{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CZDKKGN3JTZMLJMHXZ655XNF67","short_pith_number":"pith:CZDKKGN3","canonical_record":{"source":{"id":"2408.12102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T03:34:03Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"08cfdcfef82673ae2d5b3192a464124f3ee73871bc7faf122120b25144776bf0","abstract_canon_sha256":"3e1e92b9acdafe660b62a36cc3bcad90f14c7e44873b1b9330e0658e8cd3f735"},"schema_version":"1.0"},"canonical_sha256":"1646a519bb4cf2c5a587be7ddedda5f7ebdf0e70763381f64612afb082a11e1b","source":{"kind":"arxiv","id":"2408.12102","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12102","created_at":"2026-07-05T08:58:03Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12102v1","created_at":"2026-07-05T08:58:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12102","created_at":"2026-07-05T08:58:03Z"},{"alias_kind":"pith_short_12","alias_value":"CZDKKGN3JTZM","created_at":"2026-07-05T08:58:03Z"},{"alias_kind":"pith_short_16","alias_value":"CZDKKGN3JTZMLJMH","created_at":"2026-07-05T08:58:03Z"},{"alias_kind":"pith_short_8","alias_value":"CZDKKGN3","created_at":"2026-07-05T08:58:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CZDKKGN3JTZMLJMHXZ655XNF67","target":"record","payload":{"canonical_record":{"source":{"id":"2408.12102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T03:34:03Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"08cfdcfef82673ae2d5b3192a464124f3ee73871bc7faf122120b25144776bf0","abstract_canon_sha256":"3e1e92b9acdafe660b62a36cc3bcad90f14c7e44873b1b9330e0658e8cd3f735"},"schema_version":"1.0"},"canonical_sha256":"1646a519bb4cf2c5a587be7ddedda5f7ebdf0e70763381f64612afb082a11e1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:03.963682Z","signature_b64":"sipviPLuwCTpBY7Z85ZLQRRbgrmqrDxrvbFCQhqJ8WmHwl8w+f9gVdaveBIpXL0ktIkt42fWqTjFMlbmWIWRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1646a519bb4cf2c5a587be7ddedda5f7ebdf0e70763381f64612afb082a11e1b","last_reissued_at":"2026-07-05T08:58:03.963275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:03.963275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.12102","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:58:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QZNfY1BOEi+qjh6+HLLyPldCR3g9uuayZchSi4pXm/CKhCwsX1O9SMGdSWmGfEMgcQzCYWpPIJ0YjGm4jIq1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:39:43.880322Z"},"content_sha256":"d076925bf68718ac8e49f06e99b4ea1099b43579dff7b63b0ad38bef88a0be0e","schema_version":"1.0","event_id":"sha256:d076925bf68718ac8e49f06e99b4ea1099b43579dff7b63b0ad38bef88a0be0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CZDKKGN3JTZMLJMHXZ655XNF67","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Hui Wang, Luyao Cheng, Qian Chen, Qinglin Zhang, Rongjie Huang, Siqi Zheng, Xihao Li, Yafeng Chen","submitted_at":"2024-08-22T03:34:03Z","abstract_excerpt":"Speaker diarization, the process of segmenting an audio stream or transcribed speech content into homogenous partitions based on speaker identity, plays a crucial role in the interpretation and analysis of human speech. Most existing speaker diarization systems rely exclusively on unimodal acoustic information, making the task particularly challenging due to the innate ambiguities of audio signals. Recent studies have made tremendous efforts towards audio-visual or audio-semantic modeling to enhance performance. However, even the incorporation of up to two modalities often falls short in addre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12102","kind":"arxiv","version":1},"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/2408.12102/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":"2026-07-05T08:58:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6r7z0ggEQByvYjtWUM9YagvJEPdSmKpQc9pY2oL2gaXHXD4KKpV/qa2hVdUWr0Ih7HURPOtR5VPyQ7T5SX11AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:39:43.881219Z"},"content_sha256":"f6624c1da842c9708b6f67fdbcdbede3565f02fa19135686b0c5be75b3b0aeb6","schema_version":"1.0","event_id":"sha256:f6624c1da842c9708b6f67fdbcdbede3565f02fa19135686b0c5be75b3b0aeb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZDKKGN3JTZMLJMHXZ655XNF67/bundle.json","state_url":"https://pith.science/pith/CZDKKGN3JTZMLJMHXZ655XNF67/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZDKKGN3JTZMLJMHXZ655XNF67/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":"2026-08-07T17:39:43Z","links":{"resolver":"https://pith.science/pith/CZDKKGN3JTZMLJMHXZ655XNF67","bundle":"https://pith.science/pith/CZDKKGN3JTZMLJMHXZ655XNF67/bundle.json","state":"https://pith.science/pith/CZDKKGN3JTZMLJMHXZ655XNF67/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZDKKGN3JTZMLJMHXZ655XNF67/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CZDKKGN3JTZMLJMHXZ655XNF67","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":"3e1e92b9acdafe660b62a36cc3bcad90f14c7e44873b1b9330e0658e8cd3f735","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T03:34:03Z","title_canon_sha256":"08cfdcfef82673ae2d5b3192a464124f3ee73871bc7faf122120b25144776bf0"},"schema_version":"1.0","source":{"id":"2408.12102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12102","created_at":"2026-07-05T08:58:03Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12102v1","created_at":"2026-07-05T08:58:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12102","created_at":"2026-07-05T08:58:03Z"},{"alias_kind":"pith_short_12","alias_value":"CZDKKGN3JTZM","created_at":"2026-07-05T08:58:03Z"},{"alias_kind":"pith_short_16","alias_value":"CZDKKGN3JTZMLJMH","created_at":"2026-07-05T08:58:03Z"},{"alias_kind":"pith_short_8","alias_value":"CZDKKGN3","created_at":"2026-07-05T08:58:03Z"}],"graph_snapshots":[{"event_id":"sha256:f6624c1da842c9708b6f67fdbcdbede3565f02fa19135686b0c5be75b3b0aeb6","target":"graph","created_at":"2026-07-05T08:58:03Z","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/2408.12102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker diarization, the process of segmenting an audio stream or transcribed speech content into homogenous partitions based on speaker identity, plays a crucial role in the interpretation and analysis of human speech. Most existing speaker diarization systems rely exclusively on unimodal acoustic information, making the task particularly challenging due to the innate ambiguities of audio signals. Recent studies have made tremendous efforts towards audio-visual or audio-semantic modeling to enhance performance. However, even the incorporation of up to two modalities often falls short in addre","authors_text":"Hui Wang, Luyao Cheng, Qian Chen, Qinglin Zhang, Rongjie Huang, Siqi Zheng, Xihao Li, Yafeng Chen","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T03:34:03Z","title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12102","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:d076925bf68718ac8e49f06e99b4ea1099b43579dff7b63b0ad38bef88a0be0e","target":"record","created_at":"2026-07-05T08:58:03Z","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":"3e1e92b9acdafe660b62a36cc3bcad90f14c7e44873b1b9330e0658e8cd3f735","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T03:34:03Z","title_canon_sha256":"08cfdcfef82673ae2d5b3192a464124f3ee73871bc7faf122120b25144776bf0"},"schema_version":"1.0","source":{"id":"2408.12102","kind":"arxiv","version":1}},"canonical_sha256":"1646a519bb4cf2c5a587be7ddedda5f7ebdf0e70763381f64612afb082a11e1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1646a519bb4cf2c5a587be7ddedda5f7ebdf0e70763381f64612afb082a11e1b","first_computed_at":"2026-07-05T08:58:03.963275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:58:03.963275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sipviPLuwCTpBY7Z85ZLQRRbgrmqrDxrvbFCQhqJ8WmHwl8w+f9gVdaveBIpXL0ktIkt42fWqTjFMlbmWIWRAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:58:03.963682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d076925bf68718ac8e49f06e99b4ea1099b43579dff7b63b0ad38bef88a0be0e","sha256:f6624c1da842c9708b6f67fdbcdbede3565f02fa19135686b0c5be75b3b0aeb6"],"state_sha256":"0e50c3602d5494c146385093175dd69c50d54815d82d31dd650c923caf77eb68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AxvRAfQT0K6Mu8c5jERo/fMp0y6oMx0Q3Ugc8J6yItBjJ1I5nsdlpcV3vzZLXRjXrXOd2LdVCgxbhXh5IroCBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:39:43.888309Z","bundle_sha256":"b643e994c4fa93e692431f91940745f964953d20533266ec43342778ea55b455"}}