{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GHEM4VAAXOIK3UXVKETUCTMPVC","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":"257280509c870356bb9a99a77de188bd8d2dd66be46b7ce01f343c8572b212c7","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-03-02T17:45:04Z","title_canon_sha256":"5015a5a375b462037d511281da860437b6f15dcaeab196576032343e97b1945a"},"schema_version":"1.0","source":{"id":"2103.01893","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.01893","created_at":"2026-07-05T03:01:23Z"},{"alias_kind":"arxiv_version","alias_value":"2103.01893v4","created_at":"2026-07-05T03:01:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.01893","created_at":"2026-07-05T03:01:23Z"},{"alias_kind":"pith_short_12","alias_value":"GHEM4VAAXOIK","created_at":"2026-07-05T03:01:23Z"},{"alias_kind":"pith_short_16","alias_value":"GHEM4VAAXOIK3UXV","created_at":"2026-07-05T03:01:23Z"},{"alias_kind":"pith_short_8","alias_value":"GHEM4VAA","created_at":"2026-07-05T03:01:23Z"}],"graph_snapshots":[{"event_id":"sha256:aca8b2fc9f123be4bb883206c613e3b0d0951294184890728b41923c60ad8787","target":"graph","created_at":"2026-07-05T03:01:23Z","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/2103.01893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a multimodal singing language classification model that uses both audio content and textual metadata. LRID-Net, the proposed model, takes an audio signal and a language probability vector estimated from the metadata and outputs the probabilities of the target languages. Optionally, LRID-Net is facilitated with modality dropouts to handle a missing modality. In the experiment, we trained several LRID-Nets with varying modality dropout configuration and tested them with various combinations of input modalities. The experiment results demonstrate that using multimodal input improves pe","authors_text":"Keunwoo Choi, Yuxuan Wang","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-03-02T17:45:04Z","title":"Listen, Read, and Identify: Multimodal Singing Language Identification of Music"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.01893","kind":"arxiv","version":4},"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:b62b9363e82a272cd33d1e3f2fdd939e52169279ce3bb3b5ae42cca6c68fd883","target":"record","created_at":"2026-07-05T03:01:23Z","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":"257280509c870356bb9a99a77de188bd8d2dd66be46b7ce01f343c8572b212c7","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-03-02T17:45:04Z","title_canon_sha256":"5015a5a375b462037d511281da860437b6f15dcaeab196576032343e97b1945a"},"schema_version":"1.0","source":{"id":"2103.01893","kind":"arxiv","version":4}},"canonical_sha256":"31c8ce5400bb90add2f55127414d8fa89415ceb03851bd607de21790054a0ef8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31c8ce5400bb90add2f55127414d8fa89415ceb03851bd607de21790054a0ef8","first_computed_at":"2026-07-05T03:01:23.434663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:01:23.434663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lqajcmRkOU1pOUpxh85JZBfrrr8W9HKTTBfZNSmEchgEXdMcoh5ZsztNwb6QOPLyYl2KVFPuqyRQ2NT5tRH1Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:01:23.435102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.01893","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b62b9363e82a272cd33d1e3f2fdd939e52169279ce3bb3b5ae42cca6c68fd883","sha256:aca8b2fc9f123be4bb883206c613e3b0d0951294184890728b41923c60ad8787"],"state_sha256":"ed6283625ebeaeabecb91734184a9b1253c1a4158ff2c37fdad757e235cb84e6"}