{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XT3UVZMBM6D5KT7BJP4SERMDV4","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":"18d236021cb0e8e8d23a075dfd0785e2ffbcd410a3d5ca94233f5d8600c88797","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T04:08:59Z","title_canon_sha256":"8710ba6db25e10caca996527640b2b17d62a814d0a2f2d255379733a520218a0"},"schema_version":"1.0","source":{"id":"2505.21954","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21954","created_at":"2026-06-19T16:11:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21954v2","created_at":"2026-06-19T16:11:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21954","created_at":"2026-06-19T16:11:11Z"},{"alias_kind":"pith_short_12","alias_value":"XT3UVZMBM6D5","created_at":"2026-06-19T16:11:11Z"},{"alias_kind":"pith_short_16","alias_value":"XT3UVZMBM6D5KT7B","created_at":"2026-06-19T16:11:11Z"},{"alias_kind":"pith_short_8","alias_value":"XT3UVZMB","created_at":"2026-06-19T16:11:11Z"}],"graph_snapshots":[{"event_id":"sha256:b48c9200eb822ad26abd0fcaccba3375c4be7a722f6fb82222172eb92c00b23f","target":"graph","created_at":"2026-06-19T16:11:11Z","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/2505.21954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present UniTalk, a novel dataset emphasizing challenging scenarios to enhance model generalization for the task of active speaker detection (ASD). Previously established benchmarks such as AVA predominantly comprise old movies and thus exhibit significant domain gaps with real-world video. In contrast, UniTalk covers diverse video types reflecting challenging real-world conditions, including underrepresented languages, noisy backgrounds, and crowded scenes, while being on par with AVA in scale. Extensive evaluations reveal that ASD remains unsolved under realistic conditions: state-of-the-a","authors_text":"Khoa Quang Nhat Cao, Le Thien Phuc Nguyen, Lucas Poon, Soochahn Lee, Toan Ngo Duc Vo, Tuan Khai Nguyen, Tuan Tai Nguyen, Tu Ho Manh Pham, Yong Jae Lee, Yuwei Guo, Zhuoran Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T04:08:59Z","title":"Revisiting Active Speaker Detection: An In-the-Wild Benchmark for Generalization and Robustness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21954","kind":"arxiv","version":2},"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":"sha256:9180ec279bf4747f8fca11ebfbf92400df592fe4f51221e0fbbd461fc356a1ae","target":"record","created_at":"2026-06-19T16:11:11Z","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":"18d236021cb0e8e8d23a075dfd0785e2ffbcd410a3d5ca94233f5d8600c88797","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T04:08:59Z","title_canon_sha256":"8710ba6db25e10caca996527640b2b17d62a814d0a2f2d255379733a520218a0"},"schema_version":"1.0","source":{"id":"2505.21954","kind":"arxiv","version":2}},"canonical_sha256":"bcf74ae5816787d54fe14bf9224583af3a7da7c0dc24887fe8ff2e7d7efc1ed5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcf74ae5816787d54fe14bf9224583af3a7da7c0dc24887fe8ff2e7d7efc1ed5","first_computed_at":"2026-06-19T16:11:11.095614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:11.095614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1WEQBkgymOjsWkDoEqmPrxk7An84AnA6MfvQPKyP1EhQ15cJAxS2VihMiLB9vl5eFSIcgG+NOQ/yV9empP4rDw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:11.096116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21954","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9180ec279bf4747f8fca11ebfbf92400df592fe4f51221e0fbbd461fc356a1ae","sha256:b48c9200eb822ad26abd0fcaccba3375c4be7a722f6fb82222172eb92c00b23f"],"state_sha256":"930be7c72e281661f7cc047d0c3c4a28bae37257501408dcf48979615d40ae33"}