{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5QWP722OLF5PWZOIB4W4PHMZRG","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":"16e722fa204e946e18cefdbcf40f391a29a8866f248d3aedb97dbddff7854058","cross_cats_sorted":["cs.LG","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T13:45:42Z","title_canon_sha256":"11c3e1bda491d590cb06df54b0f53ac2507e589ab7d2c8b54386ae1f4cc0571d"},"schema_version":"1.0","source":{"id":"2307.15097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15097","created_at":"2026-07-05T06:35:30Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15097v1","created_at":"2026-07-05T06:35:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15097","created_at":"2026-07-05T06:35:30Z"},{"alias_kind":"pith_short_12","alias_value":"5QWP722OLF5P","created_at":"2026-07-05T06:35:30Z"},{"alias_kind":"pith_short_16","alias_value":"5QWP722OLF5PWZOI","created_at":"2026-07-05T06:35:30Z"},{"alias_kind":"pith_short_8","alias_value":"5QWP722O","created_at":"2026-07-05T06:35:30Z"}],"graph_snapshots":[{"event_id":"sha256:552abd14efaa4aab2b61d815eafd1d4c6747850645bf1f45ce2bb5175e38fe25","target":"graph","created_at":"2026-07-05T06:35:30Z","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/2307.15097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel cascaded cross-modal transformer (CCMT) that combines speech and text transcripts to detect customer requests and complaints in phone conversations. Our approach leverages a multimodal paradigm by transcribing the speech using automatic speech recognition (ASR) models and translating the transcripts into different languages. Subsequently, we combine language-specific BERT-based models with Wav2Vec2.0 audio features in a novel cascaded cross-attention transformer model. We apply our system to the Requests Sub-Challenge of the ACM Multimedia 2023 Computational Paralinguistics ","authors_text":"Nicolae-Catalin Ristea, Radu Tudor Ionescu","cross_cats":["cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T13:45:42Z","title":"Cascaded Cross-Modal Transformer for Request and Complaint Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15097","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":"sha256:375d714e547cf7e8fa9d8df0f4ca170758067797312650ca019fbcee66b616b9","target":"record","created_at":"2026-07-05T06:35:30Z","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":"16e722fa204e946e18cefdbcf40f391a29a8866f248d3aedb97dbddff7854058","cross_cats_sorted":["cs.LG","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T13:45:42Z","title_canon_sha256":"11c3e1bda491d590cb06df54b0f53ac2507e589ab7d2c8b54386ae1f4cc0571d"},"schema_version":"1.0","source":{"id":"2307.15097","kind":"arxiv","version":1}},"canonical_sha256":"ec2cffeb4e597afb65c80f2dc79d9989a3481c24819ae7588aea43f0b86be830","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec2cffeb4e597afb65c80f2dc79d9989a3481c24819ae7588aea43f0b86be830","first_computed_at":"2026-07-05T06:35:30.402149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:30.402149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k0S2tHo9lgsAIlcCb2LdZ2L1iwjdZv1Z6AXSYjKW0gfjLPcQsq5ZC2KnxvtNksbnECda09EhAGnAalV2mw2EDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:30.402539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.15097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:375d714e547cf7e8fa9d8df0f4ca170758067797312650ca019fbcee66b616b9","sha256:552abd14efaa4aab2b61d815eafd1d4c6747850645bf1f45ce2bb5175e38fe25"],"state_sha256":"ffa5e5666f7560b9eccb044e7e6cfbc5cb99fe9a3b021e345633530a9578b33e"}