{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CH72C5WPZI3S4BB6UUUZGG523U","short_pith_number":"pith:CH72C5WP","canonical_record":{"source":{"id":"2310.14778","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2023-10-23T10:29:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d74129a3912aacd06cfd9864da26da3ac03c0550163c8c9aea4e0e10492b8966","abstract_canon_sha256":"c0dd3843b969b89925f59d79d7c5aeaa2feb528223096bc730cc245d083ae246"},"schema_version":"1.0"},"canonical_sha256":"11ffa176cfca372e043ea529931bbadd0daa800f4a0146b1b18d2e0178072ca3","source":{"kind":"arxiv","id":"2310.14778","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14778","created_at":"2026-07-05T10:48:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14778v5","created_at":"2026-07-05T10:48:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14778","created_at":"2026-07-05T10:48:13Z"},{"alias_kind":"pith_short_12","alias_value":"CH72C5WPZI3S","created_at":"2026-07-05T10:48:13Z"},{"alias_kind":"pith_short_16","alias_value":"CH72C5WPZI3S4BB6","created_at":"2026-07-05T10:48:13Z"},{"alias_kind":"pith_short_8","alias_value":"CH72C5WP","created_at":"2026-07-05T10:48:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CH72C5WPZI3S4BB6UUUZGG523U","target":"record","payload":{"canonical_record":{"source":{"id":"2310.14778","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2023-10-23T10:29:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d74129a3912aacd06cfd9864da26da3ac03c0550163c8c9aea4e0e10492b8966","abstract_canon_sha256":"c0dd3843b969b89925f59d79d7c5aeaa2feb528223096bc730cc245d083ae246"},"schema_version":"1.0"},"canonical_sha256":"11ffa176cfca372e043ea529931bbadd0daa800f4a0146b1b18d2e0178072ca3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:13.230800Z","signature_b64":"NcSSMetf/nsHVTbcr+BK0l+sd4UEgB9YMQ7laKZvaEUO3iEGSbIQAHfglmJKd4WVz1G4/GBTECOSi2WYYA84Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11ffa176cfca372e043ea529931bbadd0daa800f4a0146b1b18d2e0178072ca3","last_reissued_at":"2026-07-05T10:48:13.230276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:13.230276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.14778","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:48:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6JMZXEW4M+4w39ObACLEscetTcHWGHxVoHyF6uruc20x6q7rJXiDI41z7cl8sWJ/Syvo92mkTNukj1BCmvg/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T02:31:48.477895Z"},"content_sha256":"6e65cc2119c34fe430e78e39af521f7dc9c31ee0aff16146d9c9fbf7df4ecdf9","schema_version":"1.0","event_id":"sha256:6e65cc2119c34fe430e78e39af521f7dc9c31ee0aff16146d9c9fbf7df4ecdf9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CH72C5WPZI3S4BB6UUUZGG523U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-Visual Speaker Tracking: Progress, Challenges, and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Davide Berghi, Jianyuan Sun, Jinzheng Zhao, Meng Cui, Peipei Wu, Philip J.B. Jackson, Wenwu Wang, Xinyuan Qian, Yong Xu","submitted_at":"2023-10-23T10:29:33Z","abstract_excerpt":"Audio-visual speaker tracking has drawn increasing attention over the past few years due to its academic values and wide applications. Audio and visual modalities can provide complementary information for localization and tracking. With audio and visual information, the Bayesian-based filter and deep learning-based methods can solve the problem of data association, audio-visual fusion and track management. In this paper, we conduct a comprehensive overview of audio-visual speaker tracking. To our knowledge, this is the first extensive survey over the past five years. We introduce the family of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14778","kind":"arxiv","version":5},"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/2310.14778/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":"2026-07-05T10:48:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IBzG+3G4Uh4QtVDyqcmMqM5fsxn2g51dQOfCAU0Ylg+pY4fuX6eOYyVtogYgnWePrL1yvf6p1kZ3/jYApZfvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T02:31:48.478707Z"},"content_sha256":"9a1c5ab377c8fcb60fca4b93928aa651339ae34e96f046d658c27054f9d6d2f5","schema_version":"1.0","event_id":"sha256:9a1c5ab377c8fcb60fca4b93928aa651339ae34e96f046d658c27054f9d6d2f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CH72C5WPZI3S4BB6UUUZGG523U/bundle.json","state_url":"https://pith.science/pith/CH72C5WPZI3S4BB6UUUZGG523U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CH72C5WPZI3S4BB6UUUZGG523U/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":"2026-08-07T02:31:48Z","links":{"resolver":"https://pith.science/pith/CH72C5WPZI3S4BB6UUUZGG523U","bundle":"https://pith.science/pith/CH72C5WPZI3S4BB6UUUZGG523U/bundle.json","state":"https://pith.science/pith/CH72C5WPZI3S4BB6UUUZGG523U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CH72C5WPZI3S4BB6UUUZGG523U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CH72C5WPZI3S4BB6UUUZGG523U","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":"c0dd3843b969b89925f59d79d7c5aeaa2feb528223096bc730cc245d083ae246","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2023-10-23T10:29:33Z","title_canon_sha256":"d74129a3912aacd06cfd9864da26da3ac03c0550163c8c9aea4e0e10492b8966"},"schema_version":"1.0","source":{"id":"2310.14778","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14778","created_at":"2026-07-05T10:48:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14778v5","created_at":"2026-07-05T10:48:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14778","created_at":"2026-07-05T10:48:13Z"},{"alias_kind":"pith_short_12","alias_value":"CH72C5WPZI3S","created_at":"2026-07-05T10:48:13Z"},{"alias_kind":"pith_short_16","alias_value":"CH72C5WPZI3S4BB6","created_at":"2026-07-05T10:48:13Z"},{"alias_kind":"pith_short_8","alias_value":"CH72C5WP","created_at":"2026-07-05T10:48:13Z"}],"graph_snapshots":[{"event_id":"sha256:9a1c5ab377c8fcb60fca4b93928aa651339ae34e96f046d658c27054f9d6d2f5","target":"graph","created_at":"2026-07-05T10:48:13Z","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/2310.14778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual speaker tracking has drawn increasing attention over the past few years due to its academic values and wide applications. Audio and visual modalities can provide complementary information for localization and tracking. With audio and visual information, the Bayesian-based filter and deep learning-based methods can solve the problem of data association, audio-visual fusion and track management. In this paper, we conduct a comprehensive overview of audio-visual speaker tracking. To our knowledge, this is the first extensive survey over the past five years. We introduce the family of","authors_text":"Davide Berghi, Jianyuan Sun, Jinzheng Zhao, Meng Cui, Peipei Wu, Philip J.B. Jackson, Wenwu Wang, Xinyuan Qian, Yong Xu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2023-10-23T10:29:33Z","title":"Audio-Visual Speaker Tracking: Progress, Challenges, and Future Directions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14778","kind":"arxiv","version":5},"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":"sha256:6e65cc2119c34fe430e78e39af521f7dc9c31ee0aff16146d9c9fbf7df4ecdf9","target":"record","created_at":"2026-07-05T10:48:13Z","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":"c0dd3843b969b89925f59d79d7c5aeaa2feb528223096bc730cc245d083ae246","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2023-10-23T10:29:33Z","title_canon_sha256":"d74129a3912aacd06cfd9864da26da3ac03c0550163c8c9aea4e0e10492b8966"},"schema_version":"1.0","source":{"id":"2310.14778","kind":"arxiv","version":5}},"canonical_sha256":"11ffa176cfca372e043ea529931bbadd0daa800f4a0146b1b18d2e0178072ca3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11ffa176cfca372e043ea529931bbadd0daa800f4a0146b1b18d2e0178072ca3","first_computed_at":"2026-07-05T10:48:13.230276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:13.230276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NcSSMetf/nsHVTbcr+BK0l+sd4UEgB9YMQ7laKZvaEUO3iEGSbIQAHfglmJKd4WVz1G4/GBTECOSi2WYYA84Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:13.230800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14778","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e65cc2119c34fe430e78e39af521f7dc9c31ee0aff16146d9c9fbf7df4ecdf9","sha256:9a1c5ab377c8fcb60fca4b93928aa651339ae34e96f046d658c27054f9d6d2f5"],"state_sha256":"b5533526a0af573f8427b80db4f6371f0cb5cd7a7451852cb58fb4698878887e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5MC/XDABfaM8kU7RGoFtEsXj9XynzXBT356yzRIyBI66mne1A7U7EGEgbW6Z6UoSa2o4k4+4CnRlvQP6j9amAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T02:31:48.484120Z","bundle_sha256":"47e95f2dc51e462f9369ff5075fb61471a64245b9178a4233a976e1f593c2aef"}}