{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZMSDFRZRREZTH3XOGVKTLSLNRZ","short_pith_number":"pith:ZMSDFRZR","canonical_record":{"source":{"id":"2306.00680","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-01T13:55:23Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"faa948dca090f3590132ae1bcc09b8b3cea958a72c92a3ccd196db0d587dca09","abstract_canon_sha256":"b8191e70581e671c7489fba750f175d278b3cc5d01227931080ce5f9ec373ff0"},"schema_version":"1.0"},"canonical_sha256":"cb2432c731893333eeee355535c96d8e5eb78ccc96095a221b12fb53d77d0236","source":{"kind":"arxiv","id":"2306.00680","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00680","created_at":"2026-07-05T06:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00680v1","created_at":"2026-07-05T06:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00680","created_at":"2026-07-05T06:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"ZMSDFRZRREZT","created_at":"2026-07-05T06:16:29Z"},{"alias_kind":"pith_short_16","alias_value":"ZMSDFRZRREZTH3XO","created_at":"2026-07-05T06:16:29Z"},{"alias_kind":"pith_short_8","alias_value":"ZMSDFRZR","created_at":"2026-07-05T06:16:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZMSDFRZRREZTH3XOGVKTLSLNRZ","target":"record","payload":{"canonical_record":{"source":{"id":"2306.00680","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-01T13:55:23Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"faa948dca090f3590132ae1bcc09b8b3cea958a72c92a3ccd196db0d587dca09","abstract_canon_sha256":"b8191e70581e671c7489fba750f175d278b3cc5d01227931080ce5f9ec373ff0"},"schema_version":"1.0"},"canonical_sha256":"cb2432c731893333eeee355535c96d8e5eb78ccc96095a221b12fb53d77d0236","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:29.794262Z","signature_b64":"axyIjxFmm2MzXx/Fz2PWFr24yyTh9R0lkqZmbtO86jL6VR1zUUCN+GU9Tpy9/s4ZFJQX3xfC/XX2taLojA+2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb2432c731893333eeee355535c96d8e5eb78ccc96095a221b12fb53d77d0236","last_reissued_at":"2026-07-05T06:16:29.793799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:29.793799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.00680","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":"2026-07-05T06:16:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lPmGtls+1NAdksDtvRLhFbVNjDaDZsvCUxF5xN0lIoq4Zo8IfCxqnv3Wff6pxzMRvwWxBFbCwSKm9GW9F6goCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:46:23.410559Z"},"content_sha256":"d39c9aae0fb5805795cf60de8ca90198c61b60aa276b757bb104f65630e69890","schema_version":"1.0","event_id":"sha256:d39c9aae0fb5805795cf60de8ca90198c61b60aa276b757bb104f65630e69890"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZMSDFRZRREZTH3XOGVKTLSLNRZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Encoder-decoder multimodal speaker change detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bong-Jin Lee, Geonmin Kim, Hee-Soo Heo, Jee-weon Jung, Minjae Lee, Soonshin Seo, You Jin Kim, Young-ki Kwon","submitted_at":"2023-06-01T13:55:23Z","abstract_excerpt":"The task of speaker change detection (SCD), which detects points where speakers change in an input, is essential for several applications. Several studies solved the SCD task using audio inputs only and have shown limited performance. Recently, multimodal SCD (MMSCD) models, which utilise text modality in addition to audio, have shown improved performance. In this study, the proposed model are built upon two main proposals, a novel mechanism for modality fusion and the adoption of a encoder-decoder architecture. Different to previous MMSCD works that extract speaker embeddings from extremely s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00680","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/2306.00680/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":"2026-07-05T06:16:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SYvtXB2aCezYbC0aEdJ+Cp12HStlFwS91qSSI+4QVbxQOP+oXuUxPa9PwlYq8/v3FXlblyD4dmhniZBRiQGIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:46:23.411275Z"},"content_sha256":"d70a9d7b7b720fc515f74825718ba7eac72faffbb5f5a93fa3cee1bd5d7ae0bb","schema_version":"1.0","event_id":"sha256:d70a9d7b7b720fc515f74825718ba7eac72faffbb5f5a93fa3cee1bd5d7ae0bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZMSDFRZRREZTH3XOGVKTLSLNRZ/bundle.json","state_url":"https://pith.science/pith/ZMSDFRZRREZTH3XOGVKTLSLNRZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZMSDFRZRREZTH3XOGVKTLSLNRZ/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":"2026-07-09T06:46:23Z","links":{"resolver":"https://pith.science/pith/ZMSDFRZRREZTH3XOGVKTLSLNRZ","bundle":"https://pith.science/pith/ZMSDFRZRREZTH3XOGVKTLSLNRZ/bundle.json","state":"https://pith.science/pith/ZMSDFRZRREZTH3XOGVKTLSLNRZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZMSDFRZRREZTH3XOGVKTLSLNRZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZMSDFRZRREZTH3XOGVKTLSLNRZ","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":"b8191e70581e671c7489fba750f175d278b3cc5d01227931080ce5f9ec373ff0","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-01T13:55:23Z","title_canon_sha256":"faa948dca090f3590132ae1bcc09b8b3cea958a72c92a3ccd196db0d587dca09"},"schema_version":"1.0","source":{"id":"2306.00680","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00680","created_at":"2026-07-05T06:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00680v1","created_at":"2026-07-05T06:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00680","created_at":"2026-07-05T06:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"ZMSDFRZRREZT","created_at":"2026-07-05T06:16:29Z"},{"alias_kind":"pith_short_16","alias_value":"ZMSDFRZRREZTH3XO","created_at":"2026-07-05T06:16:29Z"},{"alias_kind":"pith_short_8","alias_value":"ZMSDFRZR","created_at":"2026-07-05T06:16:29Z"}],"graph_snapshots":[{"event_id":"sha256:d70a9d7b7b720fc515f74825718ba7eac72faffbb5f5a93fa3cee1bd5d7ae0bb","target":"graph","created_at":"2026-07-05T06:16:29Z","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/2306.00680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The task of speaker change detection (SCD), which detects points where speakers change in an input, is essential for several applications. Several studies solved the SCD task using audio inputs only and have shown limited performance. Recently, multimodal SCD (MMSCD) models, which utilise text modality in addition to audio, have shown improved performance. In this study, the proposed model are built upon two main proposals, a novel mechanism for modality fusion and the adoption of a encoder-decoder architecture. Different to previous MMSCD works that extract speaker embeddings from extremely s","authors_text":"Bong-Jin Lee, Geonmin Kim, Hee-Soo Heo, Jee-weon Jung, Minjae Lee, Soonshin Seo, You Jin Kim, Young-ki Kwon","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-01T13:55:23Z","title":"Encoder-decoder multimodal speaker change detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00680","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:d39c9aae0fb5805795cf60de8ca90198c61b60aa276b757bb104f65630e69890","target":"record","created_at":"2026-07-05T06:16:29Z","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":"b8191e70581e671c7489fba750f175d278b3cc5d01227931080ce5f9ec373ff0","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-01T13:55:23Z","title_canon_sha256":"faa948dca090f3590132ae1bcc09b8b3cea958a72c92a3ccd196db0d587dca09"},"schema_version":"1.0","source":{"id":"2306.00680","kind":"arxiv","version":1}},"canonical_sha256":"cb2432c731893333eeee355535c96d8e5eb78ccc96095a221b12fb53d77d0236","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb2432c731893333eeee355535c96d8e5eb78ccc96095a221b12fb53d77d0236","first_computed_at":"2026-07-05T06:16:29.793799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:29.793799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"axyIjxFmm2MzXx/Fz2PWFr24yyTh9R0lkqZmbtO86jL6VR1zUUCN+GU9Tpy9/s4ZFJQX3xfC/XX2taLojA+2DA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:29.794262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00680","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d39c9aae0fb5805795cf60de8ca90198c61b60aa276b757bb104f65630e69890","sha256:d70a9d7b7b720fc515f74825718ba7eac72faffbb5f5a93fa3cee1bd5d7ae0bb"],"state_sha256":"cd00498bfee9c9f7624abca67c64a2574ff92e42bf8763a68127d8f5399d1fc8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FGgp8vYLbUoDOD9uCnZFhyFXByvJ5nRNxdxwP/L3aLTRnh3elFLqDWAgpX35sBIQswA9oETO9OAOGtp8Fml1BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:46:23.414429Z","bundle_sha256":"e731b20da6f6cdd687488c80fca51874b08f2078e9552aaf325535cb29dfbea4"}}