{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:V56YWO7YHJOOYFEGAASYKR6YGA","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":"3d295843493ba5755c946159eb337ffd76224874de64ee88b6f83dd827f7099e","cross_cats_sorted":["cs.CV","eess.AS","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-07-02T15:55:54Z","title_canon_sha256":"aa983cd5fa3ca7e77c9d416f6b9ec436d6d6efccb0f6485069860ad9a5c022ce"},"schema_version":"1.0","source":{"id":"2007.01216","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.01216","created_at":"2026-07-05T03:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2007.01216v3","created_at":"2026-07-05T03:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01216","created_at":"2026-07-05T03:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"V56YWO7YHJOO","created_at":"2026-07-05T03:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"V56YWO7YHJOOYFEG","created_at":"2026-07-05T03:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"V56YWO7Y","created_at":"2026-07-05T03:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:1c4fba6cebbfafd549c9c8118100bc95c0ebc04d4c62b07523e678c375742e4e","target":"graph","created_at":"2026-07-05T03:05:43Z","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/2007.01216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of this paper is speaker diarisation of videos collected 'in the wild'. We make three key contributions. First, we propose an automatic audio-visual diarisation method for YouTube videos. Our method consists of active speaker detection using audio-visual methods and speaker verification using self-enrolled speaker models. Second, we integrate our method into a semi-automatic dataset creation pipeline which significantly reduces the number of hours required to annotate videos with diarisation labels. Finally, we use this pipeline to create a large-scale diarisation dataset called VoxCo","authors_text":"Andrew Zisserman, Arsha Nagrani, Jaesung Huh, Joon Son Chung, Triantafyllos Afouras","cross_cats":["cs.CV","eess.AS","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-07-02T15:55:54Z","title":"Spot the conversation: speaker diarisation in the wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01216","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":"sha256:03a12d5ad0e523e3d97b4a0b006a323914652d10736c1a0e5a3db69779d44689","target":"record","created_at":"2026-07-05T03:05:43Z","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":"3d295843493ba5755c946159eb337ffd76224874de64ee88b6f83dd827f7099e","cross_cats_sorted":["cs.CV","eess.AS","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-07-02T15:55:54Z","title_canon_sha256":"aa983cd5fa3ca7e77c9d416f6b9ec436d6d6efccb0f6485069860ad9a5c022ce"},"schema_version":"1.0","source":{"id":"2007.01216","kind":"arxiv","version":3}},"canonical_sha256":"af7d8b3bf83a5cec148600258547d83035945f6e9729549f541fbb2194d1865b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af7d8b3bf83a5cec148600258547d83035945f6e9729549f541fbb2194d1865b","first_computed_at":"2026-07-05T03:05:43.380373Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:43.380373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qAp4fwlpykpWQgvKNGgRuRLQklc+/wt9lv1msu79qGO9vkTpqaa0cztKRMhV8ndT6tnCutEI8X5M1NC8Fyj6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:43.380810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.01216","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03a12d5ad0e523e3d97b4a0b006a323914652d10736c1a0e5a3db69779d44689","sha256:1c4fba6cebbfafd549c9c8118100bc95c0ebc04d4c62b07523e678c375742e4e"],"state_sha256":"dcc0eaa3cf68623fdfe6d8ec7874e989857e8a8e01e16a7fc22a6ecdb1546c82"}