50:19.094164Z","bundle_sha256":"5c32631d75f281fba29b0683074da5ee4569cfc40459f6dbbbdfc7b976c96d07"}}