{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:YIVJUT42HIIT6JB3A5RMPKOIDM","short_pith_number":"pith:YIVJUT42","canonical_record":{"source":{"id":"1709.00536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-02T06:02:26Z","cross_cats_sorted":[],"title_canon_sha256":"0a97b27087a3a730c5a51470a1e50e1adee2ee4ce9abd828029b54d498317e71","abstract_canon_sha256":"7ad534c52bb649c1ca17abf26c563cf81fae1cbb9601d3213075534f9005bf61"},"schema_version":"1.0"},"canonical_sha256":"c22a9a4f9a3a113f243b0762c7a9c81b29e09c33e86df131ede4128b3ea5149f","source":{"kind":"arxiv","id":"1709.00536","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00536","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00536v1","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00536","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"pith_short_12","alias_value":"YIVJUT42HIIT","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YIVJUT42HIIT6JB3","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YIVJUT42","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:YIVJUT42HIIT6JB3A5RMPKOIDM","target":"record","payload":{"canonical_record":{"source":{"id":"1709.00536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-02T06:02:26Z","cross_cats_sorted":[],"title_canon_sha256":"0a97b27087a3a730c5a51470a1e50e1adee2ee4ce9abd828029b54d498317e71","abstract_canon_sha256":"7ad534c52bb649c1ca17abf26c563cf81fae1cbb9601d3213075534f9005bf61"},"schema_version":"1.0"},"canonical_sha256":"c22a9a4f9a3a113f243b0762c7a9c81b29e09c33e86df131ede4128b3ea5149f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:07.784756Z","signature_b64":"p3lKbdw/EhXukFOkUbinF4k9czvUJMGtpRMu8JzXJpRpFykzmCmLB2eIQA65Am3guShIjrn1sB4BAV3GfFUPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c22a9a4f9a3a113f243b0762c7a9c81b29e09c33e86df131ede4128b3ea5149f","last_reissued_at":"2026-05-18T00:36:07.783981Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:07.783981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.00536","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":"2026-05-18T00:36:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S+Pu1pT2xzN9vTAMK8xpr9S/CMt3nPVYmx/eWB7JdHGCRVQW24HSri7qhKB8jiqvCKyXwKfeu6dr9ohWzessAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T03:14:22.606728Z"},"content_sha256":"071b166574be337b5f91975e2955005dc0f4eced989ff217d18015be060db922","schema_version":"1.0","event_id":"sha256:071b166574be337b5f91975e2955005dc0f4eced989ff217d18015be060db922"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:YIVJUT42HIIT6JB3A5RMPKOIDM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Dense Facial Correspondences in Unconstrained Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duygu Ceylan, Hao Li, Haoxiang Li, Ronald Yu, Shunsuke Saito","submitted_at":"2017-09-02T06:02:26Z","abstract_excerpt":"We present a minimalistic but effective neural network that computes dense facial correspondences in highly unconstrained RGB images. Our network learns a per-pixel flow and a matchability mask between 2D input photographs of a person and the projection of a textured 3D face model. To train such a network, we generate a massive dataset of synthetic faces with dense labels using renderings of a morphable face model with variations in pose, expressions, lighting, and occlusions. We found that a training refinement using real photographs is required to drastically improve the ability to handle re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00536","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":"2026-05-18T00:36:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EgK8q3z5GfirczDh3czo+mtFeGzzFDMgzGEFXsvmkSOcnVQkudC9Y0w5JVLbwVQ6wMxRiGdobFqXF4jAP57DAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T03:14:22.607438Z"},"content_sha256":"52f0d00d86c851aa910f2ce27d708bcc85311a3752bed766a949eaba6ae96bdc","schema_version":"1.0","event_id":"sha256:52f0d00d86c851aa910f2ce27d708bcc85311a3752bed766a949eaba6ae96bdc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YIVJUT42HIIT6JB3A5RMPKOIDM/bundle.json","state_url":"https://pith.science/pith/YIVJUT42HIIT6JB3A5RMPKOIDM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YIVJUT42HIIT6JB3A5RMPKOIDM/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":"2026-05-20T03:14:22Z","links":{"resolver":"https://pith.science/pith/YIVJUT42HIIT6JB3A5RMPKOIDM","bundle":"https://pith.science/pith/YIVJUT42HIIT6JB3A5RMPKOIDM/bundle.json","state":"https://pith.science/pith/YIVJUT42HIIT6JB3A5RMPKOIDM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YIVJUT42HIIT6JB3A5RMPKOIDM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YIVJUT42HIIT6JB3A5RMPKOIDM","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":"7ad534c52bb649c1ca17abf26c563cf81fae1cbb9601d3213075534f9005bf61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-02T06:02:26Z","title_canon_sha256":"0a97b27087a3a730c5a51470a1e50e1adee2ee4ce9abd828029b54d498317e71"},"schema_version":"1.0","source":{"id":"1709.00536","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00536","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00536v1","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00536","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"pith_short_12","alias_value":"YIVJUT42HIIT","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YIVJUT42HIIT6JB3","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YIVJUT42","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:52f0d00d86c851aa910f2ce27d708bcc85311a3752bed766a949eaba6ae96bdc","target":"graph","created_at":"2026-05-18T00:36:07Z","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 present a minimalistic but effective neural network that computes dense facial correspondences in highly unconstrained RGB images. Our network learns a per-pixel flow and a matchability mask between 2D input photographs of a person and the projection of a textured 3D face model. To train such a network, we generate a massive dataset of synthetic faces with dense labels using renderings of a morphable face model with variations in pose, expressions, lighting, and occlusions. We found that a training refinement using real photographs is required to drastically improve the ability to handle re","authors_text":"Duygu Ceylan, Hao Li, Haoxiang Li, Ronald Yu, Shunsuke Saito","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-02T06:02:26Z","title":"Learning Dense Facial Correspondences in Unconstrained Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00536","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":"sha256:071b166574be337b5f91975e2955005dc0f4eced989ff217d18015be060db922","target":"record","created_at":"2026-05-18T00:36:07Z","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":"7ad534c52bb649c1ca17abf26c563cf81fae1cbb9601d3213075534f9005bf61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-02T06:02:26Z","title_canon_sha256":"0a97b27087a3a730c5a51470a1e50e1adee2ee4ce9abd828029b54d498317e71"},"schema_version":"1.0","source":{"id":"1709.00536","kind":"arxiv","version":1}},"canonical_sha256":"c22a9a4f9a3a113f243b0762c7a9c81b29e09c33e86df131ede4128b3ea5149f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c22a9a4f9a3a113f243b0762c7a9c81b29e09c33e86df131ede4128b3ea5149f","first_computed_at":"2026-05-18T00:36:07.783981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:07.783981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p3lKbdw/EhXukFOkUbinF4k9czvUJMGtpRMu8JzXJpRpFykzmCmLB2eIQA65Am3guShIjrn1sB4BAV3GfFUPCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:07.784756Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.00536","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:071b166574be337b5f91975e2955005dc0f4eced989ff217d18015be060db922","sha256:52f0d00d86c851aa910f2ce27d708bcc85311a3752bed766a949eaba6ae96bdc"],"state_sha256":"2ff40795c6942f5acae7be691d0e36b19163d208e649c8d42ea3ebb08e94b3f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xnNFXBlsyFNOh3tudUVWqxHJkdLgcFTsJNEKEuPamhQNCxUD6WQBNKthiWFI+xpVhDZFvCOWtGYlOaOmR8XuBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T03:14:22.611477Z","bundle_sha256":"82385289855487470cd2eaeb4cdeefc51465effeebb9eb970e2fd6dcc4502bfa"}}