{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YSC2RN4DAVGWVYXJ2KXYOUO3TI","short_pith_number":"pith:YSC2RN4D","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"},"canonical_sha256":"c485a8b783054d6ae2e9d2af8751db9a26cdcb6b48b900f624d411b613f742a9","source":{"kind":"arxiv","id":"2506.14427","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14427","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14427v2","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14427","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_12","alias_value":"YSC2RN4DAVGW","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_16","alias_value":"YSC2RN4DAVGWVYXJ","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_8","alias_value":"YSC2RN4D","created_at":"2026-07-05T11:28:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YSC2RN4DAVGWVYXJ2KXYOUO3TI","target":"record","payload":{"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"},"canonical_sha256":"c485a8b783054d6ae2e9d2af8751db9a26cdcb6b48b900f624d411b613f742a9","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"},"source_kind":"arxiv","source_id":"2506.14427","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":"2026-07-05T11:28:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hziL6BAXYAoehq4hrepgKSk9Dib6LGxDrC7s9AUvGFyB2xe+R7b4mpG6Zg2Bb/Vri4r8OK1SvzQagN7AtGPuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:58:30.379403Z"},"content_sha256":"27f4c57ed59daaf49fb66d2bc9ee235917d18b51f8d86d69c751553cd4fba503","schema_version":"1.0","event_id":"sha256:27f4c57ed59daaf49fb66d2bc9ee235917d18b51f8d86d69c751553cd4fba503"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YSC2RN4DAVGWVYXJ2KXYOUO3TI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:28:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uC6oidBYfNsJgoXO0tQhkZvsxUFSJH/N3/yiCMvDegGLAOwSK4YSupgTMUNvuw2DibROF4g++50FVhv7vgtUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:58:30.379905Z"},"content_sha256":"a8b515e589624e50c18b9ee0e2260c7aeb67e6492abbb25843651191d77591e8","schema_version":"1.0","event_id":"sha256:a8b515e589624e50c18b9ee0e2260c7aeb67e6492abbb25843651191d77591e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI/bundle.json","state_url":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI/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":"2026-08-05T04:58:30Z","links":{"resolver":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI","bundle":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI/bundle.json","state":"https://pith.science/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YSC2RN4DAVGWVYXJ2KXYOUO3TI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YSC2RN4DAVGWVYXJ2KXYOUO3TI","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":"d5164fcefc5bf6a1c9a85fb9a7e40c984db234ed881135df8cba573c327d0606","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-17T11:44:20Z","title_canon_sha256":"3a4d6a22294f1cd7a62a06ef5856a96a05bc5aad23def2e2e0dd0a256dca07a1"},"schema_version":"1.0","source":{"id":"2506.14427","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14427","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14427v2","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14427","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_12","alias_value":"YSC2RN4DAVGW","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_16","alias_value":"YSC2RN4DAVGWVYXJ","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_8","alias_value":"YSC2RN4D","created_at":"2026-07-05T11:28:37Z"}],"graph_snapshots":[{"event_id":"sha256:a8b515e589624e50c18b9ee0e2260c7aeb67e6492abbb25843651191d77591e8","target":"graph","created_at":"2026-07-05T11:28:37Z","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/2506.14427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Shilong Wu","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-17T11:44:20Z","title":"M3SD: Multi-modal, Multi-scenario and Multi-language Speaker Diarization Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14427","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":"sha256:27f4c57ed59daaf49fb66d2bc9ee235917d18b51f8d86d69c751553cd4fba503","target":"record","created_at":"2026-07-05T11:28:37Z","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":"d5164fcefc5bf6a1c9a85fb9a7e40c984db234ed881135df8cba573c327d0606","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-17T11:44:20Z","title_canon_sha256":"3a4d6a22294f1cd7a62a06ef5856a96a05bc5aad23def2e2e0dd0a256dca07a1"},"schema_version":"1.0","source":{"id":"2506.14427","kind":"arxiv","version":2}},"canonical_sha256":"c485a8b783054d6ae2e9d2af8751db9a26cdcb6b48b900f624d411b613f742a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c485a8b783054d6ae2e9d2af8751db9a26cdcb6b48b900f624d411b613f742a9","first_computed_at":"2026-07-05T11:28:37.615164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:37.615164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t6AIkw3x34k1MsXQGHy1tGTRTk8EFqikhikmfigA9zA6+u+6j/UzhcIKskcuEEvO6SU54az0QqjdfokUhnQ5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:37.615663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14427","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27f4c57ed59daaf49fb66d2bc9ee235917d18b51f8d86d69c751553cd4fba503","sha256:a8b515e589624e50c18b9ee0e2260c7aeb67e6492abbb25843651191d77591e8"],"state_sha256":"701d173e29631f3140fbdf443afaf63ff49d7cab145c92649f5e91238f03a563"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ooSn6KRP+DZVW4dWQeso+sbhowSh6QY/KeXHwyY1zHah4l6SaleZB9L1d/KcNloo7aYNwp/SRCv9T7gJRV/7CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:58:30.383663Z","bundle_sha256":"508378b8c3f380fc44719eb75db85f270ceede22db0551f3a20f10c837ec827d"}}