{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SWFU5QAXZ35SI47HVWYOHLQX4I","short_pith_number":"pith:SWFU5QAX","canonical_record":{"source":{"id":"1903.00216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T09:14:50Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"539ae64612d90bdfb350d9084e2177d92152e1e15139dc6a0ff5b21738e5c047","abstract_canon_sha256":"ccfc523a0857220cf5237d7dd3d3fd369a7b483c094142a4650a4c8e628860f7"},"schema_version":"1.0"},"canonical_sha256":"958b4ec017cefb2473e7adb0e3ae17e212a46d0c06396f9d4e30cbcbedc9cf7c","source":{"kind":"arxiv","id":"1903.00216","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00216","created_at":"2026-05-17T23:52:20Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00216v1","created_at":"2026-05-17T23:52:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00216","created_at":"2026-05-17T23:52:20Z"},{"alias_kind":"pith_short_12","alias_value":"SWFU5QAXZ35S","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SWFU5QAXZ35SI47H","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SWFU5QAX","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SWFU5QAXZ35SI47HVWYOHLQX4I","target":"record","payload":{"canonical_record":{"source":{"id":"1903.00216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T09:14:50Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"539ae64612d90bdfb350d9084e2177d92152e1e15139dc6a0ff5b21738e5c047","abstract_canon_sha256":"ccfc523a0857220cf5237d7dd3d3fd369a7b483c094142a4650a4c8e628860f7"},"schema_version":"1.0"},"canonical_sha256":"958b4ec017cefb2473e7adb0e3ae17e212a46d0c06396f9d4e30cbcbedc9cf7c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:20.502590Z","signature_b64":"VOc9YBlYZ/9hwbgZVy5AzeSlXliVLwr2tcpkL3Vw/9pWgRBc5GHwzc8dzCzqV1X2uougSLeCIOZFRQArVx5MAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"958b4ec017cefb2473e7adb0e3ae17e212a46d0c06396f9d4e30cbcbedc9cf7c","last_reissued_at":"2026-05-17T23:52:20.501891Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:20.501891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.00216","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JSFhANVOH+9Ib8OuT53QB82CEiSltbuiyOFoIYgZONkUnJB9SkSHDV1F0fS0iMXN4K6r7nvoYaU9l5sCUVUuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:25:37.045080Z"},"content_sha256":"477fe2378813cf5135bb52a33b23aa009201c953e91c54158c4d5406e7f8cf25","schema_version":"1.0","event_id":"sha256:477fe2378813cf5135bb52a33b23aa009201c953e91c54158c4d5406e7f8cf25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SWFU5QAXZ35SI47HVWYOHLQX4I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KT-Speech-Crawler: Automatic Dataset Construction for Speech Recognition from YouTube Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Cornelius Weber, Egor Lakomkin, Stefan Wermter, Sven Magg","submitted_at":"2019-03-01T09:14:50Z","abstract_excerpt":"In this paper, we describe KT-Speech-Crawler: an approach for automatic dataset construction for speech recognition by crawling YouTube videos. We outline several filtering and post-processing steps, which extract samples that can be used for training end-to-end neural speech recognition systems. In our experiments, we demonstrate that a single-core version of the crawler can obtain around 150 hours of transcribed speech within a day, containing an estimated 3.5% word error rate in the transcriptions. Automatically collected samples contain reading and spontaneous speech recorded in various co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00216","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":""},"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":"2026-05-17T23:52:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pd+XePCVrKbtGb6Be1nuM3netXXcrBdGj0jTKudrPHiXwTGb04RmhLsYauUd/wpyk+vdApthXJN0qQeRd1JwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:25:37.045459Z"},"content_sha256":"6c57592c2a99d5336a0a9faba39c6ee1361167cf6a1644d14062b7de5eb6d92d","schema_version":"1.0","event_id":"sha256:6c57592c2a99d5336a0a9faba39c6ee1361167cf6a1644d14062b7de5eb6d92d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I/bundle.json","state_url":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SWFU5QAXZ35SI47HVWYOHLQX4I/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":"2026-05-30T02:25:37Z","links":{"resolver":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I","bundle":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I/bundle.json","state":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SWFU5QAXZ35SI47HVWYOHLQX4I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SWFU5QAXZ35SI47HVWYOHLQX4I","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":"ccfc523a0857220cf5237d7dd3d3fd369a7b483c094142a4650a4c8e628860f7","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T09:14:50Z","title_canon_sha256":"539ae64612d90bdfb350d9084e2177d92152e1e15139dc6a0ff5b21738e5c047"},"schema_version":"1.0","source":{"id":"1903.00216","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00216","created_at":"2026-05-17T23:52:20Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00216v1","created_at":"2026-05-17T23:52:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00216","created_at":"2026-05-17T23:52:20Z"},{"alias_kind":"pith_short_12","alias_value":"SWFU5QAXZ35S","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SWFU5QAXZ35SI47H","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SWFU5QAX","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:6c57592c2a99d5336a0a9faba39c6ee1361167cf6a1644d14062b7de5eb6d92d","target":"graph","created_at":"2026-05-17T23:52:20Z","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"},"paper":{"abstract_excerpt":"In this paper, we describe KT-Speech-Crawler: an approach for automatic dataset construction for speech recognition by crawling YouTube videos. We outline several filtering and post-processing steps, which extract samples that can be used for training end-to-end neural speech recognition systems. In our experiments, we demonstrate that a single-core version of the crawler can obtain around 150 hours of transcribed speech within a day, containing an estimated 3.5% word error rate in the transcriptions. Automatically collected samples contain reading and spontaneous speech recorded in various co","authors_text":"Cornelius Weber, Egor Lakomkin, Stefan Wermter, Sven Magg","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T09:14:50Z","title":"KT-Speech-Crawler: Automatic Dataset Construction for Speech Recognition from YouTube Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00216","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":"sha256:477fe2378813cf5135bb52a33b23aa009201c953e91c54158c4d5406e7f8cf25","target":"record","created_at":"2026-05-17T23:52:20Z","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":"ccfc523a0857220cf5237d7dd3d3fd369a7b483c094142a4650a4c8e628860f7","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T09:14:50Z","title_canon_sha256":"539ae64612d90bdfb350d9084e2177d92152e1e15139dc6a0ff5b21738e5c047"},"schema_version":"1.0","source":{"id":"1903.00216","kind":"arxiv","version":1}},"canonical_sha256":"958b4ec017cefb2473e7adb0e3ae17e212a46d0c06396f9d4e30cbcbedc9cf7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"958b4ec017cefb2473e7adb0e3ae17e212a46d0c06396f9d4e30cbcbedc9cf7c","first_computed_at":"2026-05-17T23:52:20.501891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:20.501891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VOc9YBlYZ/9hwbgZVy5AzeSlXliVLwr2tcpkL3Vw/9pWgRBc5GHwzc8dzCzqV1X2uougSLeCIOZFRQArVx5MAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:20.502590Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.00216","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:477fe2378813cf5135bb52a33b23aa009201c953e91c54158c4d5406e7f8cf25","sha256:6c57592c2a99d5336a0a9faba39c6ee1361167cf6a1644d14062b7de5eb6d92d"],"state_sha256":"67a430cabd85161816a206642a03bfbee25466cd0be3842d570a5c05d5c47986"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZcLBnkX7QU4X+uJm30a/r9HhuKc1BBmBodkmbxWGaSc+yKvGeT9R0Fycdknh+CAsJB6XGdY2KuB2ILsX6JQKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T02:25:37.047589Z","bundle_sha256":"0580726172a51431e32736afa653bfe072f60f8bfdaaba7ab56350b4dc92973e"}}