{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CBC3GW4C54MFADUWK5QHHJACFV","short_pith_number":"pith:CBC3GW4C","canonical_record":{"source":{"id":"1802.07421","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T04:31:51Z","cross_cats_sorted":[],"title_canon_sha256":"67795d9a28e9b18015e7deace765d0e8d503a07dfb553347d8d9bbc3021b7740","abstract_canon_sha256":"c80db9c7a2947180146f02c4dd6d68afb1ea850dfcdfb39be0f0c78edb2791f8"},"schema_version":"1.0"},"canonical_sha256":"1045b35b82ef18500e96576073a4022d4fbe027780b329ddb12d3b6fb2ecaf11","source":{"kind":"arxiv","id":"1802.07421","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07421","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07421v2","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07421","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"pith_short_12","alias_value":"CBC3GW4C54MF","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CBC3GW4C54MFADUW","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CBC3GW4C","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CBC3GW4C54MFADUWK5QHHJACFV","target":"record","payload":{"canonical_record":{"source":{"id":"1802.07421","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T04:31:51Z","cross_cats_sorted":[],"title_canon_sha256":"67795d9a28e9b18015e7deace765d0e8d503a07dfb553347d8d9bbc3021b7740","abstract_canon_sha256":"c80db9c7a2947180146f02c4dd6d68afb1ea850dfcdfb39be0f0c78edb2791f8"},"schema_version":"1.0"},"canonical_sha256":"1045b35b82ef18500e96576073a4022d4fbe027780b329ddb12d3b6fb2ecaf11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:43.417792Z","signature_b64":"Qa5k8Qc68IL0R4w7LyGu9EmvRTUdTE4QhAb3Uu8e42ZdkITp7tQuFZiWkCMDVqzFJlMnh1FQT2MiHP+QgAh3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1045b35b82ef18500e96576073a4022d4fbe027780b329ddb12d3b6fb2ecaf11","last_reissued_at":"2026-05-17T23:44:43.417300Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:43.417300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.07421","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":"2026-05-17T23:44:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sXdBPzgHOVjvuSaQv7LJJImOeeD4hqn3BzmRoficPgRK5MS8bEw2UuJXgOzlpyINaVD/BqEnHoyqgRICnfQtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:27:15.796910Z"},"content_sha256":"d233fadd1e361d9f4738a9110367ec178d445948f2636757d7e07a2a336b47af","schema_version":"1.0","event_id":"sha256:d233fadd1e361d9f4738a9110367ec178d445948f2636757d7e07a2a336b47af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CBC3GW4C54MFADUWK5QHHJACFV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conditional Adversarial Synthesis of 3D Facial Action Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoxian Song, Jianfei Cai, Juyong Zhang, Tat-Jen Cham, Zhilei Liu","submitted_at":"2018-02-21T04:31:51Z","abstract_excerpt":"Employing deep learning-based approaches for fine-grained facial expression analysis, such as those involving the estimation of Action Unit (AU) intensities, is difficult due to the lack of a large-scale dataset of real faces with sufficiently diverse AU labels for training. In this paper, we consider how AU-level facial image synthesis can be used to substantially augment such a dataset. We propose an AU synthesis framework that combines the well-known 3D Morphable Model (3DMM), which intrinsically disentangles expression parameters from other face attributes, with models that adversarially g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07421","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":"2026-05-17T23:44:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+8QD1NynznUSLM2nIWIjcPZuB8pto8DGwZ4rDdiVTGwSrccxu84a/QMtd6W7RyRSu/Ngfgi1Chg+ANGfgLF5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:27:15.797252Z"},"content_sha256":"8fbd506686df057de006c9d7c4d83397a2f09d7ebc5a75664eeb40db4b368b97","schema_version":"1.0","event_id":"sha256:8fbd506686df057de006c9d7c4d83397a2f09d7ebc5a75664eeb40db4b368b97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CBC3GW4C54MFADUWK5QHHJACFV/bundle.json","state_url":"https://pith.science/pith/CBC3GW4C54MFADUWK5QHHJACFV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CBC3GW4C54MFADUWK5QHHJACFV/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":"2026-06-01T03:27:15Z","links":{"resolver":"https://pith.science/pith/CBC3GW4C54MFADUWK5QHHJACFV","bundle":"https://pith.science/pith/CBC3GW4C54MFADUWK5QHHJACFV/bundle.json","state":"https://pith.science/pith/CBC3GW4C54MFADUWK5QHHJACFV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CBC3GW4C54MFADUWK5QHHJACFV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CBC3GW4C54MFADUWK5QHHJACFV","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":"c80db9c7a2947180146f02c4dd6d68afb1ea850dfcdfb39be0f0c78edb2791f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T04:31:51Z","title_canon_sha256":"67795d9a28e9b18015e7deace765d0e8d503a07dfb553347d8d9bbc3021b7740"},"schema_version":"1.0","source":{"id":"1802.07421","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07421","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07421v2","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07421","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"pith_short_12","alias_value":"CBC3GW4C54MF","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CBC3GW4C54MFADUW","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CBC3GW4C","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:8fbd506686df057de006c9d7c4d83397a2f09d7ebc5a75664eeb40db4b368b97","target":"graph","created_at":"2026-05-17T23:44:43Z","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":"Employing deep learning-based approaches for fine-grained facial expression analysis, such as those involving the estimation of Action Unit (AU) intensities, is difficult due to the lack of a large-scale dataset of real faces with sufficiently diverse AU labels for training. In this paper, we consider how AU-level facial image synthesis can be used to substantially augment such a dataset. We propose an AU synthesis framework that combines the well-known 3D Morphable Model (3DMM), which intrinsically disentangles expression parameters from other face attributes, with models that adversarially g","authors_text":"Guoxian Song, Jianfei Cai, Juyong Zhang, Tat-Jen Cham, Zhilei Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T04:31:51Z","title":"Conditional Adversarial Synthesis of 3D Facial Action Units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07421","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:d233fadd1e361d9f4738a9110367ec178d445948f2636757d7e07a2a336b47af","target":"record","created_at":"2026-05-17T23:44:43Z","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":"c80db9c7a2947180146f02c4dd6d68afb1ea850dfcdfb39be0f0c78edb2791f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T04:31:51Z","title_canon_sha256":"67795d9a28e9b18015e7deace765d0e8d503a07dfb553347d8d9bbc3021b7740"},"schema_version":"1.0","source":{"id":"1802.07421","kind":"arxiv","version":2}},"canonical_sha256":"1045b35b82ef18500e96576073a4022d4fbe027780b329ddb12d3b6fb2ecaf11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1045b35b82ef18500e96576073a4022d4fbe027780b329ddb12d3b6fb2ecaf11","first_computed_at":"2026-05-17T23:44:43.417300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:43.417300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qa5k8Qc68IL0R4w7LyGu9EmvRTUdTE4QhAb3Uu8e42ZdkITp7tQuFZiWkCMDVqzFJlMnh1FQT2MiHP+QgAh3AA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:43.417792Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.07421","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d233fadd1e361d9f4738a9110367ec178d445948f2636757d7e07a2a336b47af","sha256:8fbd506686df057de006c9d7c4d83397a2f09d7ebc5a75664eeb40db4b368b97"],"state_sha256":"5f1119f121183fd3997f04dfefb2baf59f3e992a6303866041cf0fe42d3baa55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oOjFrxorY74IYQl8Ao29CIUS45q4FjrBNup99UNosEPKUeTxMT/OTTujN7TkkP8EEtxnYoI/DqvlLLN6qo/WCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T03:27:15.799282Z","bundle_sha256":"53762e0f9ec1adb930964bcb7a792b46e21224d9d22f50d2dd9f8397a7b6928f"}}