{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y4IMBEQWWTMORHHU6XXXJBT5IU","short_pith_number":"pith:Y4IMBEQW","canonical_record":{"source":{"id":"2404.09509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T07:05:14Z","cross_cats_sorted":[],"title_canon_sha256":"e53b457f27d3b8e7275ea6cd6bcd26bd5a2a65493f24177df26c66d286b601e5","abstract_canon_sha256":"ce4947d58309b764d51b4077d146262032fe14d225349806557852558af4a7b0"},"schema_version":"1.0"},"canonical_sha256":"c710c09216b4d8e89cf4f5ef74867d450e668e2718902aa39fbbec69ad31324f","source":{"kind":"arxiv","id":"2404.09509","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09509","created_at":"2026-07-05T08:08:07Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09509v1","created_at":"2026-07-05T08:08:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09509","created_at":"2026-07-05T08:08:07Z"},{"alias_kind":"pith_short_12","alias_value":"Y4IMBEQWWTMO","created_at":"2026-07-05T08:08:07Z"},{"alias_kind":"pith_short_16","alias_value":"Y4IMBEQWWTMORHHU","created_at":"2026-07-05T08:08:07Z"},{"alias_kind":"pith_short_8","alias_value":"Y4IMBEQW","created_at":"2026-07-05T08:08:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y4IMBEQWWTMORHHU6XXXJBT5IU","target":"record","payload":{"canonical_record":{"source":{"id":"2404.09509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T07:05:14Z","cross_cats_sorted":[],"title_canon_sha256":"e53b457f27d3b8e7275ea6cd6bcd26bd5a2a65493f24177df26c66d286b601e5","abstract_canon_sha256":"ce4947d58309b764d51b4077d146262032fe14d225349806557852558af4a7b0"},"schema_version":"1.0"},"canonical_sha256":"c710c09216b4d8e89cf4f5ef74867d450e668e2718902aa39fbbec69ad31324f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:07.547016Z","signature_b64":"mri8ecV0bQQqW5bAZYTsqp2qUmQZAn+RBUVD7vfAmAJavk0nkWH0g2iP5te0Qj5zbaPfQOdYGWB1RhtlHXxGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c710c09216b4d8e89cf4f5ef74867d450e668e2718902aa39fbbec69ad31324f","last_reissued_at":"2026-07-05T08:08:07.546467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:07.546467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.09509","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":"2026-07-05T08:08:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pTqCFNMAcwW7+0v0EtEMsbHTh24XIkAHuyh/+JeSmh4iViSInISJtKkXaWBgkeP2P2YkmDmfoBblOXYR0nepDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:01:38.089612Z"},"content_sha256":"b82303cb56e0bea17ae072fdf898a37ae4703600227e867d84322d91a37ce9ff","schema_version":"1.0","event_id":"sha256:b82303cb56e0bea17ae072fdf898a37ae4703600227e867d84322d91a37ce9ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y4IMBEQWWTMORHHU6XXXJBT5IU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fuse after Align: Improving Face-Voice Association Learning via Multimodal Encoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Peng, Dan Su, Liqiang He","submitted_at":"2024-04-15T07:05:14Z","abstract_excerpt":"Today, there have been many achievements in learning the association between voice and face. However, most previous work models rely on cosine similarity or L2 distance to evaluate the likeness of voices and faces following contrastive learning, subsequently applied to retrieval and matching tasks. This method only considers the embeddings as high-dimensional vectors, utilizing a minimal scope of available information. This paper introduces a novel framework within an unsupervised setting for learning voice-face associations. By employing a multimodal encoder after contrastive learning and add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09509","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.09509/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T08:08:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UanurCl28ULMngvM4hEwB1C/4z/qc4KqQbvm3zfxUabh7mmEZoi9fXwx9iiKOs4+Q22D9zcZ4NWWabjgKxuUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:01:38.090340Z"},"content_sha256":"de4ac54156bbac2c7e500a23766061e16bb3150f5d40029a33d755c9ddc091d2","schema_version":"1.0","event_id":"sha256:de4ac54156bbac2c7e500a23766061e16bb3150f5d40029a33d755c9ddc091d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y4IMBEQWWTMORHHU6XXXJBT5IU/bundle.json","state_url":"https://pith.science/pith/Y4IMBEQWWTMORHHU6XXXJBT5IU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y4IMBEQWWTMORHHU6XXXJBT5IU/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":"2026-08-17T08:01:38Z","links":{"resolver":"https://pith.science/pith/Y4IMBEQWWTMORHHU6XXXJBT5IU","bundle":"https://pith.science/pith/Y4IMBEQWWTMORHHU6XXXJBT5IU/bundle.json","state":"https://pith.science/pith/Y4IMBEQWWTMORHHU6XXXJBT5IU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y4IMBEQWWTMORHHU6XXXJBT5IU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y4IMBEQWWTMORHHU6XXXJBT5IU","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":"ce4947d58309b764d51b4077d146262032fe14d225349806557852558af4a7b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T07:05:14Z","title_canon_sha256":"e53b457f27d3b8e7275ea6cd6bcd26bd5a2a65493f24177df26c66d286b601e5"},"schema_version":"1.0","source":{"id":"2404.09509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09509","created_at":"2026-07-05T08:08:07Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09509v1","created_at":"2026-07-05T08:08:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09509","created_at":"2026-07-05T08:08:07Z"},{"alias_kind":"pith_short_12","alias_value":"Y4IMBEQWWTMO","created_at":"2026-07-05T08:08:07Z"},{"alias_kind":"pith_short_16","alias_value":"Y4IMBEQWWTMORHHU","created_at":"2026-07-05T08:08:07Z"},{"alias_kind":"pith_short_8","alias_value":"Y4IMBEQW","created_at":"2026-07-05T08:08:07Z"}],"graph_snapshots":[{"event_id":"sha256:de4ac54156bbac2c7e500a23766061e16bb3150f5d40029a33d755c9ddc091d2","target":"graph","created_at":"2026-07-05T08:08:07Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.09509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Today, there have been many achievements in learning the association between voice and face. However, most previous work models rely on cosine similarity or L2 distance to evaluate the likeness of voices and faces following contrastive learning, subsequently applied to retrieval and matching tasks. This method only considers the embeddings as high-dimensional vectors, utilizing a minimal scope of available information. This paper introduces a novel framework within an unsupervised setting for learning voice-face associations. By employing a multimodal encoder after contrastive learning and add","authors_text":"Chong Peng, Dan Su, Liqiang He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T07:05:14Z","title":"Fuse after Align: Improving Face-Voice Association Learning via Multimodal Encoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09509","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:b82303cb56e0bea17ae072fdf898a37ae4703600227e867d84322d91a37ce9ff","target":"record","created_at":"2026-07-05T08:08:07Z","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":"ce4947d58309b764d51b4077d146262032fe14d225349806557852558af4a7b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T07:05:14Z","title_canon_sha256":"e53b457f27d3b8e7275ea6cd6bcd26bd5a2a65493f24177df26c66d286b601e5"},"schema_version":"1.0","source":{"id":"2404.09509","kind":"arxiv","version":1}},"canonical_sha256":"c710c09216b4d8e89cf4f5ef74867d450e668e2718902aa39fbbec69ad31324f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c710c09216b4d8e89cf4f5ef74867d450e668e2718902aa39fbbec69ad31324f","first_computed_at":"2026-07-05T08:08:07.546467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:07.546467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mri8ecV0bQQqW5bAZYTsqp2qUmQZAn+RBUVD7vfAmAJavk0nkWH0g2iP5te0Qj5zbaPfQOdYGWB1RhtlHXxGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:07.547016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b82303cb56e0bea17ae072fdf898a37ae4703600227e867d84322d91a37ce9ff","sha256:de4ac54156bbac2c7e500a23766061e16bb3150f5d40029a33d755c9ddc091d2"],"state_sha256":"5353277cafbd1b40322cc6df8cfe0ea073e62bec52bb5115188a474af5a0b0fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dWlg5MxLwsg6uOVexaUhiR6qAuzbfrqwNBQi33PwyrcSkz9GaiiDGEDXZnE/qTPII85m/IZmyrYzhCmQqpA4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T08:01:38.094715Z","bundle_sha256":"6b8255f33ad95cc61e546f7007af65e7fe4e4ac0c5f327df0ceb3f0189292b19"}}