{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZHTKCM5PQ4XCT66QXRYUNVQIMN","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":"3be892bae5ccf4bef6a375a83a613891bb6764002579c65faa677428842756d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-08-16T16:10:23Z","title_canon_sha256":"3e124e37aacaedf33a848fa4665c2557d2d5364085c727369362638fd5262475"},"schema_version":"1.0","source":{"id":"1808.05561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.05561","created_at":"2026-05-18T00:07:56Z"},{"alias_kind":"arxiv_version","alias_value":"1808.05561v1","created_at":"2026-05-18T00:07:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05561","created_at":"2026-05-18T00:07:56Z"},{"alias_kind":"pith_short_12","alias_value":"ZHTKCM5PQ4XC","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZHTKCM5PQ4XCT66Q","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZHTKCM5P","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:db758a46419ebdf6f8f403b12d71fd55b8f9027bd322a0efe437726c2a2c4b3e","target":"graph","created_at":"2026-05-18T00:07:56Z","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":"Obtaining large, human labelled speech datasets to train models for emotion recognition is a notoriously challenging task, hindered by annotation cost and label ambiguity. In this work, we consider the task of learning embeddings for speech classification without access to any form of labelled audio. We base our approach on a simple hypothesis: that the emotional content of speech correlates with the facial expression of the speaker. By exploiting this relationship, we show that annotations of expression can be transferred from the visual domain (faces) to the speech domain (voices) through cr","authors_text":"Andrea Vedaldi, Andrew Zisserman, Arsha Nagrani, Samuel Albanie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-08-16T16:10:23Z","title":"Emotion Recognition in Speech using Cross-Modal Transfer in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05561","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":"sha256:11c20cc09a1cb9a1f05e461c382a680020412cade00ff074bc737a201bfca585","target":"record","created_at":"2026-05-18T00:07:56Z","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":"3be892bae5ccf4bef6a375a83a613891bb6764002579c65faa677428842756d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-08-16T16:10:23Z","title_canon_sha256":"3e124e37aacaedf33a848fa4665c2557d2d5364085c727369362638fd5262475"},"schema_version":"1.0","source":{"id":"1808.05561","kind":"arxiv","version":1}},"canonical_sha256":"c9e6a133af872e29fbd0bc7146d608635916fbe59148081629b1d134ad37ce7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9e6a133af872e29fbd0bc7146d608635916fbe59148081629b1d134ad37ce7d","first_computed_at":"2026-05-18T00:07:56.638840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:56.638840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FjI4b1IAsvkB7PaaB6IqNzaaQ7wTQkwUUlw8aFHHaEqP4clJzii3QtQpwZzOXF/UemDs4xn0b1odHiP5q7THAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:56.639299Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.05561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11c20cc09a1cb9a1f05e461c382a680020412cade00ff074bc737a201bfca585","sha256:db758a46419ebdf6f8f403b12d71fd55b8f9027bd322a0efe437726c2a2c4b3e"],"state_sha256":"373018c7a654d94ef59e7e185c6ee6902d0717c171c95144584e63b3cd0d2111"}