{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U2FXWHZX4R7VHQQWVRPQ4DKYYV","short_pith_number":"pith:U2FXWHZX","schema_version":"1.0","canonical_sha256":"a68b7b1f37e47f53c216ac5f0e0d58c55b5245d56fdb929cb3e244bf6d02ad55","source":{"kind":"arxiv","id":"2403.07937","version":3},"attestation_state":"computed","paper":{"title":"Speech Robust Bench: A Robustness Benchmark For Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bhiksha Raj, David Solans Noguero, Mikko A. Heikkila, Muhammad A. Shah, Nicolas Kourtellis","submitted_at":"2024-03-08T08:10:29Z","abstract_excerpt":"As Automatic Speech Recognition (ASR) models become ever more pervasive, it is important to ensure that they make reliable predictions under corruptions present in the physical and digital world. We propose Speech Robust Bench (SRB), a comprehensive benchmark for evaluating the robustness of ASR models to diverse corruptions. SRB is composed of 114 input perturbations which simulate an heterogeneous range of corruptions that ASR models may encounter when deployed in the wild. We use SRB to evaluate the robustness of several state-of-the-art ASR models and observe that model size and certain mo"},"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":"2403.07937","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-08T08:10:29Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"fa8a7ba792cadd1bbc4ccbf827cb9e9c8d9b19f51f18d681f99da6b947d92069","abstract_canon_sha256":"41ff847626fd1414f8db9016a7e9c4d050014ac91e89fb79e2a0dd5e75964b3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:27.764103Z","signature_b64":"c4ObrLC17+ILG1SKv8dnjzFpEaTGKCk6NPOibklUkywHHIhoU/3HGHc48nC57mm/ELQxBOCqcdoi25c0t7WPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a68b7b1f37e47f53c216ac5f0e0d58c55b5245d56fdb929cb3e244bf6d02ad55","last_reissued_at":"2026-07-05T09:46:27.763625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:27.763625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech Robust Bench: A Robustness Benchmark For Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bhiksha Raj, David Solans Noguero, Mikko A. Heikkila, Muhammad A. Shah, Nicolas Kourtellis","submitted_at":"2024-03-08T08:10:29Z","abstract_excerpt":"As Automatic Speech Recognition (ASR) models become ever more pervasive, it is important to ensure that they make reliable predictions under corruptions present in the physical and digital world. We propose Speech Robust Bench (SRB), a comprehensive benchmark for evaluating the robustness of ASR models to diverse corruptions. SRB is composed of 114 input perturbations which simulate an heterogeneous range of corruptions that ASR models may encounter when deployed in the wild. We use SRB to evaluate the robustness of several state-of-the-art ASR models and observe that model size and certain mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07937","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/2403.07937/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":"2403.07937","created_at":"2026-07-05T09:46:27.763682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07937v3","created_at":"2026-07-05T09:46:27.763682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07937","created_at":"2026-07-05T09:46:27.763682+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2FXWHZX4R7V","created_at":"2026-07-05T09:46:27.763682+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2FXWHZX4R7VHQQW","created_at":"2026-07-05T09:46:27.763682+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2FXWHZX","created_at":"2026-07-05T09:46:27.763682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29114","citing_title":"ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16378","citing_title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12783","citing_title":"SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U2FXWHZX4R7VHQQWVRPQ4DKYYV","json":"https://pith.science/pith/U2FXWHZX4R7VHQQWVRPQ4DKYYV.json","graph_json":"https://pith.science/api/pith-number/U2FXWHZX4R7VHQQWVRPQ4DKYYV/graph.json","events_json":"https://pith.science/api/pith-number/U2FXWHZX4R7VHQQWVRPQ4DKYYV/events.json","paper":"https://pith.science/paper/U2FXWHZX"},"agent_actions":{"view_html":"https://pith.science/pith/U2FXWHZX4R7VHQQWVRPQ4DKYYV","download_json":"https://pith.science/pith/U2FXWHZX4R7VHQQWVRPQ4DKYYV.json","view_paper":"https://pith.science/paper/U2FXWHZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07937&json=true","fetch_graph":"https://pith.science/api/pith-number/U2FXWHZX4R7VHQQWVRPQ4DKYYV/graph.json","fetch_events":"https://pith.science/api/pith-number/U2FXWHZX4R7VHQQWVRPQ4DKYYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2FXWHZX4R7VHQQWVRPQ4DKYYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2FXWHZX4R7VHQQWVRPQ4DKYYV/action/storage_attestation","attest_author":"https://pith.science/pith/U2FXWHZX4R7VHQQWVRPQ4DKYYV/action/author_attestation","sign_citation":"https://pith.science/pith/U2FXWHZX4R7VHQQWVRPQ4DKYYV/action/citation_signature","submit_replication":"https://pith.science/pith/U2FXWHZX4R7VHQQWVRPQ4DKYYV/action/replication_record"}},"created_at":"2026-07-05T09:46:27.763682+00:00","updated_at":"2026-07-05T09:46:27.763682+00:00"}