{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NAI6TEEMXGX3P3WTOHSWQRMESI","short_pith_number":"pith:NAI6TEEM","schema_version":"1.0","canonical_sha256":"6811e9908cb9afb7eed371e5684584922c06d360e6b63443564906f63b956041","source":{"kind":"arxiv","id":"2306.11420","version":1},"attestation_state":"computed","paper":{"title":"On Evaluating Multilingual Compositional Generalization with Translated Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Hershcovich, Zi Wang","submitted_at":"2023-06-20T10:03:57Z","abstract_excerpt":"Compositional generalization allows efficient learning and human-like inductive biases. Since most research investigating compositional generalization in NLP is done on English, important questions remain underexplored. Do the necessary compositional generalization abilities differ across languages? Can models compositionally generalize cross-lingually? As a first step to answering these questions, recent work used neural machine translation to translate datasets for evaluating compositional generalization in semantic parsing. However, we show that this entails critical semantic distortion. To"},"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":"2306.11420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T10:03:57Z","cross_cats_sorted":[],"title_canon_sha256":"41b2b8f51af06363d7f9cb4932a5a0796870a943bdc2452902c1c19448e24478","abstract_canon_sha256":"2d80a889c84c7d3ad8ecde330382ad4082e0bd1916b193bcb19025ea5cd473e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:19.629774Z","signature_b64":"hsDThrPUl3EsNPPX5yNsobkdu68bRaQStRxD7+ME33oP4JFYapH9Yo583nVueaxQyJE0mmdU2Ukp2AbgkAnpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6811e9908cb9afb7eed371e5684584922c06d360e6b63443564906f63b956041","last_reissued_at":"2026-07-05T06:22:19.629328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:19.629328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Evaluating Multilingual Compositional Generalization with Translated Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Hershcovich, Zi Wang","submitted_at":"2023-06-20T10:03:57Z","abstract_excerpt":"Compositional generalization allows efficient learning and human-like inductive biases. Since most research investigating compositional generalization in NLP is done on English, important questions remain underexplored. Do the necessary compositional generalization abilities differ across languages? Can models compositionally generalize cross-lingually? As a first step to answering these questions, recent work used neural machine translation to translate datasets for evaluating compositional generalization in semantic parsing. However, we show that this entails critical semantic distortion. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11420","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/2306.11420/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.11420","created_at":"2026-07-05T06:22:19.629393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11420v1","created_at":"2026-07-05T06:22:19.629393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11420","created_at":"2026-07-05T06:22:19.629393+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAI6TEEMXGX3","created_at":"2026-07-05T06:22:19.629393+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAI6TEEMXGX3P3WT","created_at":"2026-07-05T06:22:19.629393+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAI6TEEM","created_at":"2026-07-05T06:22:19.629393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11786","citing_title":"Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAI6TEEMXGX3P3WTOHSWQRMESI","json":"https://pith.science/pith/NAI6TEEMXGX3P3WTOHSWQRMESI.json","graph_json":"https://pith.science/api/pith-number/NAI6TEEMXGX3P3WTOHSWQRMESI/graph.json","events_json":"https://pith.science/api/pith-number/NAI6TEEMXGX3P3WTOHSWQRMESI/events.json","paper":"https://pith.science/paper/NAI6TEEM"},"agent_actions":{"view_html":"https://pith.science/pith/NAI6TEEMXGX3P3WTOHSWQRMESI","download_json":"https://pith.science/pith/NAI6TEEMXGX3P3WTOHSWQRMESI.json","view_paper":"https://pith.science/paper/NAI6TEEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11420&json=true","fetch_graph":"https://pith.science/api/pith-number/NAI6TEEMXGX3P3WTOHSWQRMESI/graph.json","fetch_events":"https://pith.science/api/pith-number/NAI6TEEMXGX3P3WTOHSWQRMESI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAI6TEEMXGX3P3WTOHSWQRMESI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAI6TEEMXGX3P3WTOHSWQRMESI/action/storage_attestation","attest_author":"https://pith.science/pith/NAI6TEEMXGX3P3WTOHSWQRMESI/action/author_attestation","sign_citation":"https://pith.science/pith/NAI6TEEMXGX3P3WTOHSWQRMESI/action/citation_signature","submit_replication":"https://pith.science/pith/NAI6TEEMXGX3P3WTOHSWQRMESI/action/replication_record"}},"created_at":"2026-07-05T06:22:19.629393+00:00","updated_at":"2026-07-05T06:22:19.629393+00:00"}