{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YSC2RN4DAVGWVYXJ2KXYOUO3TI","short_pith_number":"pith:YSC2RN4D","schema_version":"1.0","canonical_sha256":"c485a8b783054d6ae2e9d2af8751db9a26cdcb6b48b900f624d411b613f742a9","source":{"kind":"arxiv","id":"2506.14427","version":2},"attestation_state":"computed","paper":{"title":"M3SD: Multi-modal, Multi-scenario and Multi-language Speaker Diarization Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"eess.AS","authors_text":"Shilong Wu","submitted_at":"2025-06-17T11:44:20Z","abstract_excerpt":"In the field of speaker diarization, the development of technology is constrained by two problems: insufficient data resources and poor generalization ability of deep learning models. To address these two problems, firstly, we propose an automated method for constructing speaker diarization datasets, which generates more accurate pseudo-labels for massive data through the combination of audio and video. Relying on this method, we have released Multi-modal, Multi-scenario and Multi-language Speaker Diarization (M3SD) datasets. This dataset is derived from real network videos and is highly diver"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.14427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-17T11:44:20Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"3a4d6a22294f1cd7a62a06ef5856a96a05bc5aad23def2e2e0dd0a256dca07a1","abstract_canon_sha256":"d5164fcefc5bf6a1c9a85fb9a7e40c984db234ed881135df8cba573c327d0606"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:37.615663Z","signature_b64":"t6AIkw3x34k1MsXQGHy1tGTRTk8EFqikhikmfigA9zA6+u+6j/UzhcIKskcuEEvO6SU54az0QqjdfokUhnQ5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c485a8b783054d6ae2e9d2af8751db9a26cdcb6b48b900f624d411b613f742a9","last_reissued_at":"2026-07-05T11:28:37.615164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:37.615164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M3SD: Multi-modal, Multi-scenario and Multi-language Speaker Diarization Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"eess.AS","authors_text":"Shilong Wu","submitted_at":"2025-06-17T11:44:20Z","abstract_excerpt":"In the field of speaker diarization, the development of technology is constrained by two problems: insufficient data resources and poor generalization ability of deep learning models. To address these two problems, firstly, we propose an automated method for constructing speaker diarization datasets, which generates more accurate pseudo-labels for massive data through the combination of audio and video. Relying on this method, we have released Multi-modal, Multi-scenario and Multi-language Speaker Diarization (M3SD) datasets. This dataset is derived from real network videos and is highly diver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14427","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/2506.14427/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.14427","created_at":"2026-07-05T11:28:37.615215+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14427v2","created_at":"2026-07-05T11:28:37.615215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14427","created_at":"2026-07-05T11:28:37.615215+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSC2RN4DAVGW","created_at":"2026-07-05T11:28:37.615215+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSC2RN4DAVGWVYXJ","created_at":"2026-07-05T11:28:37.615215+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSC2RN4D","created_at":"2026-07-05T11:28:37.615215+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07294","citing_title":"Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI","json":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI.json","graph_json":"https://pith.science/api/pith-number/YSC2RN4DAVGWVYXJ2KXYOUO3TI/graph.json","events_json":"https://pith.science/api/pith-number/YSC2RN4DAVGWVYXJ2KXYOUO3TI/events.json","paper":"https://pith.science/paper/YSC2RN4D"},"agent_actions":{"view_html":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI","download_json":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI.json","view_paper":"https://pith.science/paper/YSC2RN4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14427&json=true","fetch_graph":"https://pith.science/api/pith-number/YSC2RN4DAVGWVYXJ2KXYOUO3TI/graph.json","fetch_events":"https://pith.science/api/pith-number/YSC2RN4DAVGWVYXJ2KXYOUO3TI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI/action/storage_attestation","attest_author":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI/action/author_attestation","sign_citation":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI/action/citation_signature","submit_replication":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI/action/replication_record"}},"created_at":"2026-07-05T11:28:37.615215+00:00","updated_at":"2026-07-05T11:28:37.615215+00:00"}