{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:K6GG5EL33S7NPBLVWMGPZBJNDN","short_pith_number":"pith:K6GG5EL3","canonical_record":{"source":{"id":"2104.12741","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-26T17:34:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a6dafbeaf603cef405228db66d6daf8d4ffcb95341e0eb6b6668e772052978b0","abstract_canon_sha256":"4d5d50a6dfbc40e7fe0aa4d4433d88e195c8b842f99769e94e6e124a8a28c446"},"schema_version":"1.0"},"canonical_sha256":"578c6e917bdcbed78575b30cfc852d1b6f7094a4b969b6b0fc40cf17485fa4bc","source":{"kind":"arxiv","id":"2104.12741","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.12741","created_at":"2026-07-05T02:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2104.12741v1","created_at":"2026-07-05T02:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.12741","created_at":"2026-07-05T02:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"K6GG5EL33S7N","created_at":"2026-07-05T02:34:59Z"},{"alias_kind":"pith_short_16","alias_value":"K6GG5EL33S7NPBLV","created_at":"2026-07-05T02:34:59Z"},{"alias_kind":"pith_short_8","alias_value":"K6GG5EL3","created_at":"2026-07-05T02:34:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:K6GG5EL33S7NPBLVWMGPZBJNDN","target":"record","payload":{"canonical_record":{"source":{"id":"2104.12741","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-26T17:34:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a6dafbeaf603cef405228db66d6daf8d4ffcb95341e0eb6b6668e772052978b0","abstract_canon_sha256":"4d5d50a6dfbc40e7fe0aa4d4433d88e195c8b842f99769e94e6e124a8a28c446"},"schema_version":"1.0"},"canonical_sha256":"578c6e917bdcbed78575b30cfc852d1b6f7094a4b969b6b0fc40cf17485fa4bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:59.607262Z","signature_b64":"6LNtvvDQN/9/GPcZ7Xy9gPon6k2ckYVrJP8L8C0K75+ivVuPkvQN+zAkKH/UyKgO/+MTHNpQeXTHsyZJH0JfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"578c6e917bdcbed78575b30cfc852d1b6f7094a4b969b6b0fc40cf17485fa4bc","last_reissued_at":"2026-07-05T02:34:59.606752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:59.606752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.12741","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":"2026-07-05T02:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"08+zpGclEUWGTtHeK5AfYRh5sG6zS7qJkrjOEwtOYnW2NnMpMwLwsR973P4HXkn7d00JdiKCK75iFhVILRvTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T09:07:25.059403Z"},"content_sha256":"bb87ac1c90a423058ca8e95a3e8e0daafa79fa3221c5597991f534c16a789d51","schema_version":"1.0","event_id":"sha256:bb87ac1c90a423058ca8e95a3e8e0daafa79fa3221c5597991f534c16a789d51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:K6GG5EL33S7NPBLVWMGPZBJNDN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Julian Risch, Malte Pietsch, Timo M\\\"oller","submitted_at":"2021-04-26T17:34:31Z","abstract_excerpt":"A major challenge of research on non-English machine reading for question answering (QA) is the lack of annotated datasets. In this paper, we present GermanQuAD, a dataset of 13,722 extractive question/answer pairs. To improve the reproducibility of the dataset creation approach and foster QA research on other languages, we summarize lessons learned and evaluate reformulation of question/answer pairs as a way to speed up the annotation process. An extractive QA model trained on GermanQuAD significantly outperforms multilingual models and also shows that machine-translated training data cannot "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.12741","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.12741/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":"2026-07-05T02:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHeIhAliQpnxvhe7Jt7WVz9dtDDaPge7Pi3mVDq7lU/u1K6+5OWOKwyCE9QqDZ94doQAn8mSjjqrari0Q98zDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T09:07:25.059772Z"},"content_sha256":"fed23f8cbc9ab909daf4eb0049d73f89f408cc65c7f1d22a51e6177acc145100","schema_version":"1.0","event_id":"sha256:fed23f8cbc9ab909daf4eb0049d73f89f408cc65c7f1d22a51e6177acc145100"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6GG5EL33S7NPBLVWMGPZBJNDN/bundle.json","state_url":"https://pith.science/pith/K6GG5EL33S7NPBLVWMGPZBJNDN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6GG5EL33S7NPBLVWMGPZBJNDN/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":"2026-07-09T09:07:25Z","links":{"resolver":"https://pith.science/pith/K6GG5EL33S7NPBLVWMGPZBJNDN","bundle":"https://pith.science/pith/K6GG5EL33S7NPBLVWMGPZBJNDN/bundle.json","state":"https://pith.science/pith/K6GG5EL33S7NPBLVWMGPZBJNDN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6GG5EL33S7NPBLVWMGPZBJNDN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:K6GG5EL33S7NPBLVWMGPZBJNDN","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":"4d5d50a6dfbc40e7fe0aa4d4433d88e195c8b842f99769e94e6e124a8a28c446","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-26T17:34:31Z","title_canon_sha256":"a6dafbeaf603cef405228db66d6daf8d4ffcb95341e0eb6b6668e772052978b0"},"schema_version":"1.0","source":{"id":"2104.12741","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.12741","created_at":"2026-07-05T02:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2104.12741v1","created_at":"2026-07-05T02:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.12741","created_at":"2026-07-05T02:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"K6GG5EL33S7N","created_at":"2026-07-05T02:34:59Z"},{"alias_kind":"pith_short_16","alias_value":"K6GG5EL33S7NPBLV","created_at":"2026-07-05T02:34:59Z"},{"alias_kind":"pith_short_8","alias_value":"K6GG5EL3","created_at":"2026-07-05T02:34:59Z"}],"graph_snapshots":[{"event_id":"sha256:fed23f8cbc9ab909daf4eb0049d73f89f408cc65c7f1d22a51e6177acc145100","target":"graph","created_at":"2026-07-05T02:34:59Z","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/2104.12741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A major challenge of research on non-English machine reading for question answering (QA) is the lack of annotated datasets. In this paper, we present GermanQuAD, a dataset of 13,722 extractive question/answer pairs. To improve the reproducibility of the dataset creation approach and foster QA research on other languages, we summarize lessons learned and evaluate reformulation of question/answer pairs as a way to speed up the annotation process. An extractive QA model trained on GermanQuAD significantly outperforms multilingual models and also shows that machine-translated training data cannot ","authors_text":"Julian Risch, Malte Pietsch, Timo M\\\"oller","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-26T17:34:31Z","title":"GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.12741","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:bb87ac1c90a423058ca8e95a3e8e0daafa79fa3221c5597991f534c16a789d51","target":"record","created_at":"2026-07-05T02:34:59Z","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":"4d5d50a6dfbc40e7fe0aa4d4433d88e195c8b842f99769e94e6e124a8a28c446","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-26T17:34:31Z","title_canon_sha256":"a6dafbeaf603cef405228db66d6daf8d4ffcb95341e0eb6b6668e772052978b0"},"schema_version":"1.0","source":{"id":"2104.12741","kind":"arxiv","version":1}},"canonical_sha256":"578c6e917bdcbed78575b30cfc852d1b6f7094a4b969b6b0fc40cf17485fa4bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"578c6e917bdcbed78575b30cfc852d1b6f7094a4b969b6b0fc40cf17485fa4bc","first_computed_at":"2026-07-05T02:34:59.606752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:34:59.606752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6LNtvvDQN/9/GPcZ7Xy9gPon6k2ckYVrJP8L8C0K75+ivVuPkvQN+zAkKH/UyKgO/+MTHNpQeXTHsyZJH0JfCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:34:59.607262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.12741","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb87ac1c90a423058ca8e95a3e8e0daafa79fa3221c5597991f534c16a789d51","sha256:fed23f8cbc9ab909daf4eb0049d73f89f408cc65c7f1d22a51e6177acc145100"],"state_sha256":"a9b4d8f2725cfa9dd36d7778a3807a788070b11896ee05a1428463220b5b360c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ow36D84wqB9Yb/vBxwOP9n92s8k+szePve6F+NQ8o6uwt7VxWe1a7ITAtmnHfxFKJIUeS0NbM9NiXmgvIbr7Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T09:07:25.061789Z","bundle_sha256":"0307349f051eadd626d916cff598296ed64723210c9c0d2ce6201e573dd57162"}}