{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:G3ACGLLD7IJF74ISXNGUAUA4WK","short_pith_number":"pith:G3ACGLLD","canonical_record":{"source":{"id":"2008.01910","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-08-05T02:33:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d0af9522e6ed805fa98ba80fe8b5adc2d1b8b8623241c06d4ac44ff4b613dfc8","abstract_canon_sha256":"0cc6731780c4a4fe4b245576e10f501e79417c7a22495563179e11b152b27a35"},"schema_version":"1.0"},"canonical_sha256":"36c0232d63fa125ff112bb4d40501cb2b75537988b2bbc22d63911583b4d2117","source":{"kind":"arxiv","id":"2008.01910","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.01910","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"arxiv_version","alias_value":"2008.01910v4","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.01910","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_12","alias_value":"G3ACGLLD7IJF","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_16","alias_value":"G3ACGLLD7IJF74IS","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_8","alias_value":"G3ACGLLD","created_at":"2026-07-05T04:56:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:G3ACGLLD7IJF74ISXNGUAUA4WK","target":"record","payload":{"canonical_record":{"source":{"id":"2008.01910","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-08-05T02:33:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d0af9522e6ed805fa98ba80fe8b5adc2d1b8b8623241c06d4ac44ff4b613dfc8","abstract_canon_sha256":"0cc6731780c4a4fe4b245576e10f501e79417c7a22495563179e11b152b27a35"},"schema_version":"1.0"},"canonical_sha256":"36c0232d63fa125ff112bb4d40501cb2b75537988b2bbc22d63911583b4d2117","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:56:09.609048Z","signature_b64":"Oy7UJhrqYLBUUzfasklctvStkJOBOjr5dNXITNfGm6JV3DwDCGqfcKsLIr/qbzXzoaSG3ix7kh8g+LjQ4HCqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36c0232d63fa125ff112bb4d40501cb2b75537988b2bbc22d63911583b4d2117","last_reissued_at":"2026-07-05T04:56:09.608619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:56:09.608619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.01910","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":"2026-07-05T04:56:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qDxZgRspTG+VeNIleDFF8n/DTG/CLDvj/kv4fzHWO6kqr96MbjsLb06b3uG4nX9oyQViL2Xybb+vn3iknAhgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:48:48.986021Z"},"content_sha256":"dddc1436642d26362463fda71fc12e5f8d2b3628d194166cfcfd7e699442766d","schema_version":"1.0","event_id":"sha256:dddc1436642d26362463fda71fc12e5f8d2b3628d194166cfcfd7e699442766d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:G3ACGLLD7IJF74ISXNGUAUA4WK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Junxiang Chen, Kayhan Batmanghelich, Ke Yu, Li Sun, Mingming Gong, Yanwu Xu","submitted_at":"2020-08-05T02:33:04Z","abstract_excerpt":"Generative Adversarial Networks (GAN) have many potential medical imaging applications, including data augmentation, domain adaptation, and model explanation. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D GAN models are trained on low-resolution medical images, these models either cannot scale to high-resolution or are prone to patchy artifacts. In this work, we propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. During training, we adopt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.01910","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.01910/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:56:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRRzZn1kc4cwyb/FBUdQxfPeWVL9bW8gIqog5ttjduK1NXDBDLJh16XfGBDdVdiTER38zbdidLjwLiSKNnsMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:48:48.986442Z"},"content_sha256":"524ccc2049bbee85d5481b9df2efdfa086054c3a57c84c37c46ec89bebda788e","schema_version":"1.0","event_id":"sha256:524ccc2049bbee85d5481b9df2efdfa086054c3a57c84c37c46ec89bebda788e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3ACGLLD7IJF74ISXNGUAUA4WK/bundle.json","state_url":"https://pith.science/pith/G3ACGLLD7IJF74ISXNGUAUA4WK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3ACGLLD7IJF74ISXNGUAUA4WK/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":"2026-08-05T01:48:48Z","links":{"resolver":"https://pith.science/pith/G3ACGLLD7IJF74ISXNGUAUA4WK","bundle":"https://pith.science/pith/G3ACGLLD7IJF74ISXNGUAUA4WK/bundle.json","state":"https://pith.science/pith/G3ACGLLD7IJF74ISXNGUAUA4WK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3ACGLLD7IJF74ISXNGUAUA4WK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:G3ACGLLD7IJF74ISXNGUAUA4WK","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":"0cc6731780c4a4fe4b245576e10f501e79417c7a22495563179e11b152b27a35","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-08-05T02:33:04Z","title_canon_sha256":"d0af9522e6ed805fa98ba80fe8b5adc2d1b8b8623241c06d4ac44ff4b613dfc8"},"schema_version":"1.0","source":{"id":"2008.01910","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.01910","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"arxiv_version","alias_value":"2008.01910v4","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.01910","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_12","alias_value":"G3ACGLLD7IJF","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_16","alias_value":"G3ACGLLD7IJF74IS","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_8","alias_value":"G3ACGLLD","created_at":"2026-07-05T04:56:09Z"}],"graph_snapshots":[{"event_id":"sha256:524ccc2049bbee85d5481b9df2efdfa086054c3a57c84c37c46ec89bebda788e","target":"graph","created_at":"2026-07-05T04:56:09Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2008.01910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative Adversarial Networks (GAN) have many potential medical imaging applications, including data augmentation, domain adaptation, and model explanation. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D GAN models are trained on low-resolution medical images, these models either cannot scale to high-resolution or are prone to patchy artifacts. In this work, we propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. During training, we adopt","authors_text":"Junxiang Chen, Kayhan Batmanghelich, Ke Yu, Li Sun, Mingming Gong, Yanwu Xu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-08-05T02:33:04Z","title":"Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.01910","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:dddc1436642d26362463fda71fc12e5f8d2b3628d194166cfcfd7e699442766d","target":"record","created_at":"2026-07-05T04:56:09Z","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":"0cc6731780c4a4fe4b245576e10f501e79417c7a22495563179e11b152b27a35","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-08-05T02:33:04Z","title_canon_sha256":"d0af9522e6ed805fa98ba80fe8b5adc2d1b8b8623241c06d4ac44ff4b613dfc8"},"schema_version":"1.0","source":{"id":"2008.01910","kind":"arxiv","version":4}},"canonical_sha256":"36c0232d63fa125ff112bb4d40501cb2b75537988b2bbc22d63911583b4d2117","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36c0232d63fa125ff112bb4d40501cb2b75537988b2bbc22d63911583b4d2117","first_computed_at":"2026-07-05T04:56:09.608619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:56:09.608619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oy7UJhrqYLBUUzfasklctvStkJOBOjr5dNXITNfGm6JV3DwDCGqfcKsLIr/qbzXzoaSG3ix7kh8g+LjQ4HCqBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:56:09.609048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.01910","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dddc1436642d26362463fda71fc12e5f8d2b3628d194166cfcfd7e699442766d","sha256:524ccc2049bbee85d5481b9df2efdfa086054c3a57c84c37c46ec89bebda788e"],"state_sha256":"cb9d4b33eeb9338be9abf3a6f5a3a69f5e7716594dd4b5d9d4fb4310461f0449"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+sfe2RUdSQ/KOAeX74bf551HFlpoBQLJVFzUDDTl5u5orQw5+Z1YrYXU97vWbD+vvox+QWdBzMF7fDC+U3sGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:48:48.988908Z","bundle_sha256":"834dc8cedbb9a9252ee96dd34722d9ea2c32a938c697cc7c4a1d08c6b58c8223"}}