{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DEYZUYGVEFTBCP3MPEDGPJLED6","short_pith_number":"pith:DEYZUYGV","schema_version":"1.0","canonical_sha256":"19319a60d52166113f6c790667a5641fbf5fb4c4c94cf5b82aff534c092adb6d","source":{"kind":"arxiv","id":"2107.02968","version":2},"attestation_state":"computed","paper":{"title":"Deep Extrapolation for Attribute-Enhanced Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Ali Madani, Alvin Chan, Ben Krause, Nikhil Naik","submitted_at":"2021-07-07T01:30:36Z","abstract_excerpt":"Attribute extrapolation in sample generation is challenging for deep neural networks operating beyond the training distribution. We formulate a new task for extrapolation in sequence generation, focusing on natural language and proteins, and propose GENhance, a generative framework that enhances attributes through a learned latent space. Trained on movie reviews and a computed protein stability dataset, GENhance can generate strongly-positive text reviews and highly stable protein sequences without being exposed to similar data during training. We release our benchmark tasks and models to cont"},"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":"2107.02968","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-07T01:30:36Z","cross_cats_sorted":["cs.CL","q-bio.QM"],"title_canon_sha256":"b85f0b7f5ab00afc2119548e4e8b53fc9b1f5bf4fabe2a6817ccd1f86ec6b4c4","abstract_canon_sha256":"2a7c650ccaf27f75830910ab5d023564fdf274f5a5b95134fe9b47ef4ef9656a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:32.989667Z","signature_b64":"x+KnNaavzZPzxwFOIbCTlRNW337pwwtNsMI/xeFAN8VeAR+rl5n9sipxl+bjkjLdDyLePL5twz3lS2Gpl0PgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19319a60d52166113f6c790667a5641fbf5fb4c4c94cf5b82aff534c092adb6d","last_reissued_at":"2026-07-05T03:25:32.989194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:32.989194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Extrapolation for Attribute-Enhanced Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Ali Madani, Alvin Chan, Ben Krause, Nikhil Naik","submitted_at":"2021-07-07T01:30:36Z","abstract_excerpt":"Attribute extrapolation in sample generation is challenging for deep neural networks operating beyond the training distribution. We formulate a new task for extrapolation in sequence generation, focusing on natural language and proteins, and propose GENhance, a generative framework that enhances attributes through a learned latent space. Trained on movie reviews and a computed protein stability dataset, GENhance can generate strongly-positive text reviews and highly stable protein sequences without being exposed to similar data during training. We release our benchmark tasks and models to cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02968","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/2107.02968/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":"2107.02968","created_at":"2026-07-05T03:25:32.989250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.02968v2","created_at":"2026-07-05T03:25:32.989250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02968","created_at":"2026-07-05T03:25:32.989250+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEYZUYGVEFTB","created_at":"2026-07-05T03:25:32.989250+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEYZUYGVEFTBCP3M","created_at":"2026-07-05T03:25:32.989250+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEYZUYGV","created_at":"2026-07-05T03:25:32.989250+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/DEYZUYGVEFTBCP3MPEDGPJLED6","json":"https://pith.science/pith/DEYZUYGVEFTBCP3MPEDGPJLED6.json","graph_json":"https://pith.science/api/pith-number/DEYZUYGVEFTBCP3MPEDGPJLED6/graph.json","events_json":"https://pith.science/api/pith-number/DEYZUYGVEFTBCP3MPEDGPJLED6/events.json","paper":"https://pith.science/paper/DEYZUYGV"},"agent_actions":{"view_html":"https://pith.science/pith/DEYZUYGVEFTBCP3MPEDGPJLED6","download_json":"https://pith.science/pith/DEYZUYGVEFTBCP3MPEDGPJLED6.json","view_paper":"https://pith.science/paper/DEYZUYGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.02968&json=true","fetch_graph":"https://pith.science/api/pith-number/DEYZUYGVEFTBCP3MPEDGPJLED6/graph.json","fetch_events":"https://pith.science/api/pith-number/DEYZUYGVEFTBCP3MPEDGPJLED6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEYZUYGVEFTBCP3MPEDGPJLED6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEYZUYGVEFTBCP3MPEDGPJLED6/action/storage_attestation","attest_author":"https://pith.science/pith/DEYZUYGVEFTBCP3MPEDGPJLED6/action/author_attestation","sign_citation":"https://pith.science/pith/DEYZUYGVEFTBCP3MPEDGPJLED6/action/citation_signature","submit_replication":"https://pith.science/pith/DEYZUYGVEFTBCP3MPEDGPJLED6/action/replication_record"}},"created_at":"2026-07-05T03:25:32.989250+00:00","updated_at":"2026-07-05T03:25:32.989250+00:00"}