{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:3X6TVD5CTHWKYNLAUIHQ27RHPK","short_pith_number":"pith:3X6TVD5C","schema_version":"1.0","canonical_sha256":"ddfd3a8fa299ecac3560a20f0d7e277ab27c4907aa2e706bcaf571967c3f5f19","source":{"kind":"arxiv","id":"1607.00030","version":2},"attestation_state":"computed","paper":{"title":"HUME: Human UCCA-Based Evaluation of Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Birch, Barry Haddow, Omri Abend, Ondrej Bojar","submitted_at":"2016-06-30T20:35:47Z","abstract_excerpt":"Human evaluation of machine translation normally uses sentence-level measures such as relative ranking or adequacy scales. However, these provide no insight into possible errors, and do not scale well with sentence length. We argue for a semantics-based evaluation, which captures what meaning components are retained in the MT output, thus providing a more fine-grained analysis of translation quality, and enabling the construction and tuning of semantics-based MT. We present a novel human semantic evaluation measure, Human UCCA-based MT Evaluation (HUME), building on the UCCA semantic represent"},"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":"1607.00030","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-30T20:35:47Z","cross_cats_sorted":[],"title_canon_sha256":"a1045d391bd978256697646c896b45356dcf344db3ae58c523132f6d6b52c9c3","abstract_canon_sha256":"cb7dd91ce37ee264bcc2143b53c28115c4901765d60394198414c57f3bf52071"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:49.231955Z","signature_b64":"wsE1JtJ3gBAnJ/Sb8I3ndYVYQNSgkRTCgmmYqd6ztmrc5Tc+CDkcUcxaR+LQA0aSWQo5mAiNKn/iVxYxOUsxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddfd3a8fa299ecac3560a20f0d7e277ab27c4907aa2e706bcaf571967c3f5f19","last_reissued_at":"2026-05-18T01:03:49.231246Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:49.231246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HUME: Human UCCA-Based Evaluation of Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Birch, Barry Haddow, Omri Abend, Ondrej Bojar","submitted_at":"2016-06-30T20:35:47Z","abstract_excerpt":"Human evaluation of machine translation normally uses sentence-level measures such as relative ranking or adequacy scales. However, these provide no insight into possible errors, and do not scale well with sentence length. We argue for a semantics-based evaluation, which captures what meaning components are retained in the MT output, thus providing a more fine-grained analysis of translation quality, and enabling the construction and tuning of semantics-based MT. We present a novel human semantic evaluation measure, Human UCCA-based MT Evaluation (HUME), building on the UCCA semantic represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.00030","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":""},"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":"1607.00030","created_at":"2026-05-18T01:03:49.231339+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.00030v2","created_at":"2026-05-18T01:03:49.231339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.00030","created_at":"2026-05-18T01:03:49.231339+00:00"},{"alias_kind":"pith_short_12","alias_value":"3X6TVD5CTHWK","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"3X6TVD5CTHWKYNLA","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"3X6TVD5C","created_at":"2026-05-18T12:29:58.707656+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/3X6TVD5CTHWKYNLAUIHQ27RHPK","json":"https://pith.science/pith/3X6TVD5CTHWKYNLAUIHQ27RHPK.json","graph_json":"https://pith.science/api/pith-number/3X6TVD5CTHWKYNLAUIHQ27RHPK/graph.json","events_json":"https://pith.science/api/pith-number/3X6TVD5CTHWKYNLAUIHQ27RHPK/events.json","paper":"https://pith.science/paper/3X6TVD5C"},"agent_actions":{"view_html":"https://pith.science/pith/3X6TVD5CTHWKYNLAUIHQ27RHPK","download_json":"https://pith.science/pith/3X6TVD5CTHWKYNLAUIHQ27RHPK.json","view_paper":"https://pith.science/paper/3X6TVD5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.00030&json=true","fetch_graph":"https://pith.science/api/pith-number/3X6TVD5CTHWKYNLAUIHQ27RHPK/graph.json","fetch_events":"https://pith.science/api/pith-number/3X6TVD5CTHWKYNLAUIHQ27RHPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3X6TVD5CTHWKYNLAUIHQ27RHPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3X6TVD5CTHWKYNLAUIHQ27RHPK/action/storage_attestation","attest_author":"https://pith.science/pith/3X6TVD5CTHWKYNLAUIHQ27RHPK/action/author_attestation","sign_citation":"https://pith.science/pith/3X6TVD5CTHWKYNLAUIHQ27RHPK/action/citation_signature","submit_replication":"https://pith.science/pith/3X6TVD5CTHWKYNLAUIHQ27RHPK/action/replication_record"}},"created_at":"2026-05-18T01:03:49.231339+00:00","updated_at":"2026-05-18T01:03:49.231339+00:00"}