{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VMIUZSEHRYHBQEKFSWMBGKX26B","short_pith_number":"pith:VMIUZSEH","schema_version":"1.0","canonical_sha256":"ab114cc8878e0e1811459598132afaf07a65bf2c879ae3666108508ce70bf8bc","source":{"kind":"arxiv","id":"2606.20338","version":1},"attestation_state":"computed","paper":{"title":"Stuttering Classification and Segmentation with Attention-Based Multiple Instance Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hrvoje D\\v{z}apo, Petar Su\\v{s}ac, Sebastian P. Bayerl","submitted_at":"2026-06-18T15:08:55Z","abstract_excerpt":"Stuttering detection and classification using deep learning methods has the potential to improve the process of stuttering severity assessment. Most stuttering classification datasets provide clip-level labels, making them unsuitable for fine-grained frame-level classification needed to determine the duration of individual stuttering dysfluencies. To overcome this challenge, we present a multiple instance neural network architecture based on fine-tuned wav2vec 2.0, WavLM and Whisper encoders. We apply instance- and embedding-based multiple instance learning approaches to train models on a clip"},"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":"2606.20338","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-18T15:08:55Z","cross_cats_sorted":[],"title_canon_sha256":"d6df24a7ef0d32dac45ebd01c54613248e0af176a2103205fb25e69a104dad3e","abstract_canon_sha256":"9d34a6962c335aa12ec5c79038654b109b6783ee1d7bfd406969100b999f7c3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:09.352865Z","signature_b64":"5kEKYCfvQmtqKR3RBpUGF72W6vKiFut5smbLhCgb1EvYWvlzQ84fva9T1fAlG7j4X4JGhIxvInf2OcKqgkMqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab114cc8878e0e1811459598132afaf07a65bf2c879ae3666108508ce70bf8bc","last_reissued_at":"2026-06-19T16:13:09.352477Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:09.352477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stuttering Classification and Segmentation with Attention-Based Multiple Instance Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hrvoje D\\v{z}apo, Petar Su\\v{s}ac, Sebastian P. Bayerl","submitted_at":"2026-06-18T15:08:55Z","abstract_excerpt":"Stuttering detection and classification using deep learning methods has the potential to improve the process of stuttering severity assessment. Most stuttering classification datasets provide clip-level labels, making them unsuitable for fine-grained frame-level classification needed to determine the duration of individual stuttering dysfluencies. To overcome this challenge, we present a multiple instance neural network architecture based on fine-tuned wav2vec 2.0, WavLM and Whisper encoders. We apply instance- and embedding-based multiple instance learning approaches to train models on a clip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20338","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/2606.20338/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":"2606.20338","created_at":"2026-06-19T16:13:09.352541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20338v1","created_at":"2026-06-19T16:13:09.352541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20338","created_at":"2026-06-19T16:13:09.352541+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMIUZSEHRYHB","created_at":"2026-06-19T16:13:09.352541+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMIUZSEHRYHBQEKF","created_at":"2026-06-19T16:13:09.352541+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMIUZSEH","created_at":"2026-06-19T16:13:09.352541+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/VMIUZSEHRYHBQEKFSWMBGKX26B","json":"https://pith.science/pith/VMIUZSEHRYHBQEKFSWMBGKX26B.json","graph_json":"https://pith.science/api/pith-number/VMIUZSEHRYHBQEKFSWMBGKX26B/graph.json","events_json":"https://pith.science/api/pith-number/VMIUZSEHRYHBQEKFSWMBGKX26B/events.json","paper":"https://pith.science/paper/VMIUZSEH"},"agent_actions":{"view_html":"https://pith.science/pith/VMIUZSEHRYHBQEKFSWMBGKX26B","download_json":"https://pith.science/pith/VMIUZSEHRYHBQEKFSWMBGKX26B.json","view_paper":"https://pith.science/paper/VMIUZSEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20338&json=true","fetch_graph":"https://pith.science/api/pith-number/VMIUZSEHRYHBQEKFSWMBGKX26B/graph.json","fetch_events":"https://pith.science/api/pith-number/VMIUZSEHRYHBQEKFSWMBGKX26B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMIUZSEHRYHBQEKFSWMBGKX26B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMIUZSEHRYHBQEKFSWMBGKX26B/action/storage_attestation","attest_author":"https://pith.science/pith/VMIUZSEHRYHBQEKFSWMBGKX26B/action/author_attestation","sign_citation":"https://pith.science/pith/VMIUZSEHRYHBQEKFSWMBGKX26B/action/citation_signature","submit_replication":"https://pith.science/pith/VMIUZSEHRYHBQEKFSWMBGKX26B/action/replication_record"}},"created_at":"2026-06-19T16:13:09.352541+00:00","updated_at":"2026-06-19T16:13:09.352541+00:00"}