{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Z7NGBFFQO7KNKONS3DPF3P3WHD","short_pith_number":"pith:Z7NGBFFQ","canonical_record":{"source":{"id":"2007.09127","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-17T17:38:08Z","cross_cats_sorted":[],"title_canon_sha256":"0b45a621bb4ea4db35037581fd69ba98a7834471d8d0989c79ee626a0269a87f","abstract_canon_sha256":"7769e3d32bb11f909d91c5c0ba5e6b2575e62e62f755aad4621e69eef45e6e41"},"schema_version":"1.0"},"canonical_sha256":"cfda6094b077d4d539b2d8de5dbf7638ec4be7bb70c922ff72114dcd90dded42","source":{"kind":"arxiv","id":"2007.09127","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.09127","created_at":"2026-07-05T01:39:59Z"},{"alias_kind":"arxiv_version","alias_value":"2007.09127v2","created_at":"2026-07-05T01:39:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.09127","created_at":"2026-07-05T01:39:59Z"},{"alias_kind":"pith_short_12","alias_value":"Z7NGBFFQO7KN","created_at":"2026-07-05T01:39:59Z"},{"alias_kind":"pith_short_16","alias_value":"Z7NGBFFQO7KNKONS","created_at":"2026-07-05T01:39:59Z"},{"alias_kind":"pith_short_8","alias_value":"Z7NGBFFQ","created_at":"2026-07-05T01:39:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Z7NGBFFQO7KNKONS3DPF3P3WHD","target":"record","payload":{"canonical_record":{"source":{"id":"2007.09127","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-17T17:38:08Z","cross_cats_sorted":[],"title_canon_sha256":"0b45a621bb4ea4db35037581fd69ba98a7834471d8d0989c79ee626a0269a87f","abstract_canon_sha256":"7769e3d32bb11f909d91c5c0ba5e6b2575e62e62f755aad4621e69eef45e6e41"},"schema_version":"1.0"},"canonical_sha256":"cfda6094b077d4d539b2d8de5dbf7638ec4be7bb70c922ff72114dcd90dded42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:59.950635Z","signature_b64":"PhtHdXizX/z99JDByuXAUtymv1lhrXdCHwj9w5JeoenCRSfAzkEEQB+0hru0Y1vTpX/okaGAJtk9ZQ4W7wjyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfda6094b077d4d539b2d8de5dbf7638ec4be7bb70c922ff72114dcd90dded42","last_reissued_at":"2026-07-05T01:39:59.950199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:59.950199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.09127","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":"2026-07-05T01:39:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ssdt2Dg/AAX3PuJYmXe1/pmK6aXx7u56xkWVd/JgiFjZP6PXzltJtC4K6zIC7qIV3WOdGauQWX5qx/zJd1EFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:52:11.066400Z"},"content_sha256":"c81ce2977e7d745768538e8cce11113557e81320b24cde7330efcc3371dd3a25","schema_version":"1.0","event_id":"sha256:c81ce2977e7d745768538e8cce11113557e81320b24cde7330efcc3371dd3a25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Z7NGBFFQO7KNKONS3DPF3P3WHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dominik Winkelbauer, Gerhard Rigoll, Ludwig K\\\"urzinger, Lujun Li, Tobias Watzel","submitted_at":"2020-07-17T17:38:08Z","abstract_excerpt":"Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/ HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters and model capacity. However, these models also require more training data to achieve comparable performance.\n  In this work, we combine freely available corpora for German speech recognition, including yet unlabeled speech data, to a big dataset of over $1700$h of speech data. For data preparation, we propose a two-stage approach that uses an ASR model pre-tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.09127","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/2007.09127/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":"2026-07-05T01:39:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UtIBMQRaj4K5TswfstndZXgeDspdcRYRWFLug/xkBBjR0PmTVO3Qvkoq7stVy56Mz0dZj4Dlt/JCYYDs2i/0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:52:11.067378Z"},"content_sha256":"17b1d2100353919a906640370df9527183869f8d30c791fe2b61e1850eaf1ecf","schema_version":"1.0","event_id":"sha256:17b1d2100353919a906640370df9527183869f8d30c791fe2b61e1850eaf1ecf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z7NGBFFQO7KNKONS3DPF3P3WHD/bundle.json","state_url":"https://pith.science/pith/Z7NGBFFQO7KNKONS3DPF3P3WHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z7NGBFFQO7KNKONS3DPF3P3WHD/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":"2026-08-13T02:52:11Z","links":{"resolver":"https://pith.science/pith/Z7NGBFFQO7KNKONS3DPF3P3WHD","bundle":"https://pith.science/pith/Z7NGBFFQO7KNKONS3DPF3P3WHD/bundle.json","state":"https://pith.science/pith/Z7NGBFFQO7KNKONS3DPF3P3WHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z7NGBFFQO7KNKONS3DPF3P3WHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z7NGBFFQO7KNKONS3DPF3P3WHD","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":"7769e3d32bb11f909d91c5c0ba5e6b2575e62e62f755aad4621e69eef45e6e41","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-17T17:38:08Z","title_canon_sha256":"0b45a621bb4ea4db35037581fd69ba98a7834471d8d0989c79ee626a0269a87f"},"schema_version":"1.0","source":{"id":"2007.09127","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.09127","created_at":"2026-07-05T01:39:59Z"},{"alias_kind":"arxiv_version","alias_value":"2007.09127v2","created_at":"2026-07-05T01:39:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.09127","created_at":"2026-07-05T01:39:59Z"},{"alias_kind":"pith_short_12","alias_value":"Z7NGBFFQO7KN","created_at":"2026-07-05T01:39:59Z"},{"alias_kind":"pith_short_16","alias_value":"Z7NGBFFQO7KNKONS","created_at":"2026-07-05T01:39:59Z"},{"alias_kind":"pith_short_8","alias_value":"Z7NGBFFQ","created_at":"2026-07-05T01:39:59Z"}],"graph_snapshots":[{"event_id":"sha256:17b1d2100353919a906640370df9527183869f8d30c791fe2b61e1850eaf1ecf","target":"graph","created_at":"2026-07-05T01:39:59Z","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/2007.09127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/ HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters and model capacity. However, these models also require more training data to achieve comparable performance.\n  In this work, we combine freely available corpora for German speech recognition, including yet unlabeled speech data, to a big dataset of over $1700$h of speech data. For data preparation, we propose a two-stage approach that uses an ASR model pre-tra","authors_text":"Dominik Winkelbauer, Gerhard Rigoll, Ludwig K\\\"urzinger, Lujun Li, Tobias Watzel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-17T17:38:08Z","title":"CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.09127","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:c81ce2977e7d745768538e8cce11113557e81320b24cde7330efcc3371dd3a25","target":"record","created_at":"2026-07-05T01:39:59Z","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":"7769e3d32bb11f909d91c5c0ba5e6b2575e62e62f755aad4621e69eef45e6e41","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-17T17:38:08Z","title_canon_sha256":"0b45a621bb4ea4db35037581fd69ba98a7834471d8d0989c79ee626a0269a87f"},"schema_version":"1.0","source":{"id":"2007.09127","kind":"arxiv","version":2}},"canonical_sha256":"cfda6094b077d4d539b2d8de5dbf7638ec4be7bb70c922ff72114dcd90dded42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfda6094b077d4d539b2d8de5dbf7638ec4be7bb70c922ff72114dcd90dded42","first_computed_at":"2026-07-05T01:39:59.950199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:39:59.950199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PhtHdXizX/z99JDByuXAUtymv1lhrXdCHwj9w5JeoenCRSfAzkEEQB+0hru0Y1vTpX/okaGAJtk9ZQ4W7wjyAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:39:59.950635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.09127","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c81ce2977e7d745768538e8cce11113557e81320b24cde7330efcc3371dd3a25","sha256:17b1d2100353919a906640370df9527183869f8d30c791fe2b61e1850eaf1ecf"],"state_sha256":"9858fa3c45599215a64e0d63483b9e91e292a730679540385f5dce092989c759"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K/yfO5tL7Ityj3XI5+ZugYV5zmnn3FpSmzPyuTuPk/TjKg+9d5mMO4v6kZaRrQo2rQ0adm1A39FsiX1n6qsSBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T02:52:11.074213Z","bundle_sha256":"d100407201059c1ef7dbc7f0072f905ea7a37c0185d9d3e7cdf60bc77e076682"}}