{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NB5FUT3SX7MEHLHVGR2AWYRAM3","short_pith_number":"pith:NB5FUT3S","canonical_record":{"source":{"id":"2408.14585","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T19:09:21Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4cb77bc43c4da3ceda0b4dabe0768c0871579c65b12900247ab952a2c15fe5ae","abstract_canon_sha256":"5af7e8f317d1095f12da716d3e54c3fab9a02e1c95a62696769802a1f6f30bb6"},"schema_version":"1.0"},"canonical_sha256":"687a5a4f72bfd843acf534740b622066e2754586ae2410e1522bf11ea28905e7","source":{"kind":"arxiv","id":"2408.14585","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14585","created_at":"2026-07-05T10:15:19Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14585v2","created_at":"2026-07-05T10:15:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14585","created_at":"2026-07-05T10:15:19Z"},{"alias_kind":"pith_short_12","alias_value":"NB5FUT3SX7ME","created_at":"2026-07-05T10:15:19Z"},{"alias_kind":"pith_short_16","alias_value":"NB5FUT3SX7MEHLHV","created_at":"2026-07-05T10:15:19Z"},{"alias_kind":"pith_short_8","alias_value":"NB5FUT3S","created_at":"2026-07-05T10:15:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NB5FUT3SX7MEHLHVGR2AWYRAM3","target":"record","payload":{"canonical_record":{"source":{"id":"2408.14585","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T19:09:21Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4cb77bc43c4da3ceda0b4dabe0768c0871579c65b12900247ab952a2c15fe5ae","abstract_canon_sha256":"5af7e8f317d1095f12da716d3e54c3fab9a02e1c95a62696769802a1f6f30bb6"},"schema_version":"1.0"},"canonical_sha256":"687a5a4f72bfd843acf534740b622066e2754586ae2410e1522bf11ea28905e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:19.023859Z","signature_b64":"0BcW9aIiXgvzDnkOwbG/dqvmTLHGFFX9VKTgT9Yn653xlTylLGyVlJoHJsTuueYvdTRoGpFB0tFiCz8hT5ubBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"687a5a4f72bfd843acf534740b622066e2754586ae2410e1522bf11ea28905e7","last_reissued_at":"2026-07-05T10:15:19.023377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:19.023377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.14585","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:15:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WgqJ5FSH8KB6hwDmoduFzTwJQG7sHWyKqd0WDj99wDb8d1ni4ceojwv4Wdwt2L7xJmlU29BMbgeaJn1ilD+DDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:21:43.301016Z"},"content_sha256":"d5ed84ead7137c259b5695d0c18425efb1d132a7d42c09843eacb970234dd644","schema_version":"1.0","event_id":"sha256:d5ed84ead7137c259b5695d0c18425efb1d132a7d42c09843eacb970234dd644"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NB5FUT3SX7MEHLHVGR2AWYRAM3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Global-Local Distillation Network-Based Audio-Visual Speaker Tracking with Incomplete Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bin Ren, Hao Guo, Hong Liu, Nicu Sebe, Yidi Li, Yihan Li, Yixin Guo, Zhenhuan Xu","submitted_at":"2024-08-26T19:09:21Z","abstract_excerpt":"In speaker tracking research, integrating and complementing multi-modal data is a crucial strategy for improving the accuracy and robustness of tracking systems. However, tracking with incomplete modalities remains a challenging issue due to noisy observations caused by occlusion, acoustic noise, and sensor failures. Especially when there is missing data in multiple modalities, the performance of existing multi-modal fusion methods tends to decrease. To this end, we propose a Global-Local Distillation-based Tracker (GLDTracker) for robust audio-visual speaker tracking. GLDTracker is driven by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14585","kind":"arxiv","version":2},"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/2408.14585/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":"2026-07-05T10:15:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7F/u9SxhBJe3TpPuLE1vXFOF02E9n6xhd99Kcj7phVfTyhJMnQnfnJZ6gzBhwZwdDukZkkRreNTbjRCCDubXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:21:43.301407Z"},"content_sha256":"af312a2937a00f9ab422641d32b51d5f4f110072106dd2476ac34e13f94c45fa","schema_version":"1.0","event_id":"sha256:af312a2937a00f9ab422641d32b51d5f4f110072106dd2476ac34e13f94c45fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3/bundle.json","state_url":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3/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":"2026-07-06T19:21:43Z","links":{"resolver":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3","bundle":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3/bundle.json","state":"https://pith.science/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NB5FUT3SX7MEHLHVGR2AWYRAM3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NB5FUT3SX7MEHLHVGR2AWYRAM3","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":"5af7e8f317d1095f12da716d3e54c3fab9a02e1c95a62696769802a1f6f30bb6","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T19:09:21Z","title_canon_sha256":"4cb77bc43c4da3ceda0b4dabe0768c0871579c65b12900247ab952a2c15fe5ae"},"schema_version":"1.0","source":{"id":"2408.14585","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14585","created_at":"2026-07-05T10:15:19Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14585v2","created_at":"2026-07-05T10:15:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14585","created_at":"2026-07-05T10:15:19Z"},{"alias_kind":"pith_short_12","alias_value":"NB5FUT3SX7ME","created_at":"2026-07-05T10:15:19Z"},{"alias_kind":"pith_short_16","alias_value":"NB5FUT3SX7MEHLHV","created_at":"2026-07-05T10:15:19Z"},{"alias_kind":"pith_short_8","alias_value":"NB5FUT3S","created_at":"2026-07-05T10:15:19Z"}],"graph_snapshots":[{"event_id":"sha256:af312a2937a00f9ab422641d32b51d5f4f110072106dd2476ac34e13f94c45fa","target":"graph","created_at":"2026-07-05T10:15:19Z","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/2408.14585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In speaker tracking research, integrating and complementing multi-modal data is a crucial strategy for improving the accuracy and robustness of tracking systems. However, tracking with incomplete modalities remains a challenging issue due to noisy observations caused by occlusion, acoustic noise, and sensor failures. Especially when there is missing data in multiple modalities, the performance of existing multi-modal fusion methods tends to decrease. To this end, we propose a Global-Local Distillation-based Tracker (GLDTracker) for robust audio-visual speaker tracking. GLDTracker is driven by ","authors_text":"Bin Ren, Hao Guo, Hong Liu, Nicu Sebe, Yidi Li, Yihan Li, Yixin Guo, Zhenhuan Xu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T19:09:21Z","title":"Global-Local Distillation Network-Based Audio-Visual Speaker Tracking with Incomplete Modalities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14585","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:d5ed84ead7137c259b5695d0c18425efb1d132a7d42c09843eacb970234dd644","target":"record","created_at":"2026-07-05T10:15:19Z","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":"5af7e8f317d1095f12da716d3e54c3fab9a02e1c95a62696769802a1f6f30bb6","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T19:09:21Z","title_canon_sha256":"4cb77bc43c4da3ceda0b4dabe0768c0871579c65b12900247ab952a2c15fe5ae"},"schema_version":"1.0","source":{"id":"2408.14585","kind":"arxiv","version":2}},"canonical_sha256":"687a5a4f72bfd843acf534740b622066e2754586ae2410e1522bf11ea28905e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"687a5a4f72bfd843acf534740b622066e2754586ae2410e1522bf11ea28905e7","first_computed_at":"2026-07-05T10:15:19.023377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:19.023377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0BcW9aIiXgvzDnkOwbG/dqvmTLHGFFX9VKTgT9Yn653xlTylLGyVlJoHJsTuueYvdTRoGpFB0tFiCz8hT5ubBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:19.023859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14585","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5ed84ead7137c259b5695d0c18425efb1d132a7d42c09843eacb970234dd644","sha256:af312a2937a00f9ab422641d32b51d5f4f110072106dd2476ac34e13f94c45fa"],"state_sha256":"b2fa2bc11c3a17bb4e69c3eecdfce8268064adf325d232b95bb1829bc0a50501"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n9nH+LnH2ZoZNQLWpiKvyFdq6Q+yBRV70aPPNlzoO1e+zML6xNqv0yvS/3ttfUuKgVH8lIt0oQCBQyajBx50BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:21:43.303514Z","bundle_sha256":"4ff4f5a699484ac8fef1f97fe77aa9620580558f09f6dde586381eea798d28b3"}}