{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YZGYRX6DPKZLGFEJKWXWE46P3D","short_pith_number":"pith:YZGYRX6D","canonical_record":{"source":{"id":"2507.04554","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-06T22:11:22Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"476004c4236e82ed4e880e3a5130c53d27ec707ad3bdc170de0eff43965fd571","abstract_canon_sha256":"d030b072936782bf103fdf31379e722c5793e69a587afc69e8961f82d058163d"},"schema_version":"1.0"},"canonical_sha256":"c64d88dfc37ab2b3148955af6273cfd8ec28f8c3b24aa59367581de1b1efadaa","source":{"kind":"arxiv","id":"2507.04554","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04554","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04554v2","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04554","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_12","alias_value":"YZGYRX6DPKZL","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_16","alias_value":"YZGYRX6DPKZLGFEJ","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_8","alias_value":"YZGYRX6D","created_at":"2026-07-05T11:33:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YZGYRX6DPKZLGFEJKWXWE46P3D","target":"record","payload":{"canonical_record":{"source":{"id":"2507.04554","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-06T22:11:22Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"476004c4236e82ed4e880e3a5130c53d27ec707ad3bdc170de0eff43965fd571","abstract_canon_sha256":"d030b072936782bf103fdf31379e722c5793e69a587afc69e8961f82d058163d"},"schema_version":"1.0"},"canonical_sha256":"c64d88dfc37ab2b3148955af6273cfd8ec28f8c3b24aa59367581de1b1efadaa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:26.663208Z","signature_b64":"i/T3lrXmZcfW/Mm93QW7TTsuZZU9krPk2rbMXwxrQvtMAQaLaufhAsMHNGzFt/8VELGS6KVl8Zj1JJQEjsdMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c64d88dfc37ab2b3148955af6273cfd8ec28f8c3b24aa59367581de1b1efadaa","last_reissued_at":"2026-07-05T11:33:26.662709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:26.662709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.04554","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":"2026-07-05T11:33:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R8UGADBN0z5oz7YGdQUmHjEnHFQ7v54Iix/ZZcXN0U5v6mRdZ2K0OPbEJTOSbVgM7ZMaQj6UD5uwtuc2JOdjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:39:57.222012Z"},"content_sha256":"ca66f62f30a196b163b0953159a9744188b106d378c274e0f29aa8052f07662a","schema_version":"1.0","event_id":"sha256:ca66f62f30a196b163b0953159a9744188b106d378c274e0f29aa8052f07662a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YZGYRX6DPKZLGFEJKWXWE46P3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-supervised learning of speech representations with Dutch archival data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"David A. van Leeuwen, Nik Vaessen, Roeland Ordelman","submitted_at":"2025-07-06T22:11:22Z","abstract_excerpt":"This paper explores the use of Dutch archival television broadcast data for self-supervised learning of speech foundation models, specifically wav2vec 2.0. We first study data quality assumptions for pre-training, and show how music, noise and speaker overlap affect SSL convergence and downstream fine-tuning performance. Secondly, we explore effectively pre-processing strategies to convert the noisy broadcast dataset into a qualitative dataset for pre-training, by using Whisper and WhisperX. Thirdly, we compare mono-lingual and multi-lingual pre-training with equivalent amounts of data, and sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04554","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/2507.04554/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":"2026-07-05T11:33:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OFHgjie1mcGay43O5xfGHdaTTWzTESxf8bk7oJNZgLJh7IAKIgVnl0+bIyfFLs74cr/gJTNaIkROScFk2K44CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:39:57.222674Z"},"content_sha256":"553d2f87641a982cf9632ba17a54dc874ee9c6d01edf475c9792e532a44973f0","schema_version":"1.0","event_id":"sha256:553d2f87641a982cf9632ba17a54dc874ee9c6d01edf475c9792e532a44973f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZGYRX6DPKZLGFEJKWXWE46P3D/bundle.json","state_url":"https://pith.science/pith/YZGYRX6DPKZLGFEJKWXWE46P3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZGYRX6DPKZLGFEJKWXWE46P3D/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":"2026-07-07T06:39:57Z","links":{"resolver":"https://pith.science/pith/YZGYRX6DPKZLGFEJKWXWE46P3D","bundle":"https://pith.science/pith/YZGYRX6DPKZLGFEJKWXWE46P3D/bundle.json","state":"https://pith.science/pith/YZGYRX6DPKZLGFEJKWXWE46P3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZGYRX6DPKZLGFEJKWXWE46P3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YZGYRX6DPKZLGFEJKWXWE46P3D","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":"d030b072936782bf103fdf31379e722c5793e69a587afc69e8961f82d058163d","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-06T22:11:22Z","title_canon_sha256":"476004c4236e82ed4e880e3a5130c53d27ec707ad3bdc170de0eff43965fd571"},"schema_version":"1.0","source":{"id":"2507.04554","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04554","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04554v2","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04554","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_12","alias_value":"YZGYRX6DPKZL","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_16","alias_value":"YZGYRX6DPKZLGFEJ","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_8","alias_value":"YZGYRX6D","created_at":"2026-07-05T11:33:26Z"}],"graph_snapshots":[{"event_id":"sha256:553d2f87641a982cf9632ba17a54dc874ee9c6d01edf475c9792e532a44973f0","target":"graph","created_at":"2026-07-05T11:33:26Z","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/2507.04554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores the use of Dutch archival television broadcast data for self-supervised learning of speech foundation models, specifically wav2vec 2.0. We first study data quality assumptions for pre-training, and show how music, noise and speaker overlap affect SSL convergence and downstream fine-tuning performance. Secondly, we explore effectively pre-processing strategies to convert the noisy broadcast dataset into a qualitative dataset for pre-training, by using Whisper and WhisperX. Thirdly, we compare mono-lingual and multi-lingual pre-training with equivalent amounts of data, and sh","authors_text":"David A. van Leeuwen, Nik Vaessen, Roeland Ordelman","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-06T22:11:22Z","title":"Self-supervised learning of speech representations with Dutch archival data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04554","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:ca66f62f30a196b163b0953159a9744188b106d378c274e0f29aa8052f07662a","target":"record","created_at":"2026-07-05T11:33:26Z","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":"d030b072936782bf103fdf31379e722c5793e69a587afc69e8961f82d058163d","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-06T22:11:22Z","title_canon_sha256":"476004c4236e82ed4e880e3a5130c53d27ec707ad3bdc170de0eff43965fd571"},"schema_version":"1.0","source":{"id":"2507.04554","kind":"arxiv","version":2}},"canonical_sha256":"c64d88dfc37ab2b3148955af6273cfd8ec28f8c3b24aa59367581de1b1efadaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c64d88dfc37ab2b3148955af6273cfd8ec28f8c3b24aa59367581de1b1efadaa","first_computed_at":"2026-07-05T11:33:26.662709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:26.662709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i/T3lrXmZcfW/Mm93QW7TTsuZZU9krPk2rbMXwxrQvtMAQaLaufhAsMHNGzFt/8VELGS6KVl8Zj1JJQEjsdMAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:26.663208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04554","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca66f62f30a196b163b0953159a9744188b106d378c274e0f29aa8052f07662a","sha256:553d2f87641a982cf9632ba17a54dc874ee9c6d01edf475c9792e532a44973f0"],"state_sha256":"37cbdc418e944536584320ad9c75f911a2a89da071be88464133743ebec6e264"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qTT5MXStja9WpyYKyAxAwZT0DbMqGLxTeev22re1Ixeu6kshufAVdJiNVRi22WpGjp8sp/zj4yK/SiRAYbSjDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:39:57.226017Z","bundle_sha256":"12903f16088d9ee67586821b8b25e48d43a60198e41b5a565c974cf65c8cf7a7"}}