{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3PK4DJBXN6M2LMIDZGHJPYEHN3","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":"f1e9e692c6efa5651affc7d1b3a0a3075e29e16840ae8335250e7e385d5ba51c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-03-05T06:35:59Z","title_canon_sha256":"1dc0a9e99e73172b3a074664ee134d1b160c23d0b01d50bc6f14f2d0d5125b83"},"schema_version":"1.0","source":{"id":"2603.04862","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.04862","created_at":"2026-05-26T01:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2603.04862v3","created_at":"2026-05-26T01:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.04862","created_at":"2026-05-26T01:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"3PK4DJBXN6M2","created_at":"2026-05-26T01:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"3PK4DJBXN6M2LMID","created_at":"2026-05-26T01:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"3PK4DJBX","created_at":"2026-05-26T01:03:27Z"}],"graph_snapshots":[{"event_id":"sha256:82f49a7083feac60f9dcd0bf0253cb4fa24760e9dbb3a1999b4b684de50ca2dc","target":"graph","created_at":"2026-05-26T01:03:27Z","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/2603.04862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large audio language models (LALMs) are a class of foundation models for audio understanding. Existing LALMs tend to degrade significantly in real-world noisy acoustic conditions where speech and non-speech sounds interfere. While noise-aware fine-tuning can improve robustness, it requires task-specific noisy data and expensive retraining, limiting scalability. To address this issue, we propose Focus-Then-Listen (FTL), a plug-and-play audio enhancer that improves LALMs' noise robustness. Specifically, FTL first separates the input waveform into speech and non-speech, and a modality router is a","authors_text":"Han Yin, Jung-Woo Choi, Ting Dang, Yang Xiao, Younghoo Kwon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-03-05T06:35:59Z","title":"Focus Then Listen: Exploring Plug-and-Play Audio Enhancer for Noise-Robust Large Audio Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.04862","kind":"arxiv","version":3},"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":"sha256:33ea866b2f992eacdebff76154975eb079a2848991bdcc420e17f6b663ec74e7","target":"record","created_at":"2026-05-26T01:03:27Z","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":"f1e9e692c6efa5651affc7d1b3a0a3075e29e16840ae8335250e7e385d5ba51c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-03-05T06:35:59Z","title_canon_sha256":"1dc0a9e99e73172b3a074664ee134d1b160c23d0b01d50bc6f14f2d0d5125b83"},"schema_version":"1.0","source":{"id":"2603.04862","kind":"arxiv","version":3}},"canonical_sha256":"dbd5c1a4376f99a5b103c98e97e0876ee95779634fa0434fd3093c90b302be7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbd5c1a4376f99a5b103c98e97e0876ee95779634fa0434fd3093c90b302be7c","first_computed_at":"2026-05-26T01:03:27.108885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:27.108885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kKMRtwnObFdnY9/u7uh1K87vBo0V0XWnU/70XDgwDCmyVrbZiG/KFXJ4dUE0zqrR1PRQp9ll0DosIaTsVG/hBA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:27.109840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.04862","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33ea866b2f992eacdebff76154975eb079a2848991bdcc420e17f6b663ec74e7","sha256:82f49a7083feac60f9dcd0bf0253cb4fa24760e9dbb3a1999b4b684de50ca2dc"],"state_sha256":"f7db96875eff3bce16b1f1ce818e7f749cbc994fe0505ea227dcbfdfd0e68f79"}