{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R2A4YQKYB6HCSEJLTNCVLPWEHY","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":"7c50548cc00415e6774eb0aaa468ffa0368a6fbc62762ad1a0eefd9dd31d1c7b","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T17:56:53Z","title_canon_sha256":"f73cff485239c5b3e8220e94ece3e7ec789f57842c52edcc8085ea15e3dead81"},"schema_version":"1.0","source":{"id":"2406.10325","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10325","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10325v1","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10325","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"pith_short_12","alias_value":"R2A4YQKYB6HC","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"pith_short_16","alias_value":"R2A4YQKYB6HCSEJL","created_at":"2026-07-05T09:36:45Z"},{"alias_kind":"pith_short_8","alias_value":"R2A4YQKY","created_at":"2026-07-05T09:36:45Z"}],"graph_snapshots":[{"event_id":"sha256:8c04773a81f36872d2145431128972385f3a41640198de0ca711e7f51e29b09c","target":"graph","created_at":"2026-07-05T09:36:45Z","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/2406.10325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Toxicity classification for voice heavily relies on the semantic content of speech. We propose a novel framework that utilizes cross-modal learning to integrate the semantic embedding of text into a multilabel speech toxicity classifier during training. This enables us to incorporate textual information during training while still requiring only audio during inference. We evaluate this classifier on large-scale datasets with real-world characteristics to validate the effectiveness of this framework. Through ablation studies, we demonstrate that general-purpose semantic text embeddings are rich","authors_text":"Hannes Heikinheimo, Janne Pylkk\\\"onen, Joseph Liu, Mahesh Kumar Nandwana, Morgan McGuire","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T17:56:53Z","title":"Enhancing Multilingual Voice Toxicity Detection with Speech-Text Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10325","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":"sha256:6a9126ab7ec0b7c72bbea9bf39cde8e71e34e2bbefea6308d59f995ae742ac90","target":"record","created_at":"2026-07-05T09:36:45Z","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":"7c50548cc00415e6774eb0aaa468ffa0368a6fbc62762ad1a0eefd9dd31d1c7b","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T17:56:53Z","title_canon_sha256":"f73cff485239c5b3e8220e94ece3e7ec789f57842c52edcc8085ea15e3dead81"},"schema_version":"1.0","source":{"id":"2406.10325","kind":"arxiv","version":1}},"canonical_sha256":"8e81cc41580f8e29112b9b4555bec43e32b3f757914de646bafba3aefa1149f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e81cc41580f8e29112b9b4555bec43e32b3f757914de646bafba3aefa1149f9","first_computed_at":"2026-07-05T09:36:45.875968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:45.875968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3xKMKoY2q9zFU9bMC6R6BuWOSdNLNId08FMmqjjiIHmCAJOLq1NxCq12qUZ4+xxZp9chJQ9T6FgVStHWewiiDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:45.876476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10325","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a9126ab7ec0b7c72bbea9bf39cde8e71e34e2bbefea6308d59f995ae742ac90","sha256:8c04773a81f36872d2145431128972385f3a41640198de0ca711e7f51e29b09c"],"state_sha256":"312f25007352bc4a394672bfdabbadf4b36c097c281791ba42c15d476993c7ce"}