{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZUVJQNWBX4S4TOCS23TPKK5FKW","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":"f40f6fe80cade055ee3003d3810e0db7ac05c6ecdc2930806fc9a14b66f83326","cross_cats_sorted":["cs.LG","cs.MM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-02-10T17:41:51Z","title_canon_sha256":"ea94a9e4c9ef227537d5df3d84fe3ee4bc79948b70ec27abde9924f3c7ce5033"},"schema_version":"1.0","source":{"id":"2002.03977","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03977","created_at":"2026-07-05T04:26:17Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03977v3","created_at":"2026-07-05T04:26:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03977","created_at":"2026-07-05T04:26:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZUVJQNWBX4S4","created_at":"2026-07-05T04:26:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZUVJQNWBX4S4TOCS","created_at":"2026-07-05T04:26:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZUVJQNWB","created_at":"2026-07-05T04:26:17Z"}],"graph_snapshots":[{"event_id":"sha256:56ac513441ee0cd7e3f6038be8e86a135e89a8fee5fedc0971b90e9cebbff1eb","target":"graph","created_at":"2026-07-05T04:26:17Z","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/2002.03977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Active speaker detection (ASD) and virtual cinematography (VC) can significantly improve the remote user experience of a video conference by automatically panning, tilting and zooming of a video conferencing camera: users subjectively rate an expert video cinematographer's video significantly higher than unedited video. We describe a new automated ASD and VC that performs within 0.3 MOS of an expert cinematographer based on subjective ratings with a 1-5 scale. This system uses a 4K wide-FOV camera, a depth camera, and a microphone array; it extracts features from each modality and trains an AS","authors_text":"Adam Kirk, Adarsh Kowdle, Cha Zhang, Oliver Whyte, Ramin Mehran, Ross Cutler, Sam Johnson","cross_cats":["cs.LG","cs.MM","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-02-10T17:41:51Z","title":"Multimodal active speaker detection and virtual cinematography for video conferencing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03977","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":"sha256:83ad5ef2a8d6df131f3b12a3f8f4593e7ca8d37c1d8cfa11bc381d5d7239c8c5","target":"record","created_at":"2026-07-05T04:26:17Z","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":"f40f6fe80cade055ee3003d3810e0db7ac05c6ecdc2930806fc9a14b66f83326","cross_cats_sorted":["cs.LG","cs.MM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-02-10T17:41:51Z","title_canon_sha256":"ea94a9e4c9ef227537d5df3d84fe3ee4bc79948b70ec27abde9924f3c7ce5033"},"schema_version":"1.0","source":{"id":"2002.03977","kind":"arxiv","version":3}},"canonical_sha256":"cd2a9836c1bf25c9b852d6e6f52ba5559f05e36d443ebf6ca9edfabba32c507f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd2a9836c1bf25c9b852d6e6f52ba5559f05e36d443ebf6ca9edfabba32c507f","first_computed_at":"2026-07-05T04:26:17.845755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:17.845755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"95Cm9AUKecB2A3l7HRTxDPZEPTAvEX7o0yo+dRP4sKQg+uEYEq5xeM+yFyxzHPivbyEsf1654hxHhXmEiBvlDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:17.846173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.03977","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83ad5ef2a8d6df131f3b12a3f8f4593e7ca8d37c1d8cfa11bc381d5d7239c8c5","sha256:56ac513441ee0cd7e3f6038be8e86a135e89a8fee5fedc0971b90e9cebbff1eb"],"state_sha256":"4329fc9648761cc405ff744b73e80476c5d91fd8f34639725ec49906f24c0682"}