{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:THMLZ6EZWMACSFVIHUG5OVFKTY","short_pith_number":"pith:THMLZ6EZ","schema_version":"1.0","canonical_sha256":"99d8bcf899b3002916a83d0dd754aa9e12e64bc42ea70a54bfa0c77341679a62","source":{"kind":"arxiv","id":"2005.09123","version":2},"attestation_state":"computed","paper":{"title":"GPT-too: A language-model-first approach for AMR-to-text generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Manuel Mager, Md Arafat Sultan, Radu Florian, Ramon Fernandez Astudillo, Salim Roukos, Tahira Naseem, Young-Suk Lee","submitted_at":"2020-05-18T22:50:26Z","abstract_excerpt":"Meaning Representations (AMRs) are broad-coverage sentence-level semantic graphs. Existing approaches to generating text from AMR have focused on training sequence-to-sequence or graph-to-sequence models on AMR annotated data only. In this paper, we propose an alternative approach that combines a strong pre-trained language model with cycle consistency-based re-scoring. Despite the simplicity of the approach, our experimental results show these models outperform all previous techniques on the English LDC2017T10dataset, including the recent use of transformer architectures. In addition to the s"},"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":"2005.09123","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-18T22:50:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"de8cbdbf20feedd0e2d97ce58bbcebb2dde01e4e4de0960d1bbe744c1db7cf36","abstract_canon_sha256":"19f5682d3e2fbcefbe57b036c2895bd1d5f1e98dca2df04195162804d97f410a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:11.290149Z","signature_b64":"5FPc6lBZPu/P9PuuuQ6fdrFw8mvGSQHWDI+bzKa5owT+n/Aqboq0f7oJYp3m20+UgDzCQe0DGqqnsAmrTOApBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99d8bcf899b3002916a83d0dd754aa9e12e64bc42ea70a54bfa0c77341679a62","last_reissued_at":"2026-07-05T01:06:11.289738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:11.289738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT-too: A language-model-first approach for AMR-to-text generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Manuel Mager, Md Arafat Sultan, Radu Florian, Ramon Fernandez Astudillo, Salim Roukos, Tahira Naseem, Young-Suk Lee","submitted_at":"2020-05-18T22:50:26Z","abstract_excerpt":"Meaning Representations (AMRs) are broad-coverage sentence-level semantic graphs. Existing approaches to generating text from AMR have focused on training sequence-to-sequence or graph-to-sequence models on AMR annotated data only. In this paper, we propose an alternative approach that combines a strong pre-trained language model with cycle consistency-based re-scoring. Despite the simplicity of the approach, our experimental results show these models outperform all previous techniques on the English LDC2017T10dataset, including the recent use of transformer architectures. In addition to the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09123","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.09123/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":"2005.09123","created_at":"2026-07-05T01:06:11.289801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.09123v2","created_at":"2026-07-05T01:06:11.289801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09123","created_at":"2026-07-05T01:06:11.289801+00:00"},{"alias_kind":"pith_short_12","alias_value":"THMLZ6EZWMAC","created_at":"2026-07-05T01:06:11.289801+00:00"},{"alias_kind":"pith_short_16","alias_value":"THMLZ6EZWMACSFVI","created_at":"2026-07-05T01:06:11.289801+00:00"},{"alias_kind":"pith_short_8","alias_value":"THMLZ6EZ","created_at":"2026-07-05T01:06:11.289801+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/THMLZ6EZWMACSFVIHUG5OVFKTY","json":"https://pith.science/pith/THMLZ6EZWMACSFVIHUG5OVFKTY.json","graph_json":"https://pith.science/api/pith-number/THMLZ6EZWMACSFVIHUG5OVFKTY/graph.json","events_json":"https://pith.science/api/pith-number/THMLZ6EZWMACSFVIHUG5OVFKTY/events.json","paper":"https://pith.science/paper/THMLZ6EZ"},"agent_actions":{"view_html":"https://pith.science/pith/THMLZ6EZWMACSFVIHUG5OVFKTY","download_json":"https://pith.science/pith/THMLZ6EZWMACSFVIHUG5OVFKTY.json","view_paper":"https://pith.science/paper/THMLZ6EZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.09123&json=true","fetch_graph":"https://pith.science/api/pith-number/THMLZ6EZWMACSFVIHUG5OVFKTY/graph.json","fetch_events":"https://pith.science/api/pith-number/THMLZ6EZWMACSFVIHUG5OVFKTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THMLZ6EZWMACSFVIHUG5OVFKTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THMLZ6EZWMACSFVIHUG5OVFKTY/action/storage_attestation","attest_author":"https://pith.science/pith/THMLZ6EZWMACSFVIHUG5OVFKTY/action/author_attestation","sign_citation":"https://pith.science/pith/THMLZ6EZWMACSFVIHUG5OVFKTY/action/citation_signature","submit_replication":"https://pith.science/pith/THMLZ6EZWMACSFVIHUG5OVFKTY/action/replication_record"}},"created_at":"2026-07-05T01:06:11.289801+00:00","updated_at":"2026-07-05T01:06:11.289801+00:00"}