{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:T4MOAHFLNMTBBZZD3TBHJARPBC","short_pith_number":"pith:T4MOAHFL","schema_version":"1.0","canonical_sha256":"9f18e01cab6b2610e723dcc274822f08a32d2d9b7e7c17439d27ff42e8491010","source":{"kind":"arxiv","id":"1906.01081","version":1},"attestation_state":"computed","paper":{"title":"Handling Divergent Reference Texts when Evaluating Table-to-Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ankur Parikh, Bhuwan Dhingra, Dipanjan Das, Manaal Faruqui, Ming-Wei Chang, William W. Cohen","submitted_at":"2019-06-03T21:13:07Z","abstract_excerpt":"Automatically constructed datasets for generating text from semi-structured data (tables), such as WikiBio, often contain reference texts that diverge from the information in the corresponding semi-structured data. We show that metrics which rely solely on the reference texts, such as BLEU and ROUGE, show poor correlation with human judgments when those references diverge. We propose a new metric, PARENT, which aligns n-grams from the reference and generated texts to the semi-structured data before computing their precision and recall. Through a large scale human evaluation study of table-to-t"},"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":"1906.01081","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-03T21:13:07Z","cross_cats_sorted":[],"title_canon_sha256":"347510f1187cf1bf4bd72382818689307df03a0d309bf9c9a9eb82b0450118a5","abstract_canon_sha256":"b56d8b63b210a498349c92882097e9f0cfc7c4ac3b477b9a220e10f62c98e74a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:17.916560Z","signature_b64":"9Eix54GhWw9AWi2SEE3IlkcNwrcJ2lsZzBSf7i1qFDqKeG3gCr8qWjRMbqETUyPXMbBxheyNHYYGidjEKFG9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f18e01cab6b2610e723dcc274822f08a32d2d9b7e7c17439d27ff42e8491010","last_reissued_at":"2026-05-17T23:44:17.916000Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:17.916000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Handling Divergent Reference Texts when Evaluating Table-to-Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ankur Parikh, Bhuwan Dhingra, Dipanjan Das, Manaal Faruqui, Ming-Wei Chang, William W. Cohen","submitted_at":"2019-06-03T21:13:07Z","abstract_excerpt":"Automatically constructed datasets for generating text from semi-structured data (tables), such as WikiBio, often contain reference texts that diverge from the information in the corresponding semi-structured data. We show that metrics which rely solely on the reference texts, such as BLEU and ROUGE, show poor correlation with human judgments when those references diverge. We propose a new metric, PARENT, which aligns n-grams from the reference and generated texts to the semi-structured data before computing their precision and recall. Through a large scale human evaluation study of table-to-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01081","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":"1906.01081","created_at":"2026-05-17T23:44:17.916093+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01081v1","created_at":"2026-05-17T23:44:17.916093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01081","created_at":"2026-05-17T23:44:17.916093+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4MOAHFLNMTB","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4MOAHFLNMTBBZZD","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4MOAHFL","created_at":"2026-05-18T12:33:27.125529+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/T4MOAHFLNMTBBZZD3TBHJARPBC","json":"https://pith.science/pith/T4MOAHFLNMTBBZZD3TBHJARPBC.json","graph_json":"https://pith.science/api/pith-number/T4MOAHFLNMTBBZZD3TBHJARPBC/graph.json","events_json":"https://pith.science/api/pith-number/T4MOAHFLNMTBBZZD3TBHJARPBC/events.json","paper":"https://pith.science/paper/T4MOAHFL"},"agent_actions":{"view_html":"https://pith.science/pith/T4MOAHFLNMTBBZZD3TBHJARPBC","download_json":"https://pith.science/pith/T4MOAHFLNMTBBZZD3TBHJARPBC.json","view_paper":"https://pith.science/paper/T4MOAHFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01081&json=true","fetch_graph":"https://pith.science/api/pith-number/T4MOAHFLNMTBBZZD3TBHJARPBC/graph.json","fetch_events":"https://pith.science/api/pith-number/T4MOAHFLNMTBBZZD3TBHJARPBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4MOAHFLNMTBBZZD3TBHJARPBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4MOAHFLNMTBBZZD3TBHJARPBC/action/storage_attestation","attest_author":"https://pith.science/pith/T4MOAHFLNMTBBZZD3TBHJARPBC/action/author_attestation","sign_citation":"https://pith.science/pith/T4MOAHFLNMTBBZZD3TBHJARPBC/action/citation_signature","submit_replication":"https://pith.science/pith/T4MOAHFLNMTBBZZD3TBHJARPBC/action/replication_record"}},"created_at":"2026-05-17T23:44:17.916093+00:00","updated_at":"2026-05-17T23:44:17.916093+00:00"}