{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EFJWZXXRFS2QUKANTMOWKEIRHB","short_pith_number":"pith:EFJWZXXR","schema_version":"1.0","canonical_sha256":"21536cdef12cb50a280d9b1d651111386097c4d31b433af5a4fd054776c2edbc","source":{"kind":"arxiv","id":"1802.01451","version":1},"attestation_state":"computed","paper":{"title":"Quantitative Fine-Grained Human Evaluation of Machine Translation Systems: a Case Study on English to Croatian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Antonio Toral, Filip Klubi\\v{c}ka, V\\'ictor M. S\\'anchez-Cartagena","submitted_at":"2018-02-02T14:41:08Z","abstract_excerpt":"This paper presents a quantitative fine-grained manual evaluation approach to comparing the performance of different machine translation (MT) systems. We build upon the well-established Multidimensional Quality Metrics (MQM) error taxonomy and implement a novel method that assesses whether the differences in performance for MQM error types between different MT systems are statistically significant. We conduct a case study for English-to-Croatian, a language direction that involves translating into a morphologically rich language, for which we compare three MT systems belonging to different par"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1802.01451","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-02T14:41:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70829a7d4f9304ba8ba3cc2cda22c61bf28743a6b338fa8df92e65fd377dee40","abstract_canon_sha256":"2bb914c25011ffdab114842d377ce0ea640fbf1ed8f3b674c101c40f25b061c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:51.950022Z","signature_b64":"loFhly0lrey/19l7i/jJ0dV1Cr66hPiZF+jiLMMHAKUZflWN2/g8qSCb/V2xRFOL2dG50iVkUnRF9mHcwRycAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21536cdef12cb50a280d9b1d651111386097c4d31b433af5a4fd054776c2edbc","last_reissued_at":"2026-05-18T00:23:51.949544Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:51.949544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantitative Fine-Grained Human Evaluation of Machine Translation Systems: a Case Study on English to Croatian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Antonio Toral, Filip Klubi\\v{c}ka, V\\'ictor M. S\\'anchez-Cartagena","submitted_at":"2018-02-02T14:41:08Z","abstract_excerpt":"This paper presents a quantitative fine-grained manual evaluation approach to comparing the performance of different machine translation (MT) systems. We build upon the well-established Multidimensional Quality Metrics (MQM) error taxonomy and implement a novel method that assesses whether the differences in performance for MQM error types between different MT systems are statistically significant. We conduct a case study for English-to-Croatian, a language direction that involves translating into a morphologically rich language, for which we compare three MT systems belonging to different par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.01451","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1802.01451","created_at":"2026-05-18T00:23:51.949613+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.01451v1","created_at":"2026-05-18T00:23:51.949613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.01451","created_at":"2026-05-18T00:23:51.949613+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFJWZXXRFS2Q","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFJWZXXRFS2QUKAN","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFJWZXXR","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EFJWZXXRFS2QUKANTMOWKEIRHB","json":"https://pith.science/pith/EFJWZXXRFS2QUKANTMOWKEIRHB.json","graph_json":"https://pith.science/api/pith-number/EFJWZXXRFS2QUKANTMOWKEIRHB/graph.json","events_json":"https://pith.science/api/pith-number/EFJWZXXRFS2QUKANTMOWKEIRHB/events.json","paper":"https://pith.science/paper/EFJWZXXR"},"agent_actions":{"view_html":"https://pith.science/pith/EFJWZXXRFS2QUKANTMOWKEIRHB","download_json":"https://pith.science/pith/EFJWZXXRFS2QUKANTMOWKEIRHB.json","view_paper":"https://pith.science/paper/EFJWZXXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.01451&json=true","fetch_graph":"https://pith.science/api/pith-number/EFJWZXXRFS2QUKANTMOWKEIRHB/graph.json","fetch_events":"https://pith.science/api/pith-number/EFJWZXXRFS2QUKANTMOWKEIRHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFJWZXXRFS2QUKANTMOWKEIRHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFJWZXXRFS2QUKANTMOWKEIRHB/action/storage_attestation","attest_author":"https://pith.science/pith/EFJWZXXRFS2QUKANTMOWKEIRHB/action/author_attestation","sign_citation":"https://pith.science/pith/EFJWZXXRFS2QUKANTMOWKEIRHB/action/citation_signature","submit_replication":"https://pith.science/pith/EFJWZXXRFS2QUKANTMOWKEIRHB/action/replication_record"}},"created_at":"2026-05-18T00:23:51.949613+00:00","updated_at":"2026-05-18T00:23:51.949613+00:00"}