{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WLFRQAGVVP7MP26WRYMJVAQUGR","short_pith_number":"pith:WLFRQAGV","schema_version":"1.0","canonical_sha256":"b2cb1800d5abfec7ebd68e189a8214347ae5fa05689a77cb7acbd7e72a9578f5","source":{"kind":"arxiv","id":"2510.05478","version":3},"attestation_state":"computed","paper":{"title":"AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dong Yang, Haoyu Zhang, Jiaxian Guo, Yusuke Iwasawa, Yutaka Matsuo","submitted_at":"2025-10-07T00:39:14Z","abstract_excerpt":"Large Audio Language Models (LALMs) exhibit strong capabilities in general audio understanding but remain static after deployment, limiting their adaptability to real-world data. Since supervised fine-tuning is costly, we propose AQA-TTRL, a novel framework for audio understanding that enables on-the-fly evolution via test-time reinforcement learning using only unlabeled test data. It generates pseudo-labels via majority voting and optimizes the model through reinforcement learning. To address the noise in self-generated labels, we introduce confidence weighting to adjust training signals. Fur"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2510.05478","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-10-07T00:39:14Z","cross_cats_sorted":[],"title_canon_sha256":"e5d5becb5d9d40b81bb2200826dc202d65da14b37e5e2ffea93706ec1ffed4c3","abstract_canon_sha256":"5d77e90e87f21ea42f6583f7a7ed895c870f75cf3c215e6ebb9e789a51f740ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:10.701681Z","signature_b64":"ge75kHDuyf0gmWinIOSBQHKrrk54vY8hDOkgMRr3IGRAB+6LK9PQ5txtWdGxTUGTYs8G2d7sdmFY7ooGwMBxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2cb1800d5abfec7ebd68e189a8214347ae5fa05689a77cb7acbd7e72a9578f5","last_reissued_at":"2026-06-09T02:07:10.700651Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:10.700651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dong Yang, Haoyu Zhang, Jiaxian Guo, Yusuke Iwasawa, Yutaka Matsuo","submitted_at":"2025-10-07T00:39:14Z","abstract_excerpt":"Large Audio Language Models (LALMs) exhibit strong capabilities in general audio understanding but remain static after deployment, limiting their adaptability to real-world data. Since supervised fine-tuning is costly, we propose AQA-TTRL, a novel framework for audio understanding that enables on-the-fly evolution via test-time reinforcement learning using only unlabeled test data. It generates pseudo-labels via majority voting and optimizes the model through reinforcement learning. To address the noise in self-generated labels, we introduce confidence weighting to adjust training signals. Fur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.05478","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.05478/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.05478","created_at":"2026-06-09T02:07:10.700785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.05478v3","created_at":"2026-06-09T02:07:10.700785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05478","created_at":"2026-06-09T02:07:10.700785+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLFRQAGVVP7M","created_at":"2026-06-09T02:07:10.700785+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLFRQAGVVP7MP26W","created_at":"2026-06-09T02:07:10.700785+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLFRQAGV","created_at":"2026-06-09T02:07:10.700785+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WLFRQAGVVP7MP26WRYMJVAQUGR","json":"https://pith.science/pith/WLFRQAGVVP7MP26WRYMJVAQUGR.json","graph_json":"https://pith.science/api/pith-number/WLFRQAGVVP7MP26WRYMJVAQUGR/graph.json","events_json":"https://pith.science/api/pith-number/WLFRQAGVVP7MP26WRYMJVAQUGR/events.json","paper":"https://pith.science/paper/WLFRQAGV"},"agent_actions":{"view_html":"https://pith.science/pith/WLFRQAGVVP7MP26WRYMJVAQUGR","download_json":"https://pith.science/pith/WLFRQAGVVP7MP26WRYMJVAQUGR.json","view_paper":"https://pith.science/paper/WLFRQAGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.05478&json=true","fetch_graph":"https://pith.science/api/pith-number/WLFRQAGVVP7MP26WRYMJVAQUGR/graph.json","fetch_events":"https://pith.science/api/pith-number/WLFRQAGVVP7MP26WRYMJVAQUGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLFRQAGVVP7MP26WRYMJVAQUGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLFRQAGVVP7MP26WRYMJVAQUGR/action/storage_attestation","attest_author":"https://pith.science/pith/WLFRQAGVVP7MP26WRYMJVAQUGR/action/author_attestation","sign_citation":"https://pith.science/pith/WLFRQAGVVP7MP26WRYMJVAQUGR/action/citation_signature","submit_replication":"https://pith.science/pith/WLFRQAGVVP7MP26WRYMJVAQUGR/action/replication_record"}},"created_at":"2026-06-09T02:07:10.700785+00:00","updated_at":"2026-06-09T02:07:10.700785+00:00"}