{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:O76VXINKKSHTSP5GNR4DRRWEOT","short_pith_number":"pith:O76VXINK","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"},"canonical_sha256":"77fd5ba1aa548f393fa66c7838c6c474efb80fbf3ac4d1de115d9e3985f72082","source":{"kind":"arxiv","id":"2203.15135","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15135","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15135v2","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15135","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"pith_short_12","alias_value":"O76VXINKKSHT","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"pith_short_16","alias_value":"O76VXINKKSHTSP5G","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"pith_short_8","alias_value":"O76VXINK","created_at":"2026-07-05T04:36:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:O76VXINKKSHTSP5GNR4DRRWEOT","target":"record","payload":{"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"},"canonical_sha256":"77fd5ba1aa548f393fa66c7838c6c474efb80fbf3ac4d1de115d9e3985f72082","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"},"source_kind":"arxiv","source_id":"2203.15135","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:36:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CgyldE7+H66QHuB1oJfULKX3jWRTTALJux/Gi6nfW6RziTPK6lRsv6S3opU9U7O/AoEagkVuU+4dfFB4wsq7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:08:46.580303Z"},"content_sha256":"ca2bb818569b15c52f0981f6b6183b2c122b14b5c3b71bba52665ba1ee4f69d8","schema_version":"1.0","event_id":"sha256:ca2bb818569b15c52f0981f6b6183b2c122b14b5c3b71bba52665ba1ee4f69d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:O76VXINKKSHTSP5GNR4DRRWEOT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:36:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4czdkskCqWJm0ECMPB8k9nEav+zwdQxPVRVzHSR+S5OQpzZ8IdIiWhok3rPvYBHGj8UzOINSQ5+yyw4unUE2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:08:46.580640Z"},"content_sha256":"0259ae70c5701ec9f0692d7214a4339966da6bedcbf303089f0e56ba05535a49","schema_version":"1.0","event_id":"sha256:0259ae70c5701ec9f0692d7214a4339966da6bedcbf303089f0e56ba05535a49"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT/bundle.json","state_url":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O76VXINKKSHTSP5GNR4DRRWEOT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T09:08:46Z","links":{"resolver":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT","bundle":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT/bundle.json","state":"https://pith.science/pith/O76VXINKKSHTSP5GNR4DRRWEOT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O76VXINKKSHTSP5GNR4DRRWEOT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O76VXINKKSHTSP5GNR4DRRWEOT","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":"acc4fe6005da3d0e4aa7ea2cbca6a9aa4064d85444bb988b072ca168e070fe0f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-28T22:53:54Z","title_canon_sha256":"9cabac2aa51ff792b9cfc7e2c8be4278c2616d8d2582bd9c4f553deeb0008229"},"schema_version":"1.0","source":{"id":"2203.15135","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15135","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15135v2","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15135","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"pith_short_12","alias_value":"O76VXINKKSHT","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"pith_short_16","alias_value":"O76VXINKKSHTSP5G","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"pith_short_8","alias_value":"O76VXINK","created_at":"2026-07-05T04:36:48Z"}],"graph_snapshots":[{"event_id":"sha256:0259ae70c5701ec9f0692d7214a4339966da6bedcbf303089f0e56ba05535a49","target":"graph","created_at":"2026-07-05T04:36:48Z","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/2203.15135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ge Zhu, Juan-Pablo Caceres, Justin Salamon","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-28T22:53:54Z","title":"Filler Word Detection and Classification: A Dataset and Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15135","kind":"arxiv","version":2},"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:ca2bb818569b15c52f0981f6b6183b2c122b14b5c3b71bba52665ba1ee4f69d8","target":"record","created_at":"2026-07-05T04:36:48Z","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":"acc4fe6005da3d0e4aa7ea2cbca6a9aa4064d85444bb988b072ca168e070fe0f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-28T22:53:54Z","title_canon_sha256":"9cabac2aa51ff792b9cfc7e2c8be4278c2616d8d2582bd9c4f553deeb0008229"},"schema_version":"1.0","source":{"id":"2203.15135","kind":"arxiv","version":2}},"canonical_sha256":"77fd5ba1aa548f393fa66c7838c6c474efb80fbf3ac4d1de115d9e3985f72082","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77fd5ba1aa548f393fa66c7838c6c474efb80fbf3ac4d1de115d9e3985f72082","first_computed_at":"2026-07-05T04:36:48.169478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:48.169478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NWjdhqsACtwn1dIX2+q7mHrI+lVvOa/HUmRRy0T4jD7dbcPDIW6UnrJ3LbyjL2IlYhnoi38XTHTo9k2GFZiVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:48.169983Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.15135","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca2bb818569b15c52f0981f6b6183b2c122b14b5c3b71bba52665ba1ee4f69d8","sha256:0259ae70c5701ec9f0692d7214a4339966da6bedcbf303089f0e56ba05535a49"],"state_sha256":"6f7a33ffd684571f24953a3dcee698c0eacf1ec0e3bf2966a47cc9cc070cd671"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ryCX+oxlMKCvxQu1bERbqYtlIAZXxBd3bfcaWW9si8fwgpp9IqQEVFi3s2KJfpVBnhwpjRwEUufLntzgxWRyDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:08:46.584335Z","bundle_sha256":"974380a7e9297e638c6d2d258317b6a34950e4b59e6631fd15e181cb8b5ee99b"}}