{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C5NDX7J7JTAMXMRYH465I7DJWT","short_pith_number":"pith:C5NDX7J7","canonical_record":{"source":{"id":"2407.11510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-16T08:49:30Z","cross_cats_sorted":[],"title_canon_sha256":"c4632237163da98fa153205cd74f9c4c751a843426c3d5eea99c88027cb5fb90","abstract_canon_sha256":"148be633944231345a941e68f1916e3e29d725b865a01739b46ee62f1105e4b0"},"schema_version":"1.0"},"canonical_sha256":"175a3bfd3f4cc0cbb2383f3dd47c69b4e847779f618af012ca3e2df28c28952d","source":{"kind":"arxiv","id":"2407.11510","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11510","created_at":"2026-07-05T08:44:25Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11510v1","created_at":"2026-07-05T08:44:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11510","created_at":"2026-07-05T08:44:25Z"},{"alias_kind":"pith_short_12","alias_value":"C5NDX7J7JTAM","created_at":"2026-07-05T08:44:25Z"},{"alias_kind":"pith_short_16","alias_value":"C5NDX7J7JTAMXMRY","created_at":"2026-07-05T08:44:25Z"},{"alias_kind":"pith_short_8","alias_value":"C5NDX7J7","created_at":"2026-07-05T08:44:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C5NDX7J7JTAMXMRYH465I7DJWT","target":"record","payload":{"canonical_record":{"source":{"id":"2407.11510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-16T08:49:30Z","cross_cats_sorted":[],"title_canon_sha256":"c4632237163da98fa153205cd74f9c4c751a843426c3d5eea99c88027cb5fb90","abstract_canon_sha256":"148be633944231345a941e68f1916e3e29d725b865a01739b46ee62f1105e4b0"},"schema_version":"1.0"},"canonical_sha256":"175a3bfd3f4cc0cbb2383f3dd47c69b4e847779f618af012ca3e2df28c28952d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:25.529617Z","signature_b64":"AQvEXiswQIiqdkgITe2zlLJ2JbAYIrq3YQCtIezFrcTDwhTamD5yvMpbSSAKq5vvjfW22sG8y0aOZSVam/R2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"175a3bfd3f4cc0cbb2383f3dd47c69b4e847779f618af012ca3e2df28c28952d","last_reissued_at":"2026-07-05T08:44:25.529187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:25.529187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.11510","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":"2026-07-05T08:44:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z/TT3Avd/iNVALtJ+g7QEQmZelKjJXtSsUSnVLh5jXW7Bg9LXxtDd4Di0GnIbgWN4uXHVY+o9EGiJyaOPsjcCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:41:01.980740Z"},"content_sha256":"9f6e35f546671d3aef2c3dfc222acf29e8fa0e17c371f93f5b17c1faf7e316e0","schema_version":"1.0","event_id":"sha256:9f6e35f546671d3aef2c3dfc222acf29e8fa0e17c371f93f5b17c1faf7e316e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C5NDX7J7JTAMXMRYH465I7DJWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Fulin Zhang, Ming Cheng, Ming Li, Shilei Zhang, Yingying Gao, Yuke Lin","submitted_at":"2024-07-16T08:49:30Z","abstract_excerpt":"In this paper, we provide a large audio-visual speaker recognition dataset, VoxBlink2, which includes approximately 10M utterances with videos from 110K+ speakers in the wild. This dataset represents a significant expansion over the VoxBlink dataset, encompassing a broader diversity of speakers and scenarios by the grace of an optimized data collection pipeline. Afterward, we explore the impact of training strategies, data scale, and model complexity on speaker verification and finally establish a new single-model state-of-the-art EER at 0.170% and minDCF at 0.006% on the VoxCeleb1-O test set."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11510","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/2407.11510/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":"2026-07-05T08:44:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XXlw4WywPHNBxHUVGMX1HvOrskeWOt9T7Dyi5aSEE+R+SyQJyuUhnIMl33VMMhhMCX/QgujHOgIYKx17RvJDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:41:01.981272Z"},"content_sha256":"dffd2dd1b7bc28fd6c2073b372adb8493ffd9c9054040373c2c7c53d6b609831","schema_version":"1.0","event_id":"sha256:dffd2dd1b7bc28fd6c2073b372adb8493ffd9c9054040373c2c7c53d6b609831"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C5NDX7J7JTAMXMRYH465I7DJWT/bundle.json","state_url":"https://pith.science/pith/C5NDX7J7JTAMXMRYH465I7DJWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C5NDX7J7JTAMXMRYH465I7DJWT/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":"2026-08-09T21:41:01Z","links":{"resolver":"https://pith.science/pith/C5NDX7J7JTAMXMRYH465I7DJWT","bundle":"https://pith.science/pith/C5NDX7J7JTAMXMRYH465I7DJWT/bundle.json","state":"https://pith.science/pith/C5NDX7J7JTAMXMRYH465I7DJWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C5NDX7J7JTAMXMRYH465I7DJWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C5NDX7J7JTAMXMRYH465I7DJWT","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":"148be633944231345a941e68f1916e3e29d725b865a01739b46ee62f1105e4b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-16T08:49:30Z","title_canon_sha256":"c4632237163da98fa153205cd74f9c4c751a843426c3d5eea99c88027cb5fb90"},"schema_version":"1.0","source":{"id":"2407.11510","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11510","created_at":"2026-07-05T08:44:25Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11510v1","created_at":"2026-07-05T08:44:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11510","created_at":"2026-07-05T08:44:25Z"},{"alias_kind":"pith_short_12","alias_value":"C5NDX7J7JTAM","created_at":"2026-07-05T08:44:25Z"},{"alias_kind":"pith_short_16","alias_value":"C5NDX7J7JTAMXMRY","created_at":"2026-07-05T08:44:25Z"},{"alias_kind":"pith_short_8","alias_value":"C5NDX7J7","created_at":"2026-07-05T08:44:25Z"}],"graph_snapshots":[{"event_id":"sha256:dffd2dd1b7bc28fd6c2073b372adb8493ffd9c9054040373c2c7c53d6b609831","target":"graph","created_at":"2026-07-05T08:44:25Z","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/2407.11510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we provide a large audio-visual speaker recognition dataset, VoxBlink2, which includes approximately 10M utterances with videos from 110K+ speakers in the wild. This dataset represents a significant expansion over the VoxBlink dataset, encompassing a broader diversity of speakers and scenarios by the grace of an optimized data collection pipeline. Afterward, we explore the impact of training strategies, data scale, and model complexity on speaker verification and finally establish a new single-model state-of-the-art EER at 0.170% and minDCF at 0.006% on the VoxCeleb1-O test set.","authors_text":"Fulin Zhang, Ming Cheng, Ming Li, Shilei Zhang, Yingying Gao, Yuke Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-16T08:49:30Z","title":"VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11510","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":"sha256:9f6e35f546671d3aef2c3dfc222acf29e8fa0e17c371f93f5b17c1faf7e316e0","target":"record","created_at":"2026-07-05T08:44:25Z","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":"148be633944231345a941e68f1916e3e29d725b865a01739b46ee62f1105e4b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-16T08:49:30Z","title_canon_sha256":"c4632237163da98fa153205cd74f9c4c751a843426c3d5eea99c88027cb5fb90"},"schema_version":"1.0","source":{"id":"2407.11510","kind":"arxiv","version":1}},"canonical_sha256":"175a3bfd3f4cc0cbb2383f3dd47c69b4e847779f618af012ca3e2df28c28952d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"175a3bfd3f4cc0cbb2383f3dd47c69b4e847779f618af012ca3e2df28c28952d","first_computed_at":"2026-07-05T08:44:25.529187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:25.529187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AQvEXiswQIiqdkgITe2zlLJ2JbAYIrq3YQCtIezFrcTDwhTamD5yvMpbSSAKq5vvjfW22sG8y0aOZSVam/R2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:25.529617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11510","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f6e35f546671d3aef2c3dfc222acf29e8fa0e17c371f93f5b17c1faf7e316e0","sha256:dffd2dd1b7bc28fd6c2073b372adb8493ffd9c9054040373c2c7c53d6b609831"],"state_sha256":"07a29223ffe04733e2ff3e1601551337cab6c2c8717f4a51931ccbed4cc198c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tfk7Z0rFJvM78Laeo+kKr9i17HBmwjFIsBsaElUKsTeFGlPmfJFrrqZK5kLxuWvIcMH7B7W3f+Oh0dHgfU0HBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:41:01.986678Z","bundle_sha256":"54f752f51497eace0a294b2bf4a8aabec8d07d809bd4071d78fb3e840d6330aa"}}