{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BUZ3RWHVNFBHZGABEIS7TISB5T","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":"e92c42f4087918ee28a252adc9a982eb9fd072716e38a9c165078d317cf83837","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-02-13T02:36:32Z","title_canon_sha256":"c3e172a6a078964645bc9955c74c3ccd410e68c464187bbf55fd672a60cd9e6d"},"schema_version":"1.0","source":{"id":"2002.05314","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05314","created_at":"2026-07-05T00:40:30Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05314v1","created_at":"2026-07-05T00:40:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05314","created_at":"2026-07-05T00:40:30Z"},{"alias_kind":"pith_short_12","alias_value":"BUZ3RWHVNFBH","created_at":"2026-07-05T00:40:30Z"},{"alias_kind":"pith_short_16","alias_value":"BUZ3RWHVNFBHZGAB","created_at":"2026-07-05T00:40:30Z"},{"alias_kind":"pith_short_8","alias_value":"BUZ3RWHV","created_at":"2026-07-05T00:40:30Z"}],"graph_snapshots":[{"event_id":"sha256:937a3e8ce959253308afcd5a95b3c85fef57169e89d5b281efe1cdeaad235b78","target":"graph","created_at":"2026-07-05T00:40:30Z","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/2002.05314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker diarization, which is to find the speech segments of specific speakers, has been widely used in human-centered applications such as video conferences or human-computer interaction systems. In this paper, we propose a self-supervised audio-video synchronization learning method to address the problem of speaker diarization without massive labeling effort. We improve the previous approaches by introducing two new loss functions: the dynamic triplet loss and the multinomial loss. We test them on a real-world human-computer interaction system and the results show our best model yields a rem","authors_text":"Liqiang Wang, Shi-Xiong Zhang, Yahuan Cong, Yifan Ding, Yong Xu","cross_cats":["cs.LG","cs.MM","cs.SD","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-02-13T02:36:32Z","title":"Self-supervised learning for audio-visual speaker diarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05314","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:f5e859d14ea09970fbf7277e908bbf7bb58d6b46973eadc8229ac6e28577c783","target":"record","created_at":"2026-07-05T00:40:30Z","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":"e92c42f4087918ee28a252adc9a982eb9fd072716e38a9c165078d317cf83837","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-02-13T02:36:32Z","title_canon_sha256":"c3e172a6a078964645bc9955c74c3ccd410e68c464187bbf55fd672a60cd9e6d"},"schema_version":"1.0","source":{"id":"2002.05314","kind":"arxiv","version":1}},"canonical_sha256":"0d33b8d8f569427c98012225f9a241ecc09d506dd4304913d534de44212c5b07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d33b8d8f569427c98012225f9a241ecc09d506dd4304913d534de44212c5b07","first_computed_at":"2026-07-05T00:40:30.120507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:30.120507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l08Ph+P6IThYh9vAAyDUiqxL4ya2KAi1Q+zmiFlYK9UQUC6vd6JVF301RbAMrJ131LEZXNDvSh0N5Mp/8XIuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:30.120888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.05314","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5e859d14ea09970fbf7277e908bbf7bb58d6b46973eadc8229ac6e28577c783","sha256:937a3e8ce959253308afcd5a95b3c85fef57169e89d5b281efe1cdeaad235b78"],"state_sha256":"c145b19f3ebb08037600098d0dcdfc5748d060b70e87f66b2503b3d9bd24f945"}