{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5EUM4EQVLH3G6EOKGZIZRWJWUS","short_pith_number":"pith:5EUM4EQV","canonical_record":{"source":{"id":"2407.17902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-25T09:46:04Z","cross_cats_sorted":[],"title_canon_sha256":"3cdbf4cee0d4fac861f53858ecdedc24c910ce04bcadc239d6ae12b7da97a102","abstract_canon_sha256":"b23a8ede87bea3511200a2012cf325550767de420140e6a50ddb4e979a920d9c"},"schema_version":"1.0"},"canonical_sha256":"e928ce121559f66f11ca365198d936a4bd7fb13dce8547065915b7910ec9fffd","source":{"kind":"arxiv","id":"2407.17902","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17902","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17902v1","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17902","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"pith_short_12","alias_value":"5EUM4EQVLH3G","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"pith_short_16","alias_value":"5EUM4EQVLH3G6EOK","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"pith_short_8","alias_value":"5EUM4EQV","created_at":"2026-07-05T08:48:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5EUM4EQVLH3G6EOKGZIZRWJWUS","target":"record","payload":{"canonical_record":{"source":{"id":"2407.17902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-25T09:46:04Z","cross_cats_sorted":[],"title_canon_sha256":"3cdbf4cee0d4fac861f53858ecdedc24c910ce04bcadc239d6ae12b7da97a102","abstract_canon_sha256":"b23a8ede87bea3511200a2012cf325550767de420140e6a50ddb4e979a920d9c"},"schema_version":"1.0"},"canonical_sha256":"e928ce121559f66f11ca365198d936a4bd7fb13dce8547065915b7910ec9fffd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:23.237481Z","signature_b64":"VMwaeqDONsj+AHrHBpm5QskGijhKpI1dKHPZwkTNnGHNAg16s/pFu9n8JLn1nKapYjCA+ubAlCUnLaENEa4kBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e928ce121559f66f11ca365198d936a4bd7fb13dce8547065915b7910ec9fffd","last_reissued_at":"2026-07-05T08:48:23.236999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:23.236999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.17902","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":"2026-07-05T08:48:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9pz0KrX4Xq2wfHtfPN+3FQ9EXjx0VibexAFoWCil2TLb2PPVywSn0BrzZCuYAAzCh3ddfxMWv9deSW9hCLo/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:37:31.817567Z"},"content_sha256":"5ce2ecc06f97041a07ff6d889e134e88501c0c1c6671451e1a7231b2d5f7fa25","schema_version":"1.0","event_id":"sha256:5ce2ecc06f97041a07ff6d889e134e88501c0c1c6671451e1a7231b2d5f7fa25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5EUM4EQVLH3G6EOKGZIZRWJWUS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Duc-Tuan Truong, Eng-Siong Chng, Haizhou Li, Massimo Alioto, Ruijie Tao, Yidi Jiang, Zhan Shi","submitted_at":"2024-07-25T09:46:04Z","abstract_excerpt":"The human brain has the capability to associate the unknown person's voice and face by leveraging their general relationship, referred to as ``cross-modal speaker verification''. This task poses significant challenges due to the complex relationship between the modalities. In this paper, we propose a ``Multi-stage Face-voice Association Learning with Keynote Speaker Diarization''~(MFV-KSD) framework. MFV-KSD contains a keynote speaker diarization front-end to effectively address the noisy speech inputs issue. To balance and enhance the intra-modal feature learning and inter-modal correlation u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17902","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/2407.17902/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":"2026-07-05T08:48:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2c3G9k/+n3V7fXKaY58GNa5QXLgXQ7hrrTKs6CZznKCZuM//yMD360cvabCKU0drYRnVHoIN2PctebJAtiQYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:37:31.818215Z"},"content_sha256":"8d0d1e2321186f7bce2cead0041c05f2e6a1cfd0843c710ed655a5daef4f026d","schema_version":"1.0","event_id":"sha256:8d0d1e2321186f7bce2cead0041c05f2e6a1cfd0843c710ed655a5daef4f026d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5EUM4EQVLH3G6EOKGZIZRWJWUS/bundle.json","state_url":"https://pith.science/pith/5EUM4EQVLH3G6EOKGZIZRWJWUS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5EUM4EQVLH3G6EOKGZIZRWJWUS/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":"2026-08-17T02:37:31Z","links":{"resolver":"https://pith.science/pith/5EUM4EQVLH3G6EOKGZIZRWJWUS","bundle":"https://pith.science/pith/5EUM4EQVLH3G6EOKGZIZRWJWUS/bundle.json","state":"https://pith.science/pith/5EUM4EQVLH3G6EOKGZIZRWJWUS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5EUM4EQVLH3G6EOKGZIZRWJWUS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5EUM4EQVLH3G6EOKGZIZRWJWUS","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":"b23a8ede87bea3511200a2012cf325550767de420140e6a50ddb4e979a920d9c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-25T09:46:04Z","title_canon_sha256":"3cdbf4cee0d4fac861f53858ecdedc24c910ce04bcadc239d6ae12b7da97a102"},"schema_version":"1.0","source":{"id":"2407.17902","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17902","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17902v1","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17902","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"pith_short_12","alias_value":"5EUM4EQVLH3G","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"pith_short_16","alias_value":"5EUM4EQVLH3G6EOK","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"pith_short_8","alias_value":"5EUM4EQV","created_at":"2026-07-05T08:48:23Z"}],"graph_snapshots":[{"event_id":"sha256:8d0d1e2321186f7bce2cead0041c05f2e6a1cfd0843c710ed655a5daef4f026d","target":"graph","created_at":"2026-07-05T08:48:23Z","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/2407.17902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The human brain has the capability to associate the unknown person's voice and face by leveraging their general relationship, referred to as ``cross-modal speaker verification''. This task poses significant challenges due to the complex relationship between the modalities. In this paper, we propose a ``Multi-stage Face-voice Association Learning with Keynote Speaker Diarization''~(MFV-KSD) framework. MFV-KSD contains a keynote speaker diarization front-end to effectively address the noisy speech inputs issue. To balance and enhance the intra-modal feature learning and inter-modal correlation u","authors_text":"Duc-Tuan Truong, Eng-Siong Chng, Haizhou Li, Massimo Alioto, Ruijie Tao, Yidi Jiang, Zhan Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-25T09:46:04Z","title":"Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17902","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":"sha256:5ce2ecc06f97041a07ff6d889e134e88501c0c1c6671451e1a7231b2d5f7fa25","target":"record","created_at":"2026-07-05T08:48:23Z","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":"b23a8ede87bea3511200a2012cf325550767de420140e6a50ddb4e979a920d9c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-25T09:46:04Z","title_canon_sha256":"3cdbf4cee0d4fac861f53858ecdedc24c910ce04bcadc239d6ae12b7da97a102"},"schema_version":"1.0","source":{"id":"2407.17902","kind":"arxiv","version":1}},"canonical_sha256":"e928ce121559f66f11ca365198d936a4bd7fb13dce8547065915b7910ec9fffd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e928ce121559f66f11ca365198d936a4bd7fb13dce8547065915b7910ec9fffd","first_computed_at":"2026-07-05T08:48:23.236999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:23.236999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VMwaeqDONsj+AHrHBpm5QskGijhKpI1dKHPZwkTNnGHNAg16s/pFu9n8JLn1nKapYjCA+ubAlCUnLaENEa4kBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:23.237481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.17902","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ce2ecc06f97041a07ff6d889e134e88501c0c1c6671451e1a7231b2d5f7fa25","sha256:8d0d1e2321186f7bce2cead0041c05f2e6a1cfd0843c710ed655a5daef4f026d"],"state_sha256":"2f9e5677999cd513a93a21724724d1f9c31d0c96c979c3b0b413859b8f15324a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X/tH6OCpVAVbdAj3HZ2/1Fc4mKzxSH7/bZW3F3YYXYZMl4KbA3R5bhJ2Hsi53QRelZ+fuaIAhWdGJilO6DtpAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T02:37:31.822902Z","bundle_sha256":"7a37b6b3e7571481f7e201a7b418302666312ecdc76d638fef83d3a0979c1273"}}