{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ELUYHBVKU23BEDIOWW7FZ6O4ZE","short_pith_number":"pith:ELUYHBVK","canonical_record":{"source":{"id":"2010.02810","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T15:18:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d2f74f4494b48aec10a19815bbcbda82aba08500cf64eb5c69c62371752ac851","abstract_canon_sha256":"b624c0d2c919972dd78e8d76828cc32e5a94cc9dfcdc16ad9ddddefdd68bbcab"},"schema_version":"1.0"},"canonical_sha256":"22e98386aaa6b6120d0eb5be5cf9dcc9058b68b4ced9e125de6b46a7fa1cf9d8","source":{"kind":"arxiv","id":"2010.02810","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02810","created_at":"2026-07-05T02:47:39Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02810v2","created_at":"2026-07-05T02:47:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02810","created_at":"2026-07-05T02:47:39Z"},{"alias_kind":"pith_short_12","alias_value":"ELUYHBVKU23B","created_at":"2026-07-05T02:47:39Z"},{"alias_kind":"pith_short_16","alias_value":"ELUYHBVKU23BEDIO","created_at":"2026-07-05T02:47:39Z"},{"alias_kind":"pith_short_8","alias_value":"ELUYHBVK","created_at":"2026-07-05T02:47:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ELUYHBVKU23BEDIOWW7FZ6O4ZE","target":"record","payload":{"canonical_record":{"source":{"id":"2010.02810","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T15:18:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d2f74f4494b48aec10a19815bbcbda82aba08500cf64eb5c69c62371752ac851","abstract_canon_sha256":"b624c0d2c919972dd78e8d76828cc32e5a94cc9dfcdc16ad9ddddefdd68bbcab"},"schema_version":"1.0"},"canonical_sha256":"22e98386aaa6b6120d0eb5be5cf9dcc9058b68b4ced9e125de6b46a7fa1cf9d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:39.985842Z","signature_b64":"e0v2jjDiBcB5s1kuqp08bLXHLjmzs4rZaGr0lgAYVYn4aeDmekLITXVOynpqmPRZUQQTcNU0n321nD7Gny94AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22e98386aaa6b6120d0eb5be5cf9dcc9058b68b4ced9e125de6b46a7fa1cf9d8","last_reissued_at":"2026-07-05T02:47:39.985401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:39.985401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.02810","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":"2026-07-05T02:47:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8lvDstdd9FONf75vtTMat2j4tmRayxR9Y4RtFPVgPsYRayAJgqGseKgfguMBflmLz2kt0nzkdnqSRZIWLJIKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T12:44:17.136115Z"},"content_sha256":"ffd0b101c24ad3231412e2d62e254e34a35bf79b42305c673423c78a10466722","schema_version":"1.0","event_id":"sha256:ffd0b101c24ad3231412e2d62e254e34a35bf79b42305c673423c78a10466722"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ELUYHBVKU23BEDIOWW7FZ6O4ZE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Swiss Parliaments Corpus, an Automatically Aligned Swiss German Speech to Standard German Text Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Scheller, Lukas Neukom, Manfred Vogel, Michel Pl\\\"uss","submitted_at":"2020-10-06T15:18:21Z","abstract_excerpt":"We present the Swiss Parliaments Corpus (SPC), an automatically aligned Swiss German speech to Standard German text corpus. This first version of the corpus is based on publicly available data of the Bernese cantonal parliament and consists of 293 hours of data. It was created using a novel forced sentence alignment procedure and an alignment quality estimator, which can be used to trade off corpus size and quality. We trained Automatic Speech Recognition (ASR) models as baselines on different subsets of the data and achieved a Word Error Rate (WER) of 0.278 and a BLEU score of 0.586 on the SP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02810","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/2010.02810/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":"2026-07-05T02:47:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HVgMbQ7r5iYW2FnP3/X9J56/PUE25TIY0Gs1sf782fyFlvsEUnXDrlT/f3NnGSThXkKNx7GhFnEwIqXr6wtqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T12:44:17.136697Z"},"content_sha256":"fc66094b7551a15a9537d1fef7aab7e35cbfc30e0752afa1d2a71ee97a01624a","schema_version":"1.0","event_id":"sha256:fc66094b7551a15a9537d1fef7aab7e35cbfc30e0752afa1d2a71ee97a01624a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ELUYHBVKU23BEDIOWW7FZ6O4ZE/bundle.json","state_url":"https://pith.science/pith/ELUYHBVKU23BEDIOWW7FZ6O4ZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ELUYHBVKU23BEDIOWW7FZ6O4ZE/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":"2026-08-21T12:44:17Z","links":{"resolver":"https://pith.science/pith/ELUYHBVKU23BEDIOWW7FZ6O4ZE","bundle":"https://pith.science/pith/ELUYHBVKU23BEDIOWW7FZ6O4ZE/bundle.json","state":"https://pith.science/pith/ELUYHBVKU23BEDIOWW7FZ6O4ZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ELUYHBVKU23BEDIOWW7FZ6O4ZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ELUYHBVKU23BEDIOWW7FZ6O4ZE","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":"b624c0d2c919972dd78e8d76828cc32e5a94cc9dfcdc16ad9ddddefdd68bbcab","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T15:18:21Z","title_canon_sha256":"d2f74f4494b48aec10a19815bbcbda82aba08500cf64eb5c69c62371752ac851"},"schema_version":"1.0","source":{"id":"2010.02810","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02810","created_at":"2026-07-05T02:47:39Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02810v2","created_at":"2026-07-05T02:47:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02810","created_at":"2026-07-05T02:47:39Z"},{"alias_kind":"pith_short_12","alias_value":"ELUYHBVKU23B","created_at":"2026-07-05T02:47:39Z"},{"alias_kind":"pith_short_16","alias_value":"ELUYHBVKU23BEDIO","created_at":"2026-07-05T02:47:39Z"},{"alias_kind":"pith_short_8","alias_value":"ELUYHBVK","created_at":"2026-07-05T02:47:39Z"}],"graph_snapshots":[{"event_id":"sha256:fc66094b7551a15a9537d1fef7aab7e35cbfc30e0752afa1d2a71ee97a01624a","target":"graph","created_at":"2026-07-05T02:47:39Z","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/2010.02810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the Swiss Parliaments Corpus (SPC), an automatically aligned Swiss German speech to Standard German text corpus. This first version of the corpus is based on publicly available data of the Bernese cantonal parliament and consists of 293 hours of data. It was created using a novel forced sentence alignment procedure and an alignment quality estimator, which can be used to trade off corpus size and quality. We trained Automatic Speech Recognition (ASR) models as baselines on different subsets of the data and achieved a Word Error Rate (WER) of 0.278 and a BLEU score of 0.586 on the SP","authors_text":"Christian Scheller, Lukas Neukom, Manfred Vogel, Michel Pl\\\"uss","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T15:18:21Z","title":"Swiss Parliaments Corpus, an Automatically Aligned Swiss German Speech to Standard German Text Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02810","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:ffd0b101c24ad3231412e2d62e254e34a35bf79b42305c673423c78a10466722","target":"record","created_at":"2026-07-05T02:47:39Z","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":"b624c0d2c919972dd78e8d76828cc32e5a94cc9dfcdc16ad9ddddefdd68bbcab","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T15:18:21Z","title_canon_sha256":"d2f74f4494b48aec10a19815bbcbda82aba08500cf64eb5c69c62371752ac851"},"schema_version":"1.0","source":{"id":"2010.02810","kind":"arxiv","version":2}},"canonical_sha256":"22e98386aaa6b6120d0eb5be5cf9dcc9058b68b4ced9e125de6b46a7fa1cf9d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22e98386aaa6b6120d0eb5be5cf9dcc9058b68b4ced9e125de6b46a7fa1cf9d8","first_computed_at":"2026-07-05T02:47:39.985401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:39.985401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e0v2jjDiBcB5s1kuqp08bLXHLjmzs4rZaGr0lgAYVYn4aeDmekLITXVOynpqmPRZUQQTcNU0n321nD7Gny94AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:39.985842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.02810","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffd0b101c24ad3231412e2d62e254e34a35bf79b42305c673423c78a10466722","sha256:fc66094b7551a15a9537d1fef7aab7e35cbfc30e0752afa1d2a71ee97a01624a"],"state_sha256":"8129164c72653ca54a042b2ba82b9def1a39f58e02ebe9ee7224d1f41dcefc8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cZqfvZ++tWXCFT+6dvjjDVed4MNryiKuyTFozT60TlnAPe26UhFntP2vPaKp2zjXahBoL4EhJIEqCqn14120Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T12:44:17.149345Z","bundle_sha256":"c6d8f03f5f1472bd6a6f708671b4678a598563de7d3676b5821e95c9c1da5771"}}