{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NCPYKCGYW6DK7VP64XYQK4T44O","short_pith_number":"pith:NCPYKCGY","canonical_record":{"source":{"id":"2501.05963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T13:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"492afca0a87f52a31e4375a47c8832c4771da23d2ab45e26a5ed3c3aa249bf0f","abstract_canon_sha256":"f6a6aff7ead8447c29147baf61cd040513c06b7464bee20780f56a22dba98b90"},"schema_version":"1.0"},"canonical_sha256":"689f8508d8b786afd5fee5f105727ce3980717de18bdfec2ed991e75290697df","source":{"kind":"arxiv","id":"2501.05963","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05963","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05963v1","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05963","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_12","alias_value":"NCPYKCGYW6DK","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_16","alias_value":"NCPYKCGYW6DK7VP6","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_8","alias_value":"NCPYKCGY","created_at":"2026-07-05T09:59:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NCPYKCGYW6DK7VP64XYQK4T44O","target":"record","payload":{"canonical_record":{"source":{"id":"2501.05963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T13:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"492afca0a87f52a31e4375a47c8832c4771da23d2ab45e26a5ed3c3aa249bf0f","abstract_canon_sha256":"f6a6aff7ead8447c29147baf61cd040513c06b7464bee20780f56a22dba98b90"},"schema_version":"1.0"},"canonical_sha256":"689f8508d8b786afd5fee5f105727ce3980717de18bdfec2ed991e75290697df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:30.926226Z","signature_b64":"W+BeZRN8Qcgpb1vC+ZkiCBPS120bqdawZrXNYIPKughhLjuBI8+2GJmVmvyAPR48wv1I6a+ihJQnJxyVdNsIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"689f8508d8b786afd5fee5f105727ce3980717de18bdfec2ed991e75290697df","last_reissued_at":"2026-07-05T09:59:30.925683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:30.925683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.05963","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":"2026-07-05T09:59:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qUfBrMDeMA0fA6JBmQQvaqaJsK15TlMN/BbDlqcWl4oZUnBxy5v8rXEPIUOnPt2fvCy8lAd9lnwCPJ6+DHaRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:41:24.764253Z"},"content_sha256":"5a91ad896c46502aafc804a7ebe88056676015986f693fb7124daf000d21467e","schema_version":"1.0","event_id":"sha256:5a91ad896c46502aafc804a7ebe88056676015986f693fb7124daf000d21467e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NCPYKCGYW6DK7VP64XYQK4T44O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finnish SQuAD: A Simple Approach to Machine Translation of Span Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emil Nuutinen, Filip Ginter, Iiro Rastas","submitted_at":"2025-01-10T13:44:11Z","abstract_excerpt":"We apply a simple method to machine translate datasets with span-level annotation using the DeepL MT service and its ability to translate formatted documents. Using this method, we produce a Finnish version of the SQuAD2.0 question answering dataset and train QA retriever models on this new dataset. We evaluate the quality of the dataset and more generally the MT method through direct evaluation, indirect comparison to other similar datasets, a backtranslation experiment, as well as through the performance of downstream trained QA models. In all these evaluations, we find that the method of tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05963","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/2501.05963/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":"2026-07-05T09:59:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w5f/0YN0nf4zBT3M31ryzsroEVtQxlHz+/RnDEGvbNxPYZ3aAHuPdI5fNR0N02hHIjvc5y+u+OSGmg7mB9BYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:41:24.764765Z"},"content_sha256":"8ab4d652fd3912840c1cf01a542a04f6402df1577c89d53698f97ebe53ca2f52","schema_version":"1.0","event_id":"sha256:8ab4d652fd3912840c1cf01a542a04f6402df1577c89d53698f97ebe53ca2f52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCPYKCGYW6DK7VP64XYQK4T44O/bundle.json","state_url":"https://pith.science/pith/NCPYKCGYW6DK7VP64XYQK4T44O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCPYKCGYW6DK7VP64XYQK4T44O/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":"2026-08-11T12:41:24Z","links":{"resolver":"https://pith.science/pith/NCPYKCGYW6DK7VP64XYQK4T44O","bundle":"https://pith.science/pith/NCPYKCGYW6DK7VP64XYQK4T44O/bundle.json","state":"https://pith.science/pith/NCPYKCGYW6DK7VP64XYQK4T44O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCPYKCGYW6DK7VP64XYQK4T44O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NCPYKCGYW6DK7VP64XYQK4T44O","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":"f6a6aff7ead8447c29147baf61cd040513c06b7464bee20780f56a22dba98b90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T13:44:11Z","title_canon_sha256":"492afca0a87f52a31e4375a47c8832c4771da23d2ab45e26a5ed3c3aa249bf0f"},"schema_version":"1.0","source":{"id":"2501.05963","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05963","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05963v1","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05963","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_12","alias_value":"NCPYKCGYW6DK","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_16","alias_value":"NCPYKCGYW6DK7VP6","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_8","alias_value":"NCPYKCGY","created_at":"2026-07-05T09:59:30Z"}],"graph_snapshots":[{"event_id":"sha256:8ab4d652fd3912840c1cf01a542a04f6402df1577c89d53698f97ebe53ca2f52","target":"graph","created_at":"2026-07-05T09:59:30Z","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/2501.05963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We apply a simple method to machine translate datasets with span-level annotation using the DeepL MT service and its ability to translate formatted documents. Using this method, we produce a Finnish version of the SQuAD2.0 question answering dataset and train QA retriever models on this new dataset. We evaluate the quality of the dataset and more generally the MT method through direct evaluation, indirect comparison to other similar datasets, a backtranslation experiment, as well as through the performance of downstream trained QA models. In all these evaluations, we find that the method of tr","authors_text":"Emil Nuutinen, Filip Ginter, Iiro Rastas","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T13:44:11Z","title":"Finnish SQuAD: A Simple Approach to Machine Translation of Span Annotations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05963","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":"sha256:5a91ad896c46502aafc804a7ebe88056676015986f693fb7124daf000d21467e","target":"record","created_at":"2026-07-05T09:59:30Z","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":"f6a6aff7ead8447c29147baf61cd040513c06b7464bee20780f56a22dba98b90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T13:44:11Z","title_canon_sha256":"492afca0a87f52a31e4375a47c8832c4771da23d2ab45e26a5ed3c3aa249bf0f"},"schema_version":"1.0","source":{"id":"2501.05963","kind":"arxiv","version":1}},"canonical_sha256":"689f8508d8b786afd5fee5f105727ce3980717de18bdfec2ed991e75290697df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"689f8508d8b786afd5fee5f105727ce3980717de18bdfec2ed991e75290697df","first_computed_at":"2026-07-05T09:59:30.925683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:30.925683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W+BeZRN8Qcgpb1vC+ZkiCBPS120bqdawZrXNYIPKughhLjuBI8+2GJmVmvyAPR48wv1I6a+ihJQnJxyVdNsIAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:30.926226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05963","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a91ad896c46502aafc804a7ebe88056676015986f693fb7124daf000d21467e","sha256:8ab4d652fd3912840c1cf01a542a04f6402df1577c89d53698f97ebe53ca2f52"],"state_sha256":"224f509d6a256cfd8caaa342f52668fb84a5d06d34dd322255f646780037440a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i92zg322f612oA9coosrZU7tyJ9VDKdwGDSDCRc7RluyR8cq9DcTl9Sn7JULpXk9zWJsyiH2yoTlOLmmOD3PDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T12:41:24.769697Z","bundle_sha256":"1074dbdab2984e07430cc0a8417472594b1206637c7b61236ad2e3f51a3dcc5d"}}