{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2OFSHC37D4WLPYNMLLMEUTORYU","short_pith_number":"pith:2OFSHC37","schema_version":"1.0","canonical_sha256":"d38b238b7f1f2cb7e1ac5ad84a4dd1c539b773accd132df75a28abb5fc214d31","source":{"kind":"arxiv","id":"1709.08878","version":2},"attestation_state":"computed","paper":{"title":"Generating Sentences by Editing Prototypes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Kelvin Guu, Percy Liang, Tatsunori B. Hashimoto, Yonatan Oren","submitted_at":"2017-09-26T08:11:33Z","abstract_excerpt":"We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence. Compared to traditional models that generate from scratch either left-to-right or by first sampling a latent sentence vector, our prototype-then-edit model improves perplexity on language modeling and generates higher quality outputs according to human evaluation. Furthermore, the model gives rise to a latent edit vector that captures interpretable semantics such as sentence similarity and sentence-level analogies."},"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":"1709.08878","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-26T08:11:33Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"b0ebf1067b6267923d1c00cec4b13722f682b0ddde51b5257c2365afbee17ed2","abstract_canon_sha256":"eb6a25680fa89d2cce93c4add2ce755dcf4a64f24029dca687c7101d957cd333"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:20.787234Z","signature_b64":"oql5bwfKWek3LgvT1xXDXw6vSpoNGEe1Cz6Kwweo7iRDrRM2pQb2mLKjWlTGpMYeUV6jhK0QgFDw9ukdA4c0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d38b238b7f1f2cb7e1ac5ad84a4dd1c539b773accd132df75a28abb5fc214d31","last_reissued_at":"2026-05-18T00:06:20.786785Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:20.786785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Sentences by Editing Prototypes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Kelvin Guu, Percy Liang, Tatsunori B. Hashimoto, Yonatan Oren","submitted_at":"2017-09-26T08:11:33Z","abstract_excerpt":"We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence. Compared to traditional models that generate from scratch either left-to-right or by first sampling a latent sentence vector, our prototype-then-edit model improves perplexity on language modeling and generates higher quality outputs according to human evaluation. Furthermore, the model gives rise to a latent edit vector that captures interpretable semantics such as sentence similarity and sentence-level analogies."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.08878","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":""},"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":"1709.08878","created_at":"2026-05-18T00:06:20.786862+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.08878v2","created_at":"2026-05-18T00:06:20.786862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.08878","created_at":"2026-05-18T00:06:20.786862+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OFSHC37D4WL","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OFSHC37D4WLPYNM","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OFSHC37","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1910.03771","citing_title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","ref_index":112,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2OFSHC37D4WLPYNMLLMEUTORYU","json":"https://pith.science/pith/2OFSHC37D4WLPYNMLLMEUTORYU.json","graph_json":"https://pith.science/api/pith-number/2OFSHC37D4WLPYNMLLMEUTORYU/graph.json","events_json":"https://pith.science/api/pith-number/2OFSHC37D4WLPYNMLLMEUTORYU/events.json","paper":"https://pith.science/paper/2OFSHC37"},"agent_actions":{"view_html":"https://pith.science/pith/2OFSHC37D4WLPYNMLLMEUTORYU","download_json":"https://pith.science/pith/2OFSHC37D4WLPYNMLLMEUTORYU.json","view_paper":"https://pith.science/paper/2OFSHC37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.08878&json=true","fetch_graph":"https://pith.science/api/pith-number/2OFSHC37D4WLPYNMLLMEUTORYU/graph.json","fetch_events":"https://pith.science/api/pith-number/2OFSHC37D4WLPYNMLLMEUTORYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OFSHC37D4WLPYNMLLMEUTORYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OFSHC37D4WLPYNMLLMEUTORYU/action/storage_attestation","attest_author":"https://pith.science/pith/2OFSHC37D4WLPYNMLLMEUTORYU/action/author_attestation","sign_citation":"https://pith.science/pith/2OFSHC37D4WLPYNMLLMEUTORYU/action/citation_signature","submit_replication":"https://pith.science/pith/2OFSHC37D4WLPYNMLLMEUTORYU/action/replication_record"}},"created_at":"2026-05-18T00:06:20.786862+00:00","updated_at":"2026-05-18T00:06:20.786862+00:00"}