{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E3O2BMCFX6YCAAICHQQG5KM7OW","short_pith_number":"pith:E3O2BMCF","schema_version":"1.0","canonical_sha256":"26dda0b045bfb02001023c206ea99f75b8a4b16074e5936ac1a736092c84da83","source":{"kind":"arxiv","id":"2607.09833","version":1},"attestation_state":"computed","paper":{"title":"Generative Testing of Automated Speech Recognition Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Andrea Stocco, Oliver Wei{\\ss}l, Yanis Xabier Wilbrand Pe\\~na","submitted_at":"2026-07-10T14:04:28Z","abstract_excerpt":"Automatic speech recognition (ASR) systems have achieved high accuracy with transformer-based models, enabling deployment in critical applications. However, they remain vulnerable to adversarial manipulation, particularly in black-box settings where attacks must preserve perceptual naturalness. This work introduces GATAS, a black-box testing approach that generates failure inducing inputs by operating in the phoneme-level latent space of a text- to-speech model. Instead of perturbing waveforms directly, the approach interpolates latent representations to induce transcription errors while remai"},"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":"2607.09833","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-10T14:04:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f56ad76eb351c6314775ee73e508cabcd39e52e200568c79f1c267f605801722","abstract_canon_sha256":"8e094c622915b557d7930e4718ca8e62afa86610d669beb53d0df9591695277c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:38.335994Z","signature_b64":"do5ttghvYHFI/bbPkxkI+aAkXa9J6CvMrd00rLLuX1dGFzX7W7oO80BpzeUF80WuwK5gkU/QrmbBWUs9ROxADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26dda0b045bfb02001023c206ea99f75b8a4b16074e5936ac1a736092c84da83","last_reissued_at":"2026-07-14T00:18:38.334887Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:38.334887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Testing of Automated Speech Recognition Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Andrea Stocco, Oliver Wei{\\ss}l, Yanis Xabier Wilbrand Pe\\~na","submitted_at":"2026-07-10T14:04:28Z","abstract_excerpt":"Automatic speech recognition (ASR) systems have achieved high accuracy with transformer-based models, enabling deployment in critical applications. However, they remain vulnerable to adversarial manipulation, particularly in black-box settings where attacks must preserve perceptual naturalness. This work introduces GATAS, a black-box testing approach that generates failure inducing inputs by operating in the phoneme-level latent space of a text- to-speech model. Instead of perturbing waveforms directly, the approach interpolates latent representations to induce transcription errors while remai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09833","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/2607.09833/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":"2607.09833","created_at":"2026-07-14T00:18:38.335386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09833v1","created_at":"2026-07-14T00:18:38.335386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09833","created_at":"2026-07-14T00:18:38.335386+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3O2BMCFX6YC","created_at":"2026-07-14T00:18:38.335386+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3O2BMCFX6YCAAIC","created_at":"2026-07-14T00:18:38.335386+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3O2BMCF","created_at":"2026-07-14T00:18:38.335386+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/E3O2BMCFX6YCAAICHQQG5KM7OW","json":"https://pith.science/pith/E3O2BMCFX6YCAAICHQQG5KM7OW.json","graph_json":"https://pith.science/api/pith-number/E3O2BMCFX6YCAAICHQQG5KM7OW/graph.json","events_json":"https://pith.science/api/pith-number/E3O2BMCFX6YCAAICHQQG5KM7OW/events.json","paper":"https://pith.science/paper/E3O2BMCF"},"agent_actions":{"view_html":"https://pith.science/pith/E3O2BMCFX6YCAAICHQQG5KM7OW","download_json":"https://pith.science/pith/E3O2BMCFX6YCAAICHQQG5KM7OW.json","view_paper":"https://pith.science/paper/E3O2BMCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09833&json=true","fetch_graph":"https://pith.science/api/pith-number/E3O2BMCFX6YCAAICHQQG5KM7OW/graph.json","fetch_events":"https://pith.science/api/pith-number/E3O2BMCFX6YCAAICHQQG5KM7OW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3O2BMCFX6YCAAICHQQG5KM7OW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3O2BMCFX6YCAAICHQQG5KM7OW/action/storage_attestation","attest_author":"https://pith.science/pith/E3O2BMCFX6YCAAICHQQG5KM7OW/action/author_attestation","sign_citation":"https://pith.science/pith/E3O2BMCFX6YCAAICHQQG5KM7OW/action/citation_signature","submit_replication":"https://pith.science/pith/E3O2BMCFX6YCAAICHQQG5KM7OW/action/replication_record"}},"created_at":"2026-07-14T00:18:38.335386+00:00","updated_at":"2026-07-14T00:18:38.335386+00:00"}