{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2RP6KSPSZ2Z2HJNPNZ7ITNSBOP","short_pith_number":"pith:2RP6KSPS","canonical_record":{"source":{"id":"1905.03820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-09T19:14:26Z","cross_cats_sorted":[],"title_canon_sha256":"23169dbe48b905012d59c9a3761512110fb7f7c530c30ef317dbed6123b54f21","abstract_canon_sha256":"40fbe5e48d6a14dfe1b61427e9b305df68855718cf8cad945b68aaf2760a9c4a"},"schema_version":"1.0"},"canonical_sha256":"d45fe549f2ceb3a3a5af6e7e89b64173e7bcabf7738e0bec40a4a4c47edee62b","source":{"kind":"arxiv","id":"1905.03820","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.03820","created_at":"2026-05-17T23:46:35Z"},{"alias_kind":"arxiv_version","alias_value":"1905.03820v1","created_at":"2026-05-17T23:46:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03820","created_at":"2026-05-17T23:46:35Z"},{"alias_kind":"pith_short_12","alias_value":"2RP6KSPSZ2Z2","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2RP6KSPSZ2Z2HJNP","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2RP6KSPS","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2RP6KSPSZ2Z2HJNPNZ7ITNSBOP","target":"record","payload":{"canonical_record":{"source":{"id":"1905.03820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-09T19:14:26Z","cross_cats_sorted":[],"title_canon_sha256":"23169dbe48b905012d59c9a3761512110fb7f7c530c30ef317dbed6123b54f21","abstract_canon_sha256":"40fbe5e48d6a14dfe1b61427e9b305df68855718cf8cad945b68aaf2760a9c4a"},"schema_version":"1.0"},"canonical_sha256":"d45fe549f2ceb3a3a5af6e7e89b64173e7bcabf7738e0bec40a4a4c47edee62b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:35.531344Z","signature_b64":"FKrkSRXw7BHX5TorGjmgYmVlZC66zg2Q0KHyENPbdyZTrXiwk2rLcU6gOYuh9KyuhGpcIQd+h3JQGlsMeyC8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d45fe549f2ceb3a3a5af6e7e89b64173e7bcabf7738e0bec40a4a4c47edee62b","last_reissued_at":"2026-05-17T23:46:35.530799Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:35.530799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.03820","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wl6uoVxACH0UOcNVpO+4jMiULcx7XXBuDFka+G2U2GW2C3meLzsUUUZgWUWlc/w7ouzV4B1Awg6VwG7GuwjcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T05:31:51.795866Z"},"content_sha256":"d6af85fda65c71991f069c16c12a89b2769abbc8d2832a968c77c1b81adbd563","schema_version":"1.0","event_id":"sha256:d6af85fda65c71991f069c16c12a89b2769abbc8d2832a968c77c1b81adbd563"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2RP6KSPSZ2Z2HJNPNZ7ITNSBOP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Lele Chen, Ross K. Maddox, Zhiyao Duan","submitted_at":"2019-05-09T19:14:26Z","abstract_excerpt":"We devise a cascade GAN approach to generate talking face video, which is robust to different face shapes, view angles, facial characteristics, and noisy audio conditions. Instead of learning a direct mapping from audio to video frames, we propose first to transfer audio to high-level structure, i.e., the facial landmarks, and then to generate video frames conditioned on the landmarks. Compared to a direct audio-to-image approach, our cascade approach avoids fitting spurious correlations between audiovisual signals that are irrelevant to the speech content. We, humans, are sensitive to tempora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03820","kind":"arxiv","version":1},"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":"2026-05-17T23:46:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0rb51R6w37/rQYA/wCAONwo5+NHQBMDC9qaNs3dCfDs0fF1jV3jirLuwuIb/2XAAddt3hZeyLhyXYbusAQebAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T05:31:51.796369Z"},"content_sha256":"b8a4503648972798fa387f4cd247eba3b8d21f70b21f8ff4ec8df99e8adce2fa","schema_version":"1.0","event_id":"sha256:b8a4503648972798fa387f4cd247eba3b8d21f70b21f8ff4ec8df99e8adce2fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/bundle.json","state_url":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/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":"2026-05-24T05:31:51Z","links":{"resolver":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP","bundle":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/bundle.json","state":"https://pith.science/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2RP6KSPSZ2Z2HJNPNZ7ITNSBOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2RP6KSPSZ2Z2HJNPNZ7ITNSBOP","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":"40fbe5e48d6a14dfe1b61427e9b305df68855718cf8cad945b68aaf2760a9c4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-09T19:14:26Z","title_canon_sha256":"23169dbe48b905012d59c9a3761512110fb7f7c530c30ef317dbed6123b54f21"},"schema_version":"1.0","source":{"id":"1905.03820","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.03820","created_at":"2026-05-17T23:46:35Z"},{"alias_kind":"arxiv_version","alias_value":"1905.03820v1","created_at":"2026-05-17T23:46:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03820","created_at":"2026-05-17T23:46:35Z"},{"alias_kind":"pith_short_12","alias_value":"2RP6KSPSZ2Z2","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2RP6KSPSZ2Z2HJNP","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2RP6KSPS","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:b8a4503648972798fa387f4cd247eba3b8d21f70b21f8ff4ec8df99e8adce2fa","target":"graph","created_at":"2026-05-17T23:46:35Z","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 devise a cascade GAN approach to generate talking face video, which is robust to different face shapes, view angles, facial characteristics, and noisy audio conditions. Instead of learning a direct mapping from audio to video frames, we propose first to transfer audio to high-level structure, i.e., the facial landmarks, and then to generate video frames conditioned on the landmarks. Compared to a direct audio-to-image approach, our cascade approach avoids fitting spurious correlations between audiovisual signals that are irrelevant to the speech content. We, humans, are sensitive to tempora","authors_text":"Chenliang Xu, Lele Chen, Ross K. Maddox, Zhiyao Duan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-09T19:14:26Z","title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03820","kind":"arxiv","version":1},"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:d6af85fda65c71991f069c16c12a89b2769abbc8d2832a968c77c1b81adbd563","target":"record","created_at":"2026-05-17T23:46:35Z","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":"40fbe5e48d6a14dfe1b61427e9b305df68855718cf8cad945b68aaf2760a9c4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-09T19:14:26Z","title_canon_sha256":"23169dbe48b905012d59c9a3761512110fb7f7c530c30ef317dbed6123b54f21"},"schema_version":"1.0","source":{"id":"1905.03820","kind":"arxiv","version":1}},"canonical_sha256":"d45fe549f2ceb3a3a5af6e7e89b64173e7bcabf7738e0bec40a4a4c47edee62b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d45fe549f2ceb3a3a5af6e7e89b64173e7bcabf7738e0bec40a4a4c47edee62b","first_computed_at":"2026-05-17T23:46:35.530799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:35.530799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FKrkSRXw7BHX5TorGjmgYmVlZC66zg2Q0KHyENPbdyZTrXiwk2rLcU6gOYuh9KyuhGpcIQd+h3JQGlsMeyC8Cg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:35.531344Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.03820","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6af85fda65c71991f069c16c12a89b2769abbc8d2832a968c77c1b81adbd563","sha256:b8a4503648972798fa387f4cd247eba3b8d21f70b21f8ff4ec8df99e8adce2fa"],"state_sha256":"b6acc889b6bf9ccf42e419ae365236d585c81ddfa2dc4bd56118a6b9f3291bdc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lGE7kPugNr6UoPRGEObBepsKH4Jdrz5QxQrFW1405G8FMKJSmWX5sHX1fPomemwTd9Q1dITDy6xRxb9NFrseBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T05:31:51.800297Z","bundle_sha256":"e9ed830445e414af68d76f14beb06ff44e3fca4e6c8692049daee64164b59c65"}}