{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CAN5UIRKN73WOA7KSRFJCFS5KB","short_pith_number":"pith:CAN5UIRK","schema_version":"1.0","canonical_sha256":"101bda222a6ff76703ea944a91165d506598bfddf2f49858f99d5b456c082d9c","source":{"kind":"arxiv","id":"2605.30899","version":1},"attestation_state":"computed","paper":{"title":"A Unified and Reproducible Experimentation Framework for Speech Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenghao Wang, Duo Ma, Guanyu Chen, Hanqi Li, Haoran Wang, Haoyu Li, Hui Zhang, Jiang Li, Jiaqi Guo, Jing Peng, Junhao Du, Kai Yu, Lirong Qian, Shuai Fan, Shuai Wang, Wenbin Jiang, Wenming Tu, Wen Wen, Xiaoyu Gu, Yixuan Wang, Yi Yang, Yucheng Wang, Yu Xi, Zhangjie Zhao","submitted_at":"2026-05-29T06:33:36Z","abstract_excerpt":"Speech foundation models and Speech LLMs have advanced speech understanding, yet deployment-oriented model selection is hindered by non-comparable evaluations caused by mismatched post-processing, and by training results that are hard to reproduce across data scales and pipelines. We present SURE, a unified experimentation framework that standardizes prediction formats, normalization, and scoring. SURE evaluates strong systems across paradigms, from conventional pipelines to Speech LLMs, on representative tasks under realistic acoustic and linguistic stressors. Beyond evaluation, SURE introduc"},"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":"2605.30899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T06:33:36Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"e29c4b435d84241ca73816671615029013eb88c356c712899028ae2e1175a8ca","abstract_canon_sha256":"bc2aafedd7f2e93422bceb28707a1ff8d06629abb4d0e016428fe71c1627dbe8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:24.476286Z","signature_b64":"umIe/G69S237JWdZARPMM34oR/EkLIeogXHYknmG9QeTZYyaGXb88g3KRnL87cdzloSRTgmp42KB2GrQOldZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"101bda222a6ff76703ea944a91165d506598bfddf2f49858f99d5b456c082d9c","last_reissued_at":"2026-06-01T01:03:24.475441Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:24.475441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified and Reproducible Experimentation Framework for Speech Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenghao Wang, Duo Ma, Guanyu Chen, Hanqi Li, Haoran Wang, Haoyu Li, Hui Zhang, Jiang Li, Jiaqi Guo, Jing Peng, Junhao Du, Kai Yu, Lirong Qian, Shuai Fan, Shuai Wang, Wenbin Jiang, Wenming Tu, Wen Wen, Xiaoyu Gu, Yixuan Wang, Yi Yang, Yucheng Wang, Yu Xi, Zhangjie Zhao","submitted_at":"2026-05-29T06:33:36Z","abstract_excerpt":"Speech foundation models and Speech LLMs have advanced speech understanding, yet deployment-oriented model selection is hindered by non-comparable evaluations caused by mismatched post-processing, and by training results that are hard to reproduce across data scales and pipelines. We present SURE, a unified experimentation framework that standardizes prediction formats, normalization, and scoring. SURE evaluates strong systems across paradigms, from conventional pipelines to Speech LLMs, on representative tasks under realistic acoustic and linguistic stressors. Beyond evaluation, SURE introduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30899","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/2605.30899/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":"2605.30899","created_at":"2026-06-01T01:03:24.475629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30899v1","created_at":"2026-06-01T01:03:24.475629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30899","created_at":"2026-06-01T01:03:24.475629+00:00"},{"alias_kind":"pith_short_12","alias_value":"CAN5UIRKN73W","created_at":"2026-06-01T01:03:24.475629+00:00"},{"alias_kind":"pith_short_16","alias_value":"CAN5UIRKN73WOA7K","created_at":"2026-06-01T01:03:24.475629+00:00"},{"alias_kind":"pith_short_8","alias_value":"CAN5UIRK","created_at":"2026-06-01T01:03:24.475629+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/CAN5UIRKN73WOA7KSRFJCFS5KB","json":"https://pith.science/pith/CAN5UIRKN73WOA7KSRFJCFS5KB.json","graph_json":"https://pith.science/api/pith-number/CAN5UIRKN73WOA7KSRFJCFS5KB/graph.json","events_json":"https://pith.science/api/pith-number/CAN5UIRKN73WOA7KSRFJCFS5KB/events.json","paper":"https://pith.science/paper/CAN5UIRK"},"agent_actions":{"view_html":"https://pith.science/pith/CAN5UIRKN73WOA7KSRFJCFS5KB","download_json":"https://pith.science/pith/CAN5UIRKN73WOA7KSRFJCFS5KB.json","view_paper":"https://pith.science/paper/CAN5UIRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30899&json=true","fetch_graph":"https://pith.science/api/pith-number/CAN5UIRKN73WOA7KSRFJCFS5KB/graph.json","fetch_events":"https://pith.science/api/pith-number/CAN5UIRKN73WOA7KSRFJCFS5KB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CAN5UIRKN73WOA7KSRFJCFS5KB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CAN5UIRKN73WOA7KSRFJCFS5KB/action/storage_attestation","attest_author":"https://pith.science/pith/CAN5UIRKN73WOA7KSRFJCFS5KB/action/author_attestation","sign_citation":"https://pith.science/pith/CAN5UIRKN73WOA7KSRFJCFS5KB/action/citation_signature","submit_replication":"https://pith.science/pith/CAN5UIRKN73WOA7KSRFJCFS5KB/action/replication_record"}},"created_at":"2026-06-01T01:03:24.475629+00:00","updated_at":"2026-06-01T01:03:24.475629+00:00"}