{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AIU3L3YVSCGIZCP6TU6CLJV3VQ","short_pith_number":"pith:AIU3L3YV","schema_version":"1.0","canonical_sha256":"0229b5ef15908c8c89fe9d3c25a6bbac15ae088ae130ed3ac1d341bcfd440d17","source":{"kind":"arxiv","id":"1704.07431","version":5},"attestation_state":"computed","paper":{"title":"A Challenge Set Approach to Evaluating Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Colin Cherry, George Foster, Pierre Isabelle","submitted_at":"2017-04-24T19:34:38Z","abstract_excerpt":"Neural machine translation represents an exciting leap forward in translation quality. But what longstanding weaknesses does it resolve, and which remain? We address these questions with a challenge set approach to translation evaluation and error analysis. A challenge set consists of a small set of sentences, each hand-designed to probe a system's capacity to bridge a particular structural divergence between languages. To exemplify this approach, we present an English-French challenge set, and use it to analyze phrase-based and neural systems. The resulting analysis provides not only a more f"},"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":"1704.07431","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-24T19:34:38Z","cross_cats_sorted":[],"title_canon_sha256":"ea280279b048e7c5588e5e3a4736f2cc066b8e2a833de2ada0c803572439fd85","abstract_canon_sha256":"b1b3dab5593b3ff4aa3daf0050d2824a9e1ba68dc7e32ffc36c502790b38694f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:31.884880Z","signature_b64":"AZWCVqXtiK9aZgg7N7OxG+EhkwfeBi7H0p1TxREXpg3x79Hak44kH+1KpwQ2l/DHH3LRE9R4n4VSTgwJiBUFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0229b5ef15908c8c89fe9d3c25a6bbac15ae088ae130ed3ac1d341bcfd440d17","last_reissued_at":"2026-05-18T00:36:31.884254Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:31.884254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Challenge Set Approach to Evaluating Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Colin Cherry, George Foster, Pierre Isabelle","submitted_at":"2017-04-24T19:34:38Z","abstract_excerpt":"Neural machine translation represents an exciting leap forward in translation quality. But what longstanding weaknesses does it resolve, and which remain? We address these questions with a challenge set approach to translation evaluation and error analysis. A challenge set consists of a small set of sentences, each hand-designed to probe a system's capacity to bridge a particular structural divergence between languages. To exemplify this approach, we present an English-French challenge set, and use it to analyze phrase-based and neural systems. The resulting analysis provides not only a more f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.07431","kind":"arxiv","version":5},"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":"1704.07431","created_at":"2026-05-18T00:36:31.884352+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.07431v5","created_at":"2026-05-18T00:36:31.884352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.07431","created_at":"2026-05-18T00:36:31.884352+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIU3L3YVSCGI","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIU3L3YVSCGIZCP6","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIU3L3YV","created_at":"2026-05-18T12:31:05.417338+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/AIU3L3YVSCGIZCP6TU6CLJV3VQ","json":"https://pith.science/pith/AIU3L3YVSCGIZCP6TU6CLJV3VQ.json","graph_json":"https://pith.science/api/pith-number/AIU3L3YVSCGIZCP6TU6CLJV3VQ/graph.json","events_json":"https://pith.science/api/pith-number/AIU3L3YVSCGIZCP6TU6CLJV3VQ/events.json","paper":"https://pith.science/paper/AIU3L3YV"},"agent_actions":{"view_html":"https://pith.science/pith/AIU3L3YVSCGIZCP6TU6CLJV3VQ","download_json":"https://pith.science/pith/AIU3L3YVSCGIZCP6TU6CLJV3VQ.json","view_paper":"https://pith.science/paper/AIU3L3YV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.07431&json=true","fetch_graph":"https://pith.science/api/pith-number/AIU3L3YVSCGIZCP6TU6CLJV3VQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AIU3L3YVSCGIZCP6TU6CLJV3VQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIU3L3YVSCGIZCP6TU6CLJV3VQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIU3L3YVSCGIZCP6TU6CLJV3VQ/action/storage_attestation","attest_author":"https://pith.science/pith/AIU3L3YVSCGIZCP6TU6CLJV3VQ/action/author_attestation","sign_citation":"https://pith.science/pith/AIU3L3YVSCGIZCP6TU6CLJV3VQ/action/citation_signature","submit_replication":"https://pith.science/pith/AIU3L3YVSCGIZCP6TU6CLJV3VQ/action/replication_record"}},"created_at":"2026-05-18T00:36:31.884352+00:00","updated_at":"2026-05-18T00:36:31.884352+00:00"}