{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XUYPIL57P5CWLZ6Q6QOXNFWYLT","short_pith_number":"pith:XUYPIL57","canonical_record":{"source":{"id":"1905.09773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-23T16:54:17Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"7e333674281527b6c34b8e5c62b676388e114328244611da70aed20f765beb40","abstract_canon_sha256":"355d65523a239ecbbc00ec06fd7d74b6995e96838f17b000dd14266dbae67bbc"},"schema_version":"1.0"},"canonical_sha256":"bd30f42fbf7f4565e7d0f41d7696d85cd345a8d77bb8373f2de0a8c76c3b1b52","source":{"kind":"arxiv","id":"1905.09773","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09773","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09773v1","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09773","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"pith_short_12","alias_value":"XUYPIL57P5CW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XUYPIL57P5CWLZ6Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XUYPIL57","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XUYPIL57P5CWLZ6Q6QOXNFWYLT","target":"record","payload":{"canonical_record":{"source":{"id":"1905.09773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-23T16:54:17Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"7e333674281527b6c34b8e5c62b676388e114328244611da70aed20f765beb40","abstract_canon_sha256":"355d65523a239ecbbc00ec06fd7d74b6995e96838f17b000dd14266dbae67bbc"},"schema_version":"1.0"},"canonical_sha256":"bd30f42fbf7f4565e7d0f41d7696d85cd345a8d77bb8373f2de0a8c76c3b1b52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:16.080270Z","signature_b64":"kV4o819VlbTWIjABkoPOPkMvXY8LiELjwdyztzl66a7jUBJ/XVhZpzM7/6Z0NjT860Z98LTvgxuMb77FpC/0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd30f42fbf7f4565e7d0f41d7696d85cd345a8d77bb8373f2de0a8c76c3b1b52","last_reissued_at":"2026-05-17T23:45:16.079677Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:16.079677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.09773","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":"2026-05-17T23:45:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+MRi3uWCUFeYAFrnrPdsb2LKmrmwkJpqvKiS9JIpnLZupM0Mzy8mvDuRiZJUWhhQAZnSU0UtUvu35gCqm1VwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T08:12:47.240507Z"},"content_sha256":"c6902be749fc7931d9686e65a6a449e5d86f7b2ccdf3fb482ba11e49ca782c37","schema_version":"1.0","event_id":"sha256:c6902be749fc7931d9686e65a6a449e5d86f7b2ccdf3fb482ba11e49ca782c37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XUYPIL57P5CWLZ6Q6QOXNFWYLT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech2Face: Learning the Face Behind a Voice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Changil Kim, Inbar Mosseri, Michael Rubinstein, Tae-Hyun Oh, Tali Dekel, William T. Freeman, Wojciech Matusik","submitted_at":"2019-05-23T16:54:17Z","abstract_excerpt":"How much can we infer about a person's looks from the way they speak? In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of that person speaking. We design and train a deep neural network to perform this task using millions of natural Internet/YouTube videos of people speaking. During training, our model learns voice-face correlations that allow it to produce images that capture various physical attributes of the speakers such as age, gender and ethnicity. This is done in a self-supervised manner, by utilizing the natural co-occurrence of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09773","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":"2026-05-17T23:45:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"85OgYzi9VWwqghEn8OGcQzubftPI1ZcbyOuIslufxGoOKo6Z2knM///FZ2Jdx5/yxgMFH7VjlDiJ9rxC54rRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T08:12:47.245164Z"},"content_sha256":"3f2f9db36e1a48135d9c8789c1b00d7c3dcc998465612c5ab00c3f67c22ed6f8","schema_version":"1.0","event_id":"sha256:3f2f9db36e1a48135d9c8789c1b00d7c3dcc998465612c5ab00c3f67c22ed6f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT/bundle.json","state_url":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT/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":"2026-05-19T08:12:47Z","links":{"resolver":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT","bundle":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT/bundle.json","state":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XUYPIL57P5CWLZ6Q6QOXNFWYLT","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":"355d65523a239ecbbc00ec06fd7d74b6995e96838f17b000dd14266dbae67bbc","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-23T16:54:17Z","title_canon_sha256":"7e333674281527b6c34b8e5c62b676388e114328244611da70aed20f765beb40"},"schema_version":"1.0","source":{"id":"1905.09773","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09773","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09773v1","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09773","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"pith_short_12","alias_value":"XUYPIL57P5CW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XUYPIL57P5CWLZ6Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XUYPIL57","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:3f2f9db36e1a48135d9c8789c1b00d7c3dcc998465612c5ab00c3f67c22ed6f8","target":"graph","created_at":"2026-05-17T23:45:16Z","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":"How much can we infer about a person's looks from the way they speak? In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of that person speaking. We design and train a deep neural network to perform this task using millions of natural Internet/YouTube videos of people speaking. During training, our model learns voice-face correlations that allow it to produce images that capture various physical attributes of the speakers such as age, gender and ethnicity. This is done in a self-supervised manner, by utilizing the natural co-occurrence of","authors_text":"Changil Kim, Inbar Mosseri, Michael Rubinstein, Tae-Hyun Oh, Tali Dekel, William T. Freeman, Wojciech Matusik","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-23T16:54:17Z","title":"Speech2Face: Learning the Face Behind a Voice"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09773","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:c6902be749fc7931d9686e65a6a449e5d86f7b2ccdf3fb482ba11e49ca782c37","target":"record","created_at":"2026-05-17T23:45:16Z","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":"355d65523a239ecbbc00ec06fd7d74b6995e96838f17b000dd14266dbae67bbc","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-23T16:54:17Z","title_canon_sha256":"7e333674281527b6c34b8e5c62b676388e114328244611da70aed20f765beb40"},"schema_version":"1.0","source":{"id":"1905.09773","kind":"arxiv","version":1}},"canonical_sha256":"bd30f42fbf7f4565e7d0f41d7696d85cd345a8d77bb8373f2de0a8c76c3b1b52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd30f42fbf7f4565e7d0f41d7696d85cd345a8d77bb8373f2de0a8c76c3b1b52","first_computed_at":"2026-05-17T23:45:16.079677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:16.079677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kV4o819VlbTWIjABkoPOPkMvXY8LiELjwdyztzl66a7jUBJ/XVhZpzM7/6Z0NjT860Z98LTvgxuMb77FpC/0Aw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:16.080270Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.09773","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6902be749fc7931d9686e65a6a449e5d86f7b2ccdf3fb482ba11e49ca782c37","sha256:3f2f9db36e1a48135d9c8789c1b00d7c3dcc998465612c5ab00c3f67c22ed6f8"],"state_sha256":"bb5561647a3d5ccc3d64084fdad0124ff7bdbcde6d261d61980905b06df0200e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"meG6888xHhiw2reKKQePG1KWpscCDZRLRpAMrgRTkI6nHMF/Im+aaOR42Zva6rAN2twZDJ+h/PZLQqMm1ziyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T08:12:47.268342Z","bundle_sha256":"a7948e56e9f304e27f8cc3e61192db30dc19c33fb51ddb3112ef8445959041f8"}}