{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WMSVROJXVBE67GUOABYY2JO2JL","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":"23e9b1c4d1a9cc4f4f7451824e07f6cff0eff71f43de6d4c9344b3cfaa450bde","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-20T10:14:52Z","title_canon_sha256":"2f77937a9f22ffa591add05861fc4b946a2572ccb65edda58092af13f143a3fa"},"schema_version":"1.0","source":{"id":"2501.11378","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11378","created_at":"2026-07-05T10:32:38Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11378v1","created_at":"2026-07-05T10:32:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11378","created_at":"2026-07-05T10:32:38Z"},{"alias_kind":"pith_short_12","alias_value":"WMSVROJXVBE6","created_at":"2026-07-05T10:32:38Z"},{"alias_kind":"pith_short_16","alias_value":"WMSVROJXVBE67GUO","created_at":"2026-07-05T10:32:38Z"},{"alias_kind":"pith_short_8","alias_value":"WMSVROJX","created_at":"2026-07-05T10:32:38Z"}],"graph_snapshots":[{"event_id":"sha256:1a823096c4822f47e893ab5d00e669f07cdfa478bb0d71a9e817d8923b907011","target":"graph","created_at":"2026-07-05T10:32:38Z","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/2501.11378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hallucinations of deep neural models are amongst key challenges in automatic speech recognition (ASR). In this paper, we investigate hallucinations of the Whisper ASR model induced by non-speech audio segments present during inference. By inducting hallucinations with various types of sounds, we show that there exists a set of hallucinations that appear frequently. We then study hallucinations caused by the augmentation of speech with such sounds. Finally, we describe the creation of a bag of hallucinations (BoH) that allows to remove the effect of hallucinations through the post-processing of","authors_text":"Jan Jasi\\'nski, Julitta Bartolewska, Konrad Kowalczyk, Marcin Witkowski, Mateusz Bara\\'nski, Stanis{\\l}aw Kacprzak","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-20T10:14:52Z","title":"Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11378","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:bd9dcb3ffe329aaca273da993b36df904c86a6b446d7264c5d30a219a79f7f05","target":"record","created_at":"2026-07-05T10:32:38Z","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":"23e9b1c4d1a9cc4f4f7451824e07f6cff0eff71f43de6d4c9344b3cfaa450bde","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-20T10:14:52Z","title_canon_sha256":"2f77937a9f22ffa591add05861fc4b946a2572ccb65edda58092af13f143a3fa"},"schema_version":"1.0","source":{"id":"2501.11378","kind":"arxiv","version":1}},"canonical_sha256":"b32558b937a849ef9a8e00718d25da4acbaa0a49239170dfb0b243e9cda038cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b32558b937a849ef9a8e00718d25da4acbaa0a49239170dfb0b243e9cda038cd","first_computed_at":"2026-07-05T10:32:38.566300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:38.566300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pbIbIN6MCbrYbxLjBaSa5S+38aebXkZ5APaWkg2Fo//kNz5TFftcleeZPnqmC/LvxaSvJXlQN+yjCiYIRNNuAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:38.567423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11378","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd9dcb3ffe329aaca273da993b36df904c86a6b446d7264c5d30a219a79f7f05","sha256:1a823096c4822f47e893ab5d00e669f07cdfa478bb0d71a9e817d8923b907011"],"state_sha256":"15d3863c711efc319da341fb3810e68385a0890a3769124e1861300ae582cae1"}