{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TYNRTIPQHLSCW7MVJCWERHQVGY","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":"d2cee1fd02cd40e01e50d8fb6b2439be51edf9592182a086912856951b922371","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-17T02:13:58Z","title_canon_sha256":"91eca395424920448f8f8f0f2ed0fd400187c916b1602de2e5dc94304d7094b6"},"schema_version":"1.0","source":{"id":"2605.17225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17225","created_at":"2026-05-20T00:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17225v1","created_at":"2026-05-20T00:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17225","created_at":"2026-05-20T00:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"TYNRTIPQHLSC","created_at":"2026-05-20T00:03:46Z"},{"alias_kind":"pith_short_16","alias_value":"TYNRTIPQHLSCW7MV","created_at":"2026-05-20T00:03:46Z"},{"alias_kind":"pith_short_8","alias_value":"TYNRTIPQ","created_at":"2026-05-20T00:03:46Z"}],"graph_snapshots":[{"event_id":"sha256:99c4ae520802b45a3817c9383e591ba42cee3d8667a1423b5302154279c71d14","target":"graph","created_at":"2026-05-20T00:03:46Z","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":"strong single performance does not ensure robust selective auditory attention: cocktail party accuracy degrades under severe SNRs, and errors are dominated by distractor-grounded source confusion. In addition, separation reduces acoustic overlap but leaves source attribution unresolved, often yielding confident wrong-stream answers."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The MUSA benchmark pairs English targets with semantically plausible distractors under controlled SNRs in single, two-stage, and end-to-end settings, assuming this construction accurately measures selective auditory attention without major confounding factors from the specific dialogue content or model training data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Introduces the MUSA benchmark and evaluates LALMs showing that strong single-speaker performance fails to ensure robust selective attention under multilingual interference, with errors from source confusion and unresolved attribution after separation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Large audio language models lose selective attention to English targets when multilingual distractors appear at low signal-to-noise ratios."}],"snapshot_sha256":"af4eecb5ae7658a758cf42181ba7f163a1650b29dec36763b7b2f426c16d3c39"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:20.355347Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T23:22:22.898125Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.910606Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.806626Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17225/integrity.json","findings":[],"snapshot_sha256":"d10e32fc2de6b09d0c700f4c69f49ad235b1fb3e55dc342da97bcfa70b99052f","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust selective auditory attention under multilingual interference is critical for reliable deployment of Large Audio Language Models (LALMs). We introduce MUSA, a cocktail party-inspired multilingual benchmark for source-grounded spoken-language understanding and reasoning. Each item pairs an English target dialogue with a semantically plausible distractor in English, Spanish, Korean, or Chinese, and evaluates models across (1) single, (2) source separation-based two-stage, (3) and end-to-end cocktail party settings under controlled SNRs. Evaluating two closed-source and four open-weight LAL","authors_text":"Heejoon Koo","cross_cats":[],"headline":"Large audio language models lose selective attention to English targets when multilingual distractors appear at low signal-to-noise ratios.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-17T02:13:58Z","title":"Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities"},"references":{"count":36,"internal_anchors":7,"resolved_work":36,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Situational awareness , pages=","work_id":"7199963f-dbe2-4eea-a620-4532164d80f6","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Journal of the acoustical society of America , volume=","work_id":"6516012c-659c-4ffe-9b11-610c6f874bad","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=","work_id":"2e9aa9ac-c395-45a3-b980-49925a891304","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"arXiv preprint arXiv:2501.04962 , year=","work_id":"674808a4-e636-424c-882e-72318e2120af","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Audiotrust: Benchmarking the multifaceted trustworthiness of audio large language models","work_id":"ddc276b0-adb9-4470-99e0-fa7f1b36a213","year":null}],"snapshot_sha256":"93a9fbadc82b4f2e6e2382834a84ec6a37544ea14d22437d901222ee40bd0ba3"},"source":{"id":"2605.17225","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T23:13:12.660168Z","id":"b5bfd01b-fc3a-455d-a9a9-bb7da9626d62","model_set":{"reader":"grok-4.3"},"one_line_summary":"Introduces the MUSA benchmark and evaluates LALMs showing that strong single-speaker performance fails to ensure robust selective attention under multilingual interference, with errors from source confusion and unresolved attribution after separation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Large audio language models lose selective attention to English targets when multilingual distractors appear at low signal-to-noise ratios.","strongest_claim":"strong single performance does not ensure robust selective auditory attention: cocktail party accuracy degrades under severe SNRs, and errors are dominated by distractor-grounded source confusion. In addition, separation reduces acoustic overlap but leaves source attribution unresolved, often yielding confident wrong-stream answers.","weakest_assumption":"The MUSA benchmark pairs English targets with semantically plausible distractors under controlled SNRs in single, two-stage, and end-to-end settings, assuming this construction accurately measures selective auditory attention without major confounding factors from the specific dialogue content or model training data."}},"verdict_id":"b5bfd01b-fc3a-455d-a9a9-bb7da9626d62"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4801b61238130da3feeff7156d3ef742dc95a12b3990da4091c458e0fe32c520","target":"record","created_at":"2026-05-20T00:03:46Z","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":"d2cee1fd02cd40e01e50d8fb6b2439be51edf9592182a086912856951b922371","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-17T02:13:58Z","title_canon_sha256":"91eca395424920448f8f8f0f2ed0fd400187c916b1602de2e5dc94304d7094b6"},"schema_version":"1.0","source":{"id":"2605.17225","kind":"arxiv","version":1}},"canonical_sha256":"9e1b19a1f03ae42b7d9548ac489e15362e2d0d88d52d2011ae1bed8e54eda4eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e1b19a1f03ae42b7d9548ac489e15362e2d0d88d52d2011ae1bed8e54eda4eb","first_computed_at":"2026-05-20T00:03:46.147257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:46.147257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e5CKXBSCduyAXFeZ1HC8naUTg4iGQkc2ctphzJM6UAch3s5eL6A1KmQ43wN1a2FjPlyIWR0OaQ9g905ri1WqAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:46.148167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4801b61238130da3feeff7156d3ef742dc95a12b3990da4091c458e0fe32c520","sha256:99c4ae520802b45a3817c9383e591ba42cee3d8667a1423b5302154279c71d14"],"state_sha256":"b57111cafc5b580677ed67f705d1a65e1516746bee2f8e2c656148f7706ca30b"}