{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FFESSKJJRVYHZ7I3N75PMWS2OP","short_pith_number":"pith:FFESSKJJ","canonical_record":{"source":{"id":"2204.14057","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-28T07:28:56Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"bcaee68c2837d0401112795c3e01d6b719481e4cf9d7061dd77aceb8a79db0e3","abstract_canon_sha256":"95bada514eb192082616edbbeec16a5ae5a500bb1b55a78e830a16dd345485c4"},"schema_version":"1.0"},"canonical_sha256":"29492929298d707cfd1b6ffaf65a5a73f91e686df2a8d7b50bbf9778dd9416e4","source":{"kind":"arxiv","id":"2204.14057","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.14057","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"arxiv_version","alias_value":"2204.14057v3","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.14057","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"pith_short_12","alias_value":"FFESSKJJRVYH","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"pith_short_16","alias_value":"FFESSKJJRVYHZ7I3","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"pith_short_8","alias_value":"FFESSKJJ","created_at":"2026-07-05T04:26:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FFESSKJJRVYHZ7I3N75PMWS2OP","target":"record","payload":{"canonical_record":{"source":{"id":"2204.14057","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-28T07:28:56Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"bcaee68c2837d0401112795c3e01d6b719481e4cf9d7061dd77aceb8a79db0e3","abstract_canon_sha256":"95bada514eb192082616edbbeec16a5ae5a500bb1b55a78e830a16dd345485c4"},"schema_version":"1.0"},"canonical_sha256":"29492929298d707cfd1b6ffaf65a5a73f91e686df2a8d7b50bbf9778dd9416e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:49.189947Z","signature_b64":"H1MY02LEQXUhY452pLeQ1oC6UXkwJOioVu5VTtDVE6/lVk/BQAAOr2MZffCNgjutZ83DIwZbQ06qWLJ78x29AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29492929298d707cfd1b6ffaf65a5a73f91e686df2a8d7b50bbf9778dd9416e4","last_reissued_at":"2026-07-05T04:26:49.189438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:49.189438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.14057","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:26:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Id22K0C3j5+p4HJSdTuL8svoT2QQNuzFp4JLgymtIjvsMytT3ENr09UzseXxyGnZ9Dbp6U0/AcsAtMuT0D2RBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:24:37.754886Z"},"content_sha256":"cc1f413c42d4df382ed79b4f19553e5c23002c64e74e708fc23719334c7a2cfe","schema_version":"1.0","event_id":"sha256:cc1f413c42d4df382ed79b4f19553e5c23002c64e74e708fc23719334c7a2cfe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FFESSKJJRVYHZ7I3N75PMWS2OP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Boqing Zhu, Changjian Wang, Huaimin Wang, Kele Xu, Tao Sun, Yuxing Peng, Zheng Qin","submitted_at":"2022-04-28T07:28:56Z","abstract_excerpt":"We present an approach to learn voice-face representations from the talking face videos, without any identity labels. Previous works employ cross-modal instance discrimination tasks to establish the correlation of voice and face. These methods neglect the semantic content of different videos, introducing false-negative pairs as training noise. Furthermore, the positive pairs are constructed based on the natural correlation between audio clips and visual frames. However, this correlation might be weak or inaccurate in a large amount of real-world data, which leads to deviating positives into th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.14057","kind":"arxiv","version":3},"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/2204.14057/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":"2026-07-05T04:26:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VYb8K5mrurHE8+u0b2qmMJPr6ixI4K+eTOZGWv0hgFYKLCsjzjuUoBMhOMALnaCCM+UDtce96JxF+3HSeo0eDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:24:37.755779Z"},"content_sha256":"c5e4f997372a78b2fdab2ca07925800bcf9e674ee55841ad0a4cd66b3e4953b7","schema_version":"1.0","event_id":"sha256:c5e4f997372a78b2fdab2ca07925800bcf9e674ee55841ad0a4cd66b3e4953b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FFESSKJJRVYHZ7I3N75PMWS2OP/bundle.json","state_url":"https://pith.science/pith/FFESSKJJRVYHZ7I3N75PMWS2OP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FFESSKJJRVYHZ7I3N75PMWS2OP/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":"2026-08-07T10:24:37Z","links":{"resolver":"https://pith.science/pith/FFESSKJJRVYHZ7I3N75PMWS2OP","bundle":"https://pith.science/pith/FFESSKJJRVYHZ7I3N75PMWS2OP/bundle.json","state":"https://pith.science/pith/FFESSKJJRVYHZ7I3N75PMWS2OP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FFESSKJJRVYHZ7I3N75PMWS2OP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FFESSKJJRVYHZ7I3N75PMWS2OP","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":"95bada514eb192082616edbbeec16a5ae5a500bb1b55a78e830a16dd345485c4","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-28T07:28:56Z","title_canon_sha256":"bcaee68c2837d0401112795c3e01d6b719481e4cf9d7061dd77aceb8a79db0e3"},"schema_version":"1.0","source":{"id":"2204.14057","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.14057","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"arxiv_version","alias_value":"2204.14057v3","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.14057","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"pith_short_12","alias_value":"FFESSKJJRVYH","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"pith_short_16","alias_value":"FFESSKJJRVYHZ7I3","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"pith_short_8","alias_value":"FFESSKJJ","created_at":"2026-07-05T04:26:49Z"}],"graph_snapshots":[{"event_id":"sha256:c5e4f997372a78b2fdab2ca07925800bcf9e674ee55841ad0a4cd66b3e4953b7","target":"graph","created_at":"2026-07-05T04:26:49Z","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/2204.14057/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an approach to learn voice-face representations from the talking face videos, without any identity labels. Previous works employ cross-modal instance discrimination tasks to establish the correlation of voice and face. These methods neglect the semantic content of different videos, introducing false-negative pairs as training noise. Furthermore, the positive pairs are constructed based on the natural correlation between audio clips and visual frames. However, this correlation might be weak or inaccurate in a large amount of real-world data, which leads to deviating positives into th","authors_text":"Boqing Zhu, Changjian Wang, Huaimin Wang, Kele Xu, Tao Sun, Yuxing Peng, Zheng Qin","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-28T07:28:56Z","title":"Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.14057","kind":"arxiv","version":3},"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:cc1f413c42d4df382ed79b4f19553e5c23002c64e74e708fc23719334c7a2cfe","target":"record","created_at":"2026-07-05T04:26:49Z","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":"95bada514eb192082616edbbeec16a5ae5a500bb1b55a78e830a16dd345485c4","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-28T07:28:56Z","title_canon_sha256":"bcaee68c2837d0401112795c3e01d6b719481e4cf9d7061dd77aceb8a79db0e3"},"schema_version":"1.0","source":{"id":"2204.14057","kind":"arxiv","version":3}},"canonical_sha256":"29492929298d707cfd1b6ffaf65a5a73f91e686df2a8d7b50bbf9778dd9416e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29492929298d707cfd1b6ffaf65a5a73f91e686df2a8d7b50bbf9778dd9416e4","first_computed_at":"2026-07-05T04:26:49.189438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:49.189438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H1MY02LEQXUhY452pLeQ1oC6UXkwJOioVu5VTtDVE6/lVk/BQAAOr2MZffCNgjutZ83DIwZbQ06qWLJ78x29AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:49.189947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.14057","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc1f413c42d4df382ed79b4f19553e5c23002c64e74e708fc23719334c7a2cfe","sha256:c5e4f997372a78b2fdab2ca07925800bcf9e674ee55841ad0a4cd66b3e4953b7"],"state_sha256":"aa783af243109b382fce1fee4928db31bb7654e8b391e4690a4518a86e2f1895"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FL8yGrqoKyp7Jf73jKtmUbv2MlDV8NoHnkaq3ayYql+srxn+vPL46szG9+h5Mrv/1pxrd2WuDbSJZmT/OfqmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:24:37.762091Z","bundle_sha256":"b07aaa8da5b7711ded0c24fad47011159d9504efa1adecd3384f8b69513e3d97"}}