{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5AZ7XQK4EGWZI2ESSE5KDF3MWC","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":"ce1101ea381e634b6edd72cf5e1f285cbafdd50472b13e6625deec8ea40f83b7","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T15:35:32Z","title_canon_sha256":"9b40e4f53377f7c48b579fdc5e43ed3570a9765e282812d07a491654a8bb574b"},"schema_version":"1.0","source":{"id":"2409.13582","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13582","created_at":"2026-07-05T09:09:38Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13582v1","created_at":"2026-07-05T09:09:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13582","created_at":"2026-07-05T09:09:38Z"},{"alias_kind":"pith_short_12","alias_value":"5AZ7XQK4EGWZ","created_at":"2026-07-05T09:09:38Z"},{"alias_kind":"pith_short_16","alias_value":"5AZ7XQK4EGWZI2ES","created_at":"2026-07-05T09:09:38Z"},{"alias_kind":"pith_short_8","alias_value":"5AZ7XQK4","created_at":"2026-07-05T09:09:38Z"}],"graph_snapshots":[{"event_id":"sha256:773611ec43eb647b4d40583a36cd80e1bfbdf504f6a0b3780ac43e3630a022cb","target":"graph","created_at":"2026-07-05T09:09:38Z","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/2409.13582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech dysfluency modeling is a task to detect dysfluencies in speech, such as repetition, block, insertion, replacement, and deletion. Most recent advancements treat this problem as a time-based object detection problem. In this work, we revisit this problem from a new perspective: tokenizing dysfluencies and modeling the detection problem as a token-based automatic speech recognition (ASR) problem. We propose rule-based speech and text dysfluency simulators and develop VCTK-token, and then develop a Whisper-like seq2seq architecture to build a new benchmark with decent performance. We also s","authors_text":"Brittany Morin, Cheol Jun Cho, David Baquirin, Gopala Anumanchipalli, Jet Vonk, Jiachen Lian, Jingwen Liu, Jinming Zhang, Maria Luisa Gorno Tempini, Xuanru Zhou, Zachary Miller, Zoe Ezzes, Zongli Ye","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T15:35:32Z","title":"Time and Tokens: Benchmarking End-to-End Speech Dysfluency Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13582","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:d203bd5a8308152a33f7c1f0d289053a62bc8163480a9d8b2d6a64e0ca1f2697","target":"record","created_at":"2026-07-05T09:09:38Z","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":"ce1101ea381e634b6edd72cf5e1f285cbafdd50472b13e6625deec8ea40f83b7","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T15:35:32Z","title_canon_sha256":"9b40e4f53377f7c48b579fdc5e43ed3570a9765e282812d07a491654a8bb574b"},"schema_version":"1.0","source":{"id":"2409.13582","kind":"arxiv","version":1}},"canonical_sha256":"e833fbc15c21ad946892913aa1976cb08d07aacc2599601276a69e7235f73c7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e833fbc15c21ad946892913aa1976cb08d07aacc2599601276a69e7235f73c7c","first_computed_at":"2026-07-05T09:09:38.093867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:38.093867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6c3SktRHbShMWaxqd8kGmkJNFl2KuNeyVBGHtMzFbsCFkZqI2Pgi9DaAFW8/HVaH/CNMR7xyO9A3b2HhyZ0aAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:38.094423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13582","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d203bd5a8308152a33f7c1f0d289053a62bc8163480a9d8b2d6a64e0ca1f2697","sha256:773611ec43eb647b4d40583a36cd80e1bfbdf504f6a0b3780ac43e3630a022cb"],"state_sha256":"4059d7a044f3874de40697bbe5690cbd511dc213b94f8fe31de986580513e9c0"}