{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5N3GIAKBXCEQABDFSVEZ4P2QWV","short_pith_number":"pith:5N3GIAKB","schema_version":"1.0","canonical_sha256":"eb76640141b88900046595499e3f50b5443019c5d89afac6ce1abd780b6beb7c","source":{"kind":"arxiv","id":"1904.04428","version":2},"attestation_state":"computed","paper":{"title":"Text Generation with Exemplar-based Adaptive Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ankur P. Parikh, Bhuwan Dhingra, Dipanjan Das, Hao Peng, Manaal Faruqui","submitted_at":"2019-04-09T02:34:30Z","abstract_excerpt":"We propose a novel conditioned text generation model. It draws inspiration from traditional template-based text generation techniques, where the source provides the content (i.e., what to say), and the template influences how to say it. Building on the successful encoder-decoder paradigm, it first encodes the content representation from the given input text; to produce the output, it retrieves exemplar text from the training data as \"soft templates,\" which are then used to construct an exemplar-specific decoder. We evaluate the proposed model on abstractive text summarization and data-to-text "},"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":"1904.04428","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-09T02:34:30Z","cross_cats_sorted":[],"title_canon_sha256":"1b33b5b95a620dbf09e40d61d055a8901650c40d2ff63ef471cea89c9bd99b71","abstract_canon_sha256":"7bc5bd6968f7d6043f754aa7c322f9753b79f0ee6f827999689194e3f3c1eb24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:49.856377Z","signature_b64":"SGnDUsKwuunItti/deCCXdkbaBcqlmqE4+vF9slQY54gtPtpl9vp2r+VyqlZhuKTOufUqE04DMCqQ1GLdKA4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb76640141b88900046595499e3f50b5443019c5d89afac6ce1abd780b6beb7c","last_reissued_at":"2026-05-17T23:48:49.855785Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:49.855785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text Generation with Exemplar-based Adaptive Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ankur P. Parikh, Bhuwan Dhingra, Dipanjan Das, Hao Peng, Manaal Faruqui","submitted_at":"2019-04-09T02:34:30Z","abstract_excerpt":"We propose a novel conditioned text generation model. It draws inspiration from traditional template-based text generation techniques, where the source provides the content (i.e., what to say), and the template influences how to say it. Building on the successful encoder-decoder paradigm, it first encodes the content representation from the given input text; to produce the output, it retrieves exemplar text from the training data as \"soft templates,\" which are then used to construct an exemplar-specific decoder. We evaluate the proposed model on abstractive text summarization and data-to-text "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04428","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":"1904.04428","created_at":"2026-05-17T23:48:49.855900+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.04428v2","created_at":"2026-05-17T23:48:49.855900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04428","created_at":"2026-05-17T23:48:49.855900+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2303.09014","citing_title":"ART: Automatic multi-step reasoning and tool-use for large language models","ref_index":121,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5N3GIAKBXCEQABDFSVEZ4P2QWV","json":"https://pith.science/pith/5N3GIAKBXCEQABDFSVEZ4P2QWV.json","graph_json":"https://pith.science/api/pith-number/5N3GIAKBXCEQABDFSVEZ4P2QWV/graph.json","events_json":"https://pith.science/api/pith-number/5N3GIAKBXCEQABDFSVEZ4P2QWV/events.json","paper":"https://pith.science/paper/5N3GIAKB"},"agent_actions":{"view_html":"https://pith.science/pith/5N3GIAKBXCEQABDFSVEZ4P2QWV","download_json":"https://pith.science/pith/5N3GIAKBXCEQABDFSVEZ4P2QWV.json","view_paper":"https://pith.science/paper/5N3GIAKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.04428&json=true","fetch_graph":"https://pith.science/api/pith-number/5N3GIAKBXCEQABDFSVEZ4P2QWV/graph.json","fetch_events":"https://pith.science/api/pith-number/5N3GIAKBXCEQABDFSVEZ4P2QWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5N3GIAKBXCEQABDFSVEZ4P2QWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5N3GIAKBXCEQABDFSVEZ4P2QWV/action/storage_attestation","attest_author":"https://pith.science/pith/5N3GIAKBXCEQABDFSVEZ4P2QWV/action/author_attestation","sign_citation":"https://pith.science/pith/5N3GIAKBXCEQABDFSVEZ4P2QWV/action/citation_signature","submit_replication":"https://pith.science/pith/5N3GIAKBXCEQABDFSVEZ4P2QWV/action/replication_record"}},"created_at":"2026-05-17T23:48:49.855900+00:00","updated_at":"2026-05-17T23:48:49.855900+00:00"}