{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LE5VXDBBMBFDU24IIKZ72ZADD5","short_pith_number":"pith:LE5VXDBB","schema_version":"1.0","canonical_sha256":"593b5b8c21604a3a6b8842b3fd64031f4c868b7f504a2c21bbc5bf7640f44709","source":{"kind":"arxiv","id":"1908.03067","version":1},"attestation_state":"computed","paper":{"title":"Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Zhou, Pengcheng Yang, Peng Li, Shuming Ma, Tianyu Liu, Xu Sun","submitted_at":"2019-08-08T13:41:31Z","abstract_excerpt":"Table-to-text generation aims to translate the structured data into the unstructured text. Most existing methods adopt the encoder-decoder framework to learn the transformation, which requires large-scale training samples. However, the lack of large parallel data is a major practical problem for many domains. In this work, we consider the scenario of low resource table-to-text generation, where only limited parallel data is available. We propose a novel model to separate the generation into two stages: key fact prediction and surface realization. It first predicts the key facts from the tables"},"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":"1908.03067","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-08T13:41:31Z","cross_cats_sorted":[],"title_canon_sha256":"8aed1df68be376e1e0a5cc7ff372f2da6b07a7e6b11e99bd806066578c9fdba2","abstract_canon_sha256":"ea2a17e8b666bbaac486eb02dedfa4db5580f92a55b07212ee1748a7631b009a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:25.907731Z","signature_b64":"wPdyW18bvwWW36AGhAtwd//+GvEaHjEcpoanNloTXJJ6nsYudzUaKyCSZTy/zdQ8W7K9jgMfBSPlwB/Je6G0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"593b5b8c21604a3a6b8842b3fd64031f4c868b7f504a2c21bbc5bf7640f44709","last_reissued_at":"2026-07-04T23:52:25.907227Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:25.907227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Zhou, Pengcheng Yang, Peng Li, Shuming Ma, Tianyu Liu, Xu Sun","submitted_at":"2019-08-08T13:41:31Z","abstract_excerpt":"Table-to-text generation aims to translate the structured data into the unstructured text. Most existing methods adopt the encoder-decoder framework to learn the transformation, which requires large-scale training samples. However, the lack of large parallel data is a major practical problem for many domains. In this work, we consider the scenario of low resource table-to-text generation, where only limited parallel data is available. We propose a novel model to separate the generation into two stages: key fact prediction and surface realization. It first predicts the key facts from the tables"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03067","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/1908.03067/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":"1908.03067","created_at":"2026-07-04T23:52:25.907280+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03067v1","created_at":"2026-07-04T23:52:25.907280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03067","created_at":"2026-07-04T23:52:25.907280+00:00"},{"alias_kind":"pith_short_12","alias_value":"LE5VXDBBMBFD","created_at":"2026-07-04T23:52:25.907280+00:00"},{"alias_kind":"pith_short_16","alias_value":"LE5VXDBBMBFDU24I","created_at":"2026-07-04T23:52:25.907280+00:00"},{"alias_kind":"pith_short_8","alias_value":"LE5VXDBB","created_at":"2026-07-04T23:52:25.907280+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/LE5VXDBBMBFDU24IIKZ72ZADD5","json":"https://pith.science/pith/LE5VXDBBMBFDU24IIKZ72ZADD5.json","graph_json":"https://pith.science/api/pith-number/LE5VXDBBMBFDU24IIKZ72ZADD5/graph.json","events_json":"https://pith.science/api/pith-number/LE5VXDBBMBFDU24IIKZ72ZADD5/events.json","paper":"https://pith.science/paper/LE5VXDBB"},"agent_actions":{"view_html":"https://pith.science/pith/LE5VXDBBMBFDU24IIKZ72ZADD5","download_json":"https://pith.science/pith/LE5VXDBBMBFDU24IIKZ72ZADD5.json","view_paper":"https://pith.science/paper/LE5VXDBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03067&json=true","fetch_graph":"https://pith.science/api/pith-number/LE5VXDBBMBFDU24IIKZ72ZADD5/graph.json","fetch_events":"https://pith.science/api/pith-number/LE5VXDBBMBFDU24IIKZ72ZADD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LE5VXDBBMBFDU24IIKZ72ZADD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LE5VXDBBMBFDU24IIKZ72ZADD5/action/storage_attestation","attest_author":"https://pith.science/pith/LE5VXDBBMBFDU24IIKZ72ZADD5/action/author_attestation","sign_citation":"https://pith.science/pith/LE5VXDBBMBFDU24IIKZ72ZADD5/action/citation_signature","submit_replication":"https://pith.science/pith/LE5VXDBBMBFDU24IIKZ72ZADD5/action/replication_record"}},"created_at":"2026-07-04T23:52:25.907280+00:00","updated_at":"2026-07-04T23:52:25.907280+00:00"}