{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SKE2NBLRWVOUNN7SRJKKBGGJEN","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":"54de44658172ddf00f1ce44369b1df634032bf257d72e15a2e5ce579f574d9c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-17T10:39:01Z","title_canon_sha256":"7c9d282de657efb8aa36a91925d7c3188ba5d23806d7eceee5bb901408e97c81"},"schema_version":"1.0","source":{"id":"2604.15929","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.15929","created_at":"2026-05-20T00:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2604.15929v2","created_at":"2026-05-20T00:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.15929","created_at":"2026-05-20T00:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"SKE2NBLRWVOU","created_at":"2026-05-20T00:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"SKE2NBLRWVOUNN7S","created_at":"2026-05-20T00:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"SKE2NBLR","created_at":"2026-05-20T00:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:d8737be9ceeb75701a62ef6c10d39850b0c3dd091ab02c9d68a735d584b7a0c1","target":"graph","created_at":"2026-05-20T00:05:44Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We propose a new benchmark to evaluate current Automatic Speech Recognition (ASR) systems, whether they are able to handle these challenges. Experimental results demonstrate that the proposed dataset is still an open challenge for state-of-the-art ASR systems."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The bilingual discussions constructed for the benchmark accurately represent the real-world challenges of mixed multilingual input, specific vocabulary, and code-switching in scientific conversations."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MUSCAT is a benchmark of bilingual scientific conversations designed to evaluate ASR systems on code-switching and domain-specific challenges."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MUSCAT introduces a benchmark of bilingual scientific discussions to test ASR systems on mixed-language inputs and code-switching."}],"snapshot_sha256":"6d8a0f5bc0e7d15f03344c9a95410af7421247a9eba7bfbb58b076ff44dd63f2"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.15929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of multilingual speech technology is to facilitate seamless communication between individuals speaking different languages, creating the experience as though everyone were a multilingual speaker. To create this experience, speech technology needs to address several challenges: Handling mixed multilingual input, specific vocabulary, and code-switching. However, there is currently no dataset benchmarking this situation. We propose a new benchmark to evaluate current Automatic Speech Recognition (ASR) systems, whether they are able to handle these challenges. The benchmark consists of bi","authors_text":"Alexander Waibel, Enes Ugan, Jan Niehues, Supriti Sinhamahapatra, Thai-Binh Nguyen, Yi\\u{g}it O\\u{g}uz","cross_cats":[],"headline":"MUSCAT introduces a benchmark of bilingual scientific discussions to test ASR systems on mixed-language inputs and code-switching.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-17T10:39:01Z","title":"MUSCAT: MUltilingual, SCientific ConversATion Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.15929","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T09:16:06.215117Z","id":"a02c27ee-13f0-4021-823a-1f3f43f6af27","model_set":{"reader":"grok-4.3"},"one_line_summary":"MUSCAT is a benchmark of bilingual scientific conversations designed to evaluate ASR systems on code-switching and domain-specific challenges.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MUSCAT introduces a benchmark of bilingual scientific discussions to test ASR systems on mixed-language inputs and code-switching.","strongest_claim":"We propose a new benchmark to evaluate current Automatic Speech Recognition (ASR) systems, whether they are able to handle these challenges. Experimental results demonstrate that the proposed dataset is still an open challenge for state-of-the-art ASR systems.","weakest_assumption":"The bilingual discussions constructed for the benchmark accurately represent the real-world challenges of mixed multilingual input, specific vocabulary, and code-switching in scientific conversations."}},"verdict_id":"a02c27ee-13f0-4021-823a-1f3f43f6af27"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:aa43d38146534fff8062f735cb4b5ead176858cf676a1d0266cdd57d07262f1d","target":"record","created_at":"2026-05-20T00:05:44Z","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":"54de44658172ddf00f1ce44369b1df634032bf257d72e15a2e5ce579f574d9c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-17T10:39:01Z","title_canon_sha256":"7c9d282de657efb8aa36a91925d7c3188ba5d23806d7eceee5bb901408e97c81"},"schema_version":"1.0","source":{"id":"2604.15929","kind":"arxiv","version":2}},"canonical_sha256":"9289a68571b55d46b7f28a54a098c9237a41d3e75b13c9ce61da845ebae538f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9289a68571b55d46b7f28a54a098c9237a41d3e75b13c9ce61da845ebae538f2","first_computed_at":"2026-05-20T00:05:44.791091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:44.791091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a/nzQ9mMOYgSTVTn/jHjZm+6V53zsU2aogEtYgfem8PqrHHW0uEWluRhIxZ5J54BJVYZUe4P0M7GOnXpWYB3DA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:44.791645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.15929","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa43d38146534fff8062f735cb4b5ead176858cf676a1d0266cdd57d07262f1d","sha256:d8737be9ceeb75701a62ef6c10d39850b0c3dd091ab02c9d68a735d584b7a0c1"],"state_sha256":"c01ef3f32d4a059412c1eebe52ecaaa8329bcd8f8c7e171cadda534271022c24"}