{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3QEXGUC7GRHBPU7TVM2ZM5YH5F","short_pith_number":"pith:3QEXGUC7","schema_version":"1.0","canonical_sha256":"dc0973505f344e17d3f3ab35967707e97076c5d92233b2a4694200d7afbf4865","source":{"kind":"arxiv","id":"2105.11174","version":1},"attestation_state":"computed","paper":{"title":"Retrieval Enhanced Model for Commonsense Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Han Wang, Linjun Shou, Michael Zeng, Ming Gong, Yang Liu, Yichong Xu","submitted_at":"2021-05-24T09:49:17Z","abstract_excerpt":"Commonsense generation is a challenging task of generating a plausible sentence describing an everyday scenario using provided concepts. Its requirement of reasoning over commonsense knowledge and compositional generalization ability even puzzles strong pre-trained language generation models. We propose a novel framework using retrieval methods to enhance both the pre-training and fine-tuning for commonsense generation. We retrieve prototype sentence candidates by concept matching and use them as auxiliary input. For fine-tuning, we further boost its performance with a trainable sentence retri"},"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":"2105.11174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T09:49:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07448857e4699d2c8f32823065ec18d06435488e856fd882ec94e3e77abb0406","abstract_canon_sha256":"b65a227d08858f8faa70bb132bad0708ddcf0759848236a0446f59f0c7f04ca4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:36.106897Z","signature_b64":"+BJBp9jgsf+QFSKJSLW2mjZfulV7THovQPiSwDGa5hfJsdkeEVH+yqQ5VHefZfkQYuQ+CVQBRTshSe3clgV6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc0973505f344e17d3f3ab35967707e97076c5d92233b2a4694200d7afbf4865","last_reissued_at":"2026-07-05T02:42:36.106460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:36.106460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval Enhanced Model for Commonsense Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Han Wang, Linjun Shou, Michael Zeng, Ming Gong, Yang Liu, Yichong Xu","submitted_at":"2021-05-24T09:49:17Z","abstract_excerpt":"Commonsense generation is a challenging task of generating a plausible sentence describing an everyday scenario using provided concepts. Its requirement of reasoning over commonsense knowledge and compositional generalization ability even puzzles strong pre-trained language generation models. We propose a novel framework using retrieval methods to enhance both the pre-training and fine-tuning for commonsense generation. We retrieve prototype sentence candidates by concept matching and use them as auxiliary input. For fine-tuning, we further boost its performance with a trainable sentence retri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11174","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/2105.11174/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":"2105.11174","created_at":"2026-07-05T02:42:36.106515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.11174v1","created_at":"2026-07-05T02:42:36.106515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11174","created_at":"2026-07-05T02:42:36.106515+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QEXGUC7GRHB","created_at":"2026-07-05T02:42:36.106515+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QEXGUC7GRHBPU7T","created_at":"2026-07-05T02:42:36.106515+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QEXGUC7","created_at":"2026-07-05T02:42:36.106515+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/3QEXGUC7GRHBPU7TVM2ZM5YH5F","json":"https://pith.science/pith/3QEXGUC7GRHBPU7TVM2ZM5YH5F.json","graph_json":"https://pith.science/api/pith-number/3QEXGUC7GRHBPU7TVM2ZM5YH5F/graph.json","events_json":"https://pith.science/api/pith-number/3QEXGUC7GRHBPU7TVM2ZM5YH5F/events.json","paper":"https://pith.science/paper/3QEXGUC7"},"agent_actions":{"view_html":"https://pith.science/pith/3QEXGUC7GRHBPU7TVM2ZM5YH5F","download_json":"https://pith.science/pith/3QEXGUC7GRHBPU7TVM2ZM5YH5F.json","view_paper":"https://pith.science/paper/3QEXGUC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.11174&json=true","fetch_graph":"https://pith.science/api/pith-number/3QEXGUC7GRHBPU7TVM2ZM5YH5F/graph.json","fetch_events":"https://pith.science/api/pith-number/3QEXGUC7GRHBPU7TVM2ZM5YH5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QEXGUC7GRHBPU7TVM2ZM5YH5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QEXGUC7GRHBPU7TVM2ZM5YH5F/action/storage_attestation","attest_author":"https://pith.science/pith/3QEXGUC7GRHBPU7TVM2ZM5YH5F/action/author_attestation","sign_citation":"https://pith.science/pith/3QEXGUC7GRHBPU7TVM2ZM5YH5F/action/citation_signature","submit_replication":"https://pith.science/pith/3QEXGUC7GRHBPU7TVM2ZM5YH5F/action/replication_record"}},"created_at":"2026-07-05T02:42:36.106515+00:00","updated_at":"2026-07-05T02:42:36.106515+00:00"}