{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3MQ5ZTAMMSVNWMX2MKHSBWQ66Z","short_pith_number":"pith:3MQ5ZTAM","schema_version":"1.0","canonical_sha256":"db21dccc0c64aadb32fa628f20da1ef66d2b4a949046e954cceb0b356d608041","source":{"kind":"arxiv","id":"2101.00420","version":2},"attestation_state":"computed","paper":{"title":"Learning to Generate Task-Specific Adapters from Task Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Qinyuan Ye, Xiang Ren","submitted_at":"2021-01-02T10:50:23Z","abstract_excerpt":"Pre-trained text-to-text transformers such as BART have achieved impressive performance across a range of NLP tasks. Recent study further shows that they can learn to generalize to novel tasks, by including task descriptions as part of the source sequence and training the model with (source, target) examples. At test time, these fine-tuned models can make inferences on new tasks using the new task descriptions as part of the input. However, this approach has potential limitations, as the model learns to solve individual (source, target) examples (i.e., at the instance level), instead of learni"},"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":"2101.00420","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T10:50:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6174e984c961cacd585e0fb4a48a2a166a0752868000c18bfa24dacc0fb80641","abstract_canon_sha256":"42c15939f86bb0e195522c8c9f66b3037cef76f965e5f2a7d3994536bf11edd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:22.919752Z","signature_b64":"UmXJh23OM7hIigo70veP4Nka+B55GydubL3AeX+inSiVHUclgCMSeBZwdTD7TCM7BL5u2r7QPso2tejzftTxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db21dccc0c64aadb32fa628f20da1ef66d2b4a949046e954cceb0b356d608041","last_reissued_at":"2026-07-05T02:49:22.919264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:22.919264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Generate Task-Specific Adapters from Task Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Qinyuan Ye, Xiang Ren","submitted_at":"2021-01-02T10:50:23Z","abstract_excerpt":"Pre-trained text-to-text transformers such as BART have achieved impressive performance across a range of NLP tasks. Recent study further shows that they can learn to generalize to novel tasks, by including task descriptions as part of the source sequence and training the model with (source, target) examples. At test time, these fine-tuned models can make inferences on new tasks using the new task descriptions as part of the input. However, this approach has potential limitations, as the model learns to solve individual (source, target) examples (i.e., at the instance level), instead of learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00420","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/2101.00420/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":"2101.00420","created_at":"2026-07-05T02:49:22.919328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.00420v2","created_at":"2026-07-05T02:49:22.919328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00420","created_at":"2026-07-05T02:49:22.919328+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MQ5ZTAMMSVN","created_at":"2026-07-05T02:49:22.919328+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MQ5ZTAMMSVNWMX2","created_at":"2026-07-05T02:49:22.919328+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MQ5ZTAM","created_at":"2026-07-05T02:49:22.919328+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2104.08773","citing_title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","ref_index":111,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z","json":"https://pith.science/pith/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z.json","graph_json":"https://pith.science/api/pith-number/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z/graph.json","events_json":"https://pith.science/api/pith-number/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z/events.json","paper":"https://pith.science/paper/3MQ5ZTAM"},"agent_actions":{"view_html":"https://pith.science/pith/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z","download_json":"https://pith.science/pith/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z.json","view_paper":"https://pith.science/paper/3MQ5ZTAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.00420&json=true","fetch_graph":"https://pith.science/api/pith-number/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z/graph.json","fetch_events":"https://pith.science/api/pith-number/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z/action/storage_attestation","attest_author":"https://pith.science/pith/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z/action/author_attestation","sign_citation":"https://pith.science/pith/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z/action/citation_signature","submit_replication":"https://pith.science/pith/3MQ5ZTAMMSVNWMX2MKHSBWQ66Z/action/replication_record"}},"created_at":"2026-07-05T02:49:22.919328+00:00","updated_at":"2026-07-05T02:49:22.919328+00:00"}