{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZW2ABK3Z756E3KGTOT2L4CZQOQ","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":"eacb265b283cfc709a326b41c4cd583e44554f76248859c16cff7d22ab73bd3f","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-19T13:26:51Z","title_canon_sha256":"80a95b1651d5acf595cbb6ec2dad6b79228a31a599b183e9cf409938a95fd5f5"},"schema_version":"1.0","source":{"id":"2605.19833","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19833","created_at":"2026-05-20T01:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19833v1","created_at":"2026-05-20T01:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19833","created_at":"2026-05-20T01:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZW2ABK3Z756E","created_at":"2026-05-20T01:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZW2ABK3Z756E3KGT","created_at":"2026-05-20T01:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZW2ABK3Z","created_at":"2026-05-20T01:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:36aa130a3698ba9cc6d17fea99c8e7370fe868307bc93720e2ef24457c9b598a","target":"graph","created_at":"2026-05-20T01:06:16Z","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/2605.19833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chunyan Miao, Deheng Ye, Haobin Zhang, Kaiyu Pang, Shuicheng Yan, Xiaobin Hu, Zhifei Xie","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-19T13:26:51Z","title":"Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19833","kind":"arxiv","version":1},"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":"sha256:2e78d6b0921409726d28cf111971b26c537f7a1290bfdccb98922bf5c3957e11","target":"record","created_at":"2026-05-20T01:06:16Z","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":"eacb265b283cfc709a326b41c4cd583e44554f76248859c16cff7d22ab73bd3f","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-19T13:26:51Z","title_canon_sha256":"80a95b1651d5acf595cbb6ec2dad6b79228a31a599b183e9cf409938a95fd5f5"},"schema_version":"1.0","source":{"id":"2605.19833","kind":"arxiv","version":1}},"canonical_sha256":"cdb400ab79ff7c4da8d374f4be0b30742f03f04eff55c7a434ab855c273464b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdb400ab79ff7c4da8d374f4be0b30742f03f04eff55c7a434ab855c273464b1","first_computed_at":"2026-05-20T01:06:16.834673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:06:16.834673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EcEblfswGXITsW7SaQfVEVMEer4eKg8nlrWXNsQYo5crdwlLa7/0xIQoirGjjrqfCrrijZD2/H2aAG/01qVhBQ==","signature_status":"signed_v1","signed_at":"2026-05-20T01:06:16.835442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19833","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e78d6b0921409726d28cf111971b26c537f7a1290bfdccb98922bf5c3957e11","sha256:36aa130a3698ba9cc6d17fea99c8e7370fe868307bc93720e2ef24457c9b598a"],"state_sha256":"1aa56c24628d1356966b6b6520a1f0158f5e5731eb839b8389c432c7977839fd"}