{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:YZKW5B7US7F5XGYWZHBPLC7U3N","short_pith_number":"pith:YZKW5B7U","canonical_record":{"source":{"id":"1709.03759","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-09-12T09:27:12Z","cross_cats_sorted":[],"title_canon_sha256":"f19425e350cecc49472e7ffc5cebb0d70f5a505a974da76576714250d21395b8","abstract_canon_sha256":"7c8beb58e2f573e3317401326f7b14fa99ec15d8d27c8a1f4ff6a6835e597078"},"schema_version":"1.0"},"canonical_sha256":"c6556e87f497cbdb9b16c9c2f58bf4db6aa8a804a5d958d3c29966e48e8e563c","source":{"kind":"arxiv","id":"1709.03759","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.03759","created_at":"2026-05-18T00:35:29Z"},{"alias_kind":"arxiv_version","alias_value":"1709.03759v1","created_at":"2026-05-18T00:35:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03759","created_at":"2026-05-18T00:35:29Z"},{"alias_kind":"pith_short_12","alias_value":"YZKW5B7US7F5","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"YZKW5B7US7F5XGYW","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"YZKW5B7U","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:YZKW5B7US7F5XGYWZHBPLC7U3N","target":"record","payload":{"canonical_record":{"source":{"id":"1709.03759","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-09-12T09:27:12Z","cross_cats_sorted":[],"title_canon_sha256":"f19425e350cecc49472e7ffc5cebb0d70f5a505a974da76576714250d21395b8","abstract_canon_sha256":"7c8beb58e2f573e3317401326f7b14fa99ec15d8d27c8a1f4ff6a6835e597078"},"schema_version":"1.0"},"canonical_sha256":"c6556e87f497cbdb9b16c9c2f58bf4db6aa8a804a5d958d3c29966e48e8e563c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:29.576201Z","signature_b64":"6CHecxqBtnEJu7nqcyQ+THAJh3QUIx4BKasOhUiKxJl2ytaERGewFzyMTGu2ziNQr5NEXqnLbVz4KkQXqQ3CCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6556e87f497cbdb9b16c9c2f58bf4db6aa8a804a5d958d3c29966e48e8e563c","last_reissued_at":"2026-05-18T00:35:29.575535Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:29.575535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.03759","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":"2026-05-18T00:35:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2GehYjOc54RgdvY61UGCb+B/OU/bVp2PTp15QBFBr4KiUBYxtjhA9vU8lYnCPvEhB46Sw4fLM4iqp36isijOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:40:31.834876Z"},"content_sha256":"3b722548b733f313d7da5cd7e2c736561dd6feae68b51f2bd80d0f9c69d1843a","schema_version":"1.0","event_id":"sha256:3b722548b733f313d7da5cd7e2c736561dd6feae68b51f2bd80d0f9c69d1843a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:YZKW5B7US7F5XGYWZHBPLC7U3N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Models of Spoken Dutch","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hugo Van hamme, Joris Pelemans, Lyan Verwimp, Marieke Lycke, Patrick Wambacq","submitted_at":"2017-09-12T09:27:12Z","abstract_excerpt":"In Flanders, all TV shows are subtitled. However, the process of subtitling is a very time-consuming one and can be sped up by providing the output of a speech recognizer run on the audio of the TV show, prior to the subtitling. Naturally, this speech recognition will perform much better if the employed language model is adapted to the register and the topic of the program. We present several language models trained on subtitles of television shows provided by the Flemish public-service broadcaster VRT. This data was gathered in the context of the project STON which has as purpose to facilitat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03759","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":"2026-05-18T00:35:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oTLrLvzRPJMKPGfPUvC7cURalTogBmqu9D00Qfd5vbAI5br55yN964ElqdLqdkga9Q2pe1d48KAHqERk0YPNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:40:31.835321Z"},"content_sha256":"b84eba6a7c799213cf7bfd1c7b3c2315fd68e134036b06dd9e9f065420aa941d","schema_version":"1.0","event_id":"sha256:b84eba6a7c799213cf7bfd1c7b3c2315fd68e134036b06dd9e9f065420aa941d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZKW5B7US7F5XGYWZHBPLC7U3N/bundle.json","state_url":"https://pith.science/pith/YZKW5B7US7F5XGYWZHBPLC7U3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZKW5B7US7F5XGYWZHBPLC7U3N/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":"2026-08-05T10:40:31Z","links":{"resolver":"https://pith.science/pith/YZKW5B7US7F5XGYWZHBPLC7U3N","bundle":"https://pith.science/pith/YZKW5B7US7F5XGYWZHBPLC7U3N/bundle.json","state":"https://pith.science/pith/YZKW5B7US7F5XGYWZHBPLC7U3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZKW5B7US7F5XGYWZHBPLC7U3N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YZKW5B7US7F5XGYWZHBPLC7U3N","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":"7c8beb58e2f573e3317401326f7b14fa99ec15d8d27c8a1f4ff6a6835e597078","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-09-12T09:27:12Z","title_canon_sha256":"f19425e350cecc49472e7ffc5cebb0d70f5a505a974da76576714250d21395b8"},"schema_version":"1.0","source":{"id":"1709.03759","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.03759","created_at":"2026-05-18T00:35:29Z"},{"alias_kind":"arxiv_version","alias_value":"1709.03759v1","created_at":"2026-05-18T00:35:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03759","created_at":"2026-05-18T00:35:29Z"},{"alias_kind":"pith_short_12","alias_value":"YZKW5B7US7F5","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"YZKW5B7US7F5XGYW","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"YZKW5B7U","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:b84eba6a7c799213cf7bfd1c7b3c2315fd68e134036b06dd9e9f065420aa941d","target":"graph","created_at":"2026-05-18T00:35:29Z","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 Flanders, all TV shows are subtitled. However, the process of subtitling is a very time-consuming one and can be sped up by providing the output of a speech recognizer run on the audio of the TV show, prior to the subtitling. Naturally, this speech recognition will perform much better if the employed language model is adapted to the register and the topic of the program. We present several language models trained on subtitles of television shows provided by the Flemish public-service broadcaster VRT. This data was gathered in the context of the project STON which has as purpose to facilitat","authors_text":"Hugo Van hamme, Joris Pelemans, Lyan Verwimp, Marieke Lycke, Patrick Wambacq","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-09-12T09:27:12Z","title":"Language Models of Spoken Dutch"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03759","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":"sha256:3b722548b733f313d7da5cd7e2c736561dd6feae68b51f2bd80d0f9c69d1843a","target":"record","created_at":"2026-05-18T00:35:29Z","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":"7c8beb58e2f573e3317401326f7b14fa99ec15d8d27c8a1f4ff6a6835e597078","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-09-12T09:27:12Z","title_canon_sha256":"f19425e350cecc49472e7ffc5cebb0d70f5a505a974da76576714250d21395b8"},"schema_version":"1.0","source":{"id":"1709.03759","kind":"arxiv","version":1}},"canonical_sha256":"c6556e87f497cbdb9b16c9c2f58bf4db6aa8a804a5d958d3c29966e48e8e563c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6556e87f497cbdb9b16c9c2f58bf4db6aa8a804a5d958d3c29966e48e8e563c","first_computed_at":"2026-05-18T00:35:29.575535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:29.575535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6CHecxqBtnEJu7nqcyQ+THAJh3QUIx4BKasOhUiKxJl2ytaERGewFzyMTGu2ziNQr5NEXqnLbVz4KkQXqQ3CCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:29.576201Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.03759","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b722548b733f313d7da5cd7e2c736561dd6feae68b51f2bd80d0f9c69d1843a","sha256:b84eba6a7c799213cf7bfd1c7b3c2315fd68e134036b06dd9e9f065420aa941d"],"state_sha256":"341624f76d46761cabe771f0fde21948dd6924703b7059ab6fcff9b6d7f68e8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+MoptfO/gn9gbXOf6ciE/7YBaMQb9jC+f/6pYF12rbmPbVIBpmmtR3VC+4BY3RRbuYfg3KVgd0aM7SLNO61Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:40:31.838398Z","bundle_sha256":"e2410238cafb23b3ba9788999ab3ad6b48c38fcb543363e13984aacc3fec0516"}}