{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VCIF3LNYHFZLHE2H2H7JBUNZRJ","short_pith_number":"pith:VCIF3LNY","canonical_record":{"source":{"id":"1801.02227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-07T18:44:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fa277eba6f2b08f8439432ca1313238559f6f4e0480badcaba3ef2de8513b28a","abstract_canon_sha256":"5de43020d115414d1ef1dada0c1bd466808bfd7e6d88469e4b677fe0f5c70a31"},"schema_version":"1.0"},"canonical_sha256":"a8905dadb83972b39347d1fe90d1b98a77537f95152d6c587011b3d146759e92","source":{"kind":"arxiv","id":"1801.02227","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.02227","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"arxiv_version","alias_value":"1801.02227v2","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.02227","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"pith_short_12","alias_value":"VCIF3LNYHFZL","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VCIF3LNYHFZLHE2H","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VCIF3LNY","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VCIF3LNYHFZLHE2H2H7JBUNZRJ","target":"record","payload":{"canonical_record":{"source":{"id":"1801.02227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-07T18:44:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fa277eba6f2b08f8439432ca1313238559f6f4e0480badcaba3ef2de8513b28a","abstract_canon_sha256":"5de43020d115414d1ef1dada0c1bd466808bfd7e6d88469e4b677fe0f5c70a31"},"schema_version":"1.0"},"canonical_sha256":"a8905dadb83972b39347d1fe90d1b98a77537f95152d6c587011b3d146759e92","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:19.429569Z","signature_b64":"z+2CiuIyqmsQzfxTIkcZ0gfTHw0UnX+xvLbk/+krr4zUMNP9MvI+kaCs9rtXMz9HjkOm36SPnCXMc1O20yYxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8905dadb83972b39347d1fe90d1b98a77537f95152d6c587011b3d146759e92","last_reissued_at":"2026-05-18T00:13:19.429128Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:19.429128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.02227","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":"2026-05-18T00:13:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zsuRmwU7ZD9ogDEiVuNnsWGJ/WVXkL9ArVq+ezq3k8OkcIzV+yAcH5KisHyaiUhQCCosood3mzOCxWCgtgTMAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:25:54.505989Z"},"content_sha256":"ea7d055eaabda9c843b37a1958bfa1a3a279bce629af52cd5e14603c4e9bc272","schema_version":"1.0","event_id":"sha256:ea7d055eaabda9c843b37a1958bfa1a3a279bce629af52cd5e14603c4e9bc272"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VCIF3LNYHFZLHE2H2H7JBUNZRJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Atsushi Nitanda, Taiji Suzuki","submitted_at":"2018-01-07T18:44:10Z","abstract_excerpt":"We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep network is expressed using a highly non-convex finite-dimensional model, and thus the parameter gets stuck in a local optimum. Because of this, methods often suffer not only from degeneration of the convergence speed but also from limitations in the representational power of the trained network. To overcome this issue, we propose an additional layer called the g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.02227","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":"2026-05-18T00:13:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hxjU5yMjfAsT8h9W8pZ9uxdplUZOqX53PXBrQH9NImCuR5fwxuDZzkJxJNtgsABINd07xHk9Q/gqBmWjMU+JDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:25:54.506839Z"},"content_sha256":"956620e9c888ff068e6a40138a67559081847b4377716df1fab92336cf3ac7f3","schema_version":"1.0","event_id":"sha256:956620e9c888ff068e6a40138a67559081847b4377716df1fab92336cf3ac7f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VCIF3LNYHFZLHE2H2H7JBUNZRJ/bundle.json","state_url":"https://pith.science/pith/VCIF3LNYHFZLHE2H2H7JBUNZRJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VCIF3LNYHFZLHE2H2H7JBUNZRJ/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":"2026-05-28T18:25:54Z","links":{"resolver":"https://pith.science/pith/VCIF3LNYHFZLHE2H2H7JBUNZRJ","bundle":"https://pith.science/pith/VCIF3LNYHFZLHE2H2H7JBUNZRJ/bundle.json","state":"https://pith.science/pith/VCIF3LNYHFZLHE2H2H7JBUNZRJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VCIF3LNYHFZLHE2H2H7JBUNZRJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VCIF3LNYHFZLHE2H2H7JBUNZRJ","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":"5de43020d115414d1ef1dada0c1bd466808bfd7e6d88469e4b677fe0f5c70a31","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-07T18:44:10Z","title_canon_sha256":"fa277eba6f2b08f8439432ca1313238559f6f4e0480badcaba3ef2de8513b28a"},"schema_version":"1.0","source":{"id":"1801.02227","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.02227","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"arxiv_version","alias_value":"1801.02227v2","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.02227","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"pith_short_12","alias_value":"VCIF3LNYHFZL","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VCIF3LNYHFZLHE2H","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VCIF3LNY","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:956620e9c888ff068e6a40138a67559081847b4377716df1fab92336cf3ac7f3","target":"graph","created_at":"2026-05-18T00:13:19Z","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":"We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep network is expressed using a highly non-convex finite-dimensional model, and thus the parameter gets stuck in a local optimum. Because of this, methods often suffer not only from degeneration of the convergence speed but also from limitations in the representational power of the trained network. To overcome this issue, we propose an additional layer called the g","authors_text":"Atsushi Nitanda, Taiji Suzuki","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-07T18:44:10Z","title":"Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.02227","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:ea7d055eaabda9c843b37a1958bfa1a3a279bce629af52cd5e14603c4e9bc272","target":"record","created_at":"2026-05-18T00:13:19Z","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":"5de43020d115414d1ef1dada0c1bd466808bfd7e6d88469e4b677fe0f5c70a31","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-07T18:44:10Z","title_canon_sha256":"fa277eba6f2b08f8439432ca1313238559f6f4e0480badcaba3ef2de8513b28a"},"schema_version":"1.0","source":{"id":"1801.02227","kind":"arxiv","version":2}},"canonical_sha256":"a8905dadb83972b39347d1fe90d1b98a77537f95152d6c587011b3d146759e92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8905dadb83972b39347d1fe90d1b98a77537f95152d6c587011b3d146759e92","first_computed_at":"2026-05-18T00:13:19.429128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:19.429128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z+2CiuIyqmsQzfxTIkcZ0gfTHw0UnX+xvLbk/+krr4zUMNP9MvI+kaCs9rtXMz9HjkOm36SPnCXMc1O20yYxCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:19.429569Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.02227","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea7d055eaabda9c843b37a1958bfa1a3a279bce629af52cd5e14603c4e9bc272","sha256:956620e9c888ff068e6a40138a67559081847b4377716df1fab92336cf3ac7f3"],"state_sha256":"ca92ad9ec4191e7c799a3e867e75359817eb07b2543e21e5c2563b4fe7564b1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nO9SXJ87NBK6Qby96Q71cGrfwUDaSZb117hfoZKvbUh7Niqb1LlOSnWEa99FIRJWrvOEMEXVXkIY1oZOXPKBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T18:25:54.510600Z","bundle_sha256":"e60fc1359686f8ca2435b7ffb4ff5b70bfb8c395aaea1841b1300ab7358499ab"}}