{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:O76VXINKKSHTSP5GNR4DRRWEOT","short_pith_number":"pith:O76VXINK","schema_version":"1.0","canonical_sha256":"77fd5ba1aa548f393fa66c7838c6c474efb80fbf3ac4d1de115d9e3985f72082","source":{"kind":"arxiv","id":"2203.15135","version":2},"attestation_state":"computed","paper":{"title":"Filler Word Detection and Classification: A Dataset and Benchmark","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ge Zhu, Juan-Pablo Caceres, Justin Salamon","submitted_at":"2022-03-28T22:53:54Z","abstract_excerpt":"Filler words such as `uh' or `um' are sounds or words people use to signal they are pausing to think. Finding and removing filler words from recordings is a common and tedious task in media editing. Automatically detecting and classifying filler words could greatly aid in this task, but few studies have been published on this problem to date. A key reason is the absence of a dataset with annotated filler words for model training and evaluation. In this work, we present a novel speech dataset, PodcastFillers, with 35K annotated filler words and 50K annotations of other sounds that commonly occu"},"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":"2203.15135","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-28T22:53:54Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9cabac2aa51ff792b9cfc7e2c8be4278c2616d8d2582bd9c4f553deeb0008229","abstract_canon_sha256":"acc4fe6005da3d0e4aa7ea2cbca6a9aa4064d85444bb988b072ca168e070fe0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:48.169983Z","signature_b64":"NWjdhqsACtwn1dIX2+q7mHrI+lVvOa/HUmRRy0T4jD7dbcPDIW6UnrJ3LbyjL2IlYhnoi38XTHTo9k2GFZiVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77fd5ba1aa548f393fa66c7838c6c474efb80fbf3ac4d1de115d9e3985f72082","last_reissued_at":"2026-07-05T04:36:48.169478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:48.169478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Filler Word Detection and Classification: A Dataset and Benchmark","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ge Zhu, Juan-Pablo Caceres, Justin Salamon","submitted_at":"2022-03-28T22:53:54Z","abstract_excerpt":"Filler words such as `uh' or `um' are sounds or words people use to signal they are pausing to think. Finding and removing filler words from recordings is a common and tedious task in media editing. Automatically detecting and classifying filler words could greatly aid in this task, but few studies have been published on this problem to date. A key reason is the absence of a dataset with annotated filler words for model training and evaluation. In this work, we present a novel speech dataset, PodcastFillers, with 35K annotated filler words and 50K annotations of other sounds that commonly occu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15135","kind":"arxiv","version":2},"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/2203.15135/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":"2203.15135","created_at":"2026-07-05T04:36:48.169538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15135v2","created_at":"2026-07-05T04:36:48.169538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15135","created_at":"2026-07-05T04:36:48.169538+00:00"},{"alias_kind":"pith_short_12","alias_value":"O76VXINKKSHT","created_at":"2026-07-05T04:36:48.169538+00:00"},{"alias_kind":"pith_short_16","alias_value":"O76VXINKKSHTSP5G","created_at":"2026-07-05T04:36:48.169538+00:00"},{"alias_kind":"pith_short_8","alias_value":"O76VXINK","created_at":"2026-07-05T04:36:48.169538+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/O76VXINKKSHTSP5GNR4DRRWEOT","json":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT.json","graph_json":"https://pith.science/api/pith-number/O76VXINKKSHTSP5GNR4DRRWEOT/graph.json","events_json":"https://pith.science/api/pith-number/O76VXINKKSHTSP5GNR4DRRWEOT/events.json","paper":"https://pith.science/paper/O76VXINK"},"agent_actions":{"view_html":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT","download_json":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT.json","view_paper":"https://pith.science/paper/O76VXINK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15135&json=true","fetch_graph":"https://pith.science/api/pith-number/O76VXINKKSHTSP5GNR4DRRWEOT/graph.json","fetch_events":"https://pith.science/api/pith-number/O76VXINKKSHTSP5GNR4DRRWEOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT/action/storage_attestation","attest_author":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT/action/author_attestation","sign_citation":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT/action/citation_signature","submit_replication":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT/action/replication_record"}},"created_at":"2026-07-05T04:36:48.169538+00:00","updated_at":"2026-07-05T04:36:48.169538+00:00"}