{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZW2ABK3Z756E3KGTOT2L4CZQOQ","short_pith_number":"pith:ZW2ABK3Z","schema_version":"1.0","canonical_sha256":"cdb400ab79ff7c4da8d374f4be0b30742f03f04eff55c7a434ab855c273464b1","source":{"kind":"arxiv","id":"2605.19833","version":1},"attestation_state":"computed","paper":{"title":"Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chunyan Miao, Deheng Ye, Haobin Zhang, Kaiyu Pang, Shuicheng Yan, Xiaobin Hu, Zhifei Xie","submitted_at":"2026-05-19T13:26:51Z","abstract_excerpt":"Despite rapid advances in automatic speech recognition (ASR) and large audio-language models, robust recognition in real-world environments remains limited by an \"acoustic robustness bottleneck\": models often lose acoustic grounding and produce omissions or hallucinations under severe, compositional distortions. We propose Mega-ASR, a unified ASR-in-the-wild framework that combines scalable compound-data construction with progressive acoustic-to-semantic optimization. We introduce Voices-in-the-Wild-2M, covering 7 classic acoustic phenomena and 54 physically plausible compound scenarios, and t"},"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":"2605.19833","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-19T13:26:51Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"title_canon_sha256":"80a95b1651d5acf595cbb6ec2dad6b79228a31a599b183e9cf409938a95fd5f5","abstract_canon_sha256":"eacb265b283cfc709a326b41c4cd583e44554f76248859c16cff7d22ab73bd3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:16.835442Z","signature_b64":"EcEblfswGXITsW7SaQfVEVMEer4eKg8nlrWXNsQYo5crdwlLa7/0xIQoirGjjrqfCrrijZD2/H2aAG/01qVhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdb400ab79ff7c4da8d374f4be0b30742f03f04eff55c7a434ab855c273464b1","last_reissued_at":"2026-05-20T01:06:16.834673Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:16.834673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chunyan Miao, Deheng Ye, Haobin Zhang, Kaiyu Pang, Shuicheng Yan, Xiaobin Hu, Zhifei Xie","submitted_at":"2026-05-19T13:26:51Z","abstract_excerpt":"Despite rapid advances in automatic speech recognition (ASR) and large audio-language models, robust recognition in real-world environments remains limited by an \"acoustic robustness bottleneck\": models often lose acoustic grounding and produce omissions or hallucinations under severe, compositional distortions. We propose Mega-ASR, a unified ASR-in-the-wild framework that combines scalable compound-data construction with progressive acoustic-to-semantic optimization. We introduce Voices-in-the-Wild-2M, covering 7 classic acoustic phenomena and 54 physically plausible compound scenarios, and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19833","kind":"arxiv","version":1},"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/2605.19833/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":"2605.19833","created_at":"2026-05-20T01:06:16.834803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19833v1","created_at":"2026-05-20T01:06:16.834803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19833","created_at":"2026-05-20T01:06:16.834803+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZW2ABK3Z756E","created_at":"2026-05-20T01:06:16.834803+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZW2ABK3Z756E3KGT","created_at":"2026-05-20T01:06:16.834803+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZW2ABK3Z","created_at":"2026-05-20T01:06:16.834803+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/ZW2ABK3Z756E3KGTOT2L4CZQOQ","json":"https://pith.science/pith/ZW2ABK3Z756E3KGTOT2L4CZQOQ.json","graph_json":"https://pith.science/api/pith-number/ZW2ABK3Z756E3KGTOT2L4CZQOQ/graph.json","events_json":"https://pith.science/api/pith-number/ZW2ABK3Z756E3KGTOT2L4CZQOQ/events.json","paper":"https://pith.science/paper/ZW2ABK3Z"},"agent_actions":{"view_html":"https://pith.science/pith/ZW2ABK3Z756E3KGTOT2L4CZQOQ","download_json":"https://pith.science/pith/ZW2ABK3Z756E3KGTOT2L4CZQOQ.json","view_paper":"https://pith.science/paper/ZW2ABK3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19833&json=true","fetch_graph":"https://pith.science/api/pith-number/ZW2ABK3Z756E3KGTOT2L4CZQOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZW2ABK3Z756E3KGTOT2L4CZQOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZW2ABK3Z756E3KGTOT2L4CZQOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZW2ABK3Z756E3KGTOT2L4CZQOQ/action/storage_attestation","attest_author":"https://pith.science/pith/ZW2ABK3Z756E3KGTOT2L4CZQOQ/action/author_attestation","sign_citation":"https://pith.science/pith/ZW2ABK3Z756E3KGTOT2L4CZQOQ/action/citation_signature","submit_replication":"https://pith.science/pith/ZW2ABK3Z756E3KGTOT2L4CZQOQ/action/replication_record"}},"created_at":"2026-05-20T01:06:16.834803+00:00","updated_at":"2026-05-20T01:06:16.834803+00:00"}