{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UICPL3IMDA2GYP6PPGW7NF2PV5","short_pith_number":"pith:UICPL3IM","schema_version":"1.0","canonical_sha256":"a204f5ed0c18346c3fcf79adf6974faf5afba9cf9b8285ad3f46397178ed27d0","source":{"kind":"arxiv","id":"2009.09139","version":3},"attestation_state":"computed","paper":{"title":"Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amine Elhattami, Christopher Pal, Jonathan Pilault","submitted_at":"2020-09-19T02:04:34Z","abstract_excerpt":"Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MTL must deal with challenges such as: overfitting to low resource tasks, catastrophic forgetting, and negative task transfer, or learning interference. Often, in Natural Language Processing (NLP), a separate model per task is needed to obtain the best performance. However, many fine-tuning approaches are both parameter inefficient, i.e., potentially involving one new model per task, and highly susceptible to losing knowledge acquired during pretraining. We "},"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":"2009.09139","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-09-19T02:04:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4184426ade87651aa0ce9861db71c2b07a794bf93741bd320001e0caba9f63a7","abstract_canon_sha256":"55ce4b0131e0b531340b70893c93f5231c1f5c71d95c480b8b20c505daed4556"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:34.498903Z","signature_b64":"Dx1CbdKFsBqznf9zkGiwJJp949HNk4/5syrY+6PlF5iNNYu2CEtdymZ5Ja2g+TqEvyNN7e4NUR6qiSWs8xgfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a204f5ed0c18346c3fcf79adf6974faf5afba9cf9b8285ad3f46397178ed27d0","last_reissued_at":"2026-07-05T04:16:34.498410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:34.498410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amine Elhattami, Christopher Pal, Jonathan Pilault","submitted_at":"2020-09-19T02:04:34Z","abstract_excerpt":"Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MTL must deal with challenges such as: overfitting to low resource tasks, catastrophic forgetting, and negative task transfer, or learning interference. Often, in Natural Language Processing (NLP), a separate model per task is needed to obtain the best performance. However, many fine-tuning approaches are both parameter inefficient, i.e., potentially involving one new model per task, and highly susceptible to losing knowledge acquired during pretraining. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09139","kind":"arxiv","version":3},"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/2009.09139/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":"2009.09139","created_at":"2026-07-05T04:16:34.498471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.09139v3","created_at":"2026-07-05T04:16:34.498471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09139","created_at":"2026-07-05T04:16:34.498471+00:00"},{"alias_kind":"pith_short_12","alias_value":"UICPL3IMDA2G","created_at":"2026-07-05T04:16:34.498471+00:00"},{"alias_kind":"pith_short_16","alias_value":"UICPL3IMDA2GYP6P","created_at":"2026-07-05T04:16:34.498471+00:00"},{"alias_kind":"pith_short_8","alias_value":"UICPL3IM","created_at":"2026-07-05T04:16:34.498471+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/UICPL3IMDA2GYP6PPGW7NF2PV5","json":"https://pith.science/pith/UICPL3IMDA2GYP6PPGW7NF2PV5.json","graph_json":"https://pith.science/api/pith-number/UICPL3IMDA2GYP6PPGW7NF2PV5/graph.json","events_json":"https://pith.science/api/pith-number/UICPL3IMDA2GYP6PPGW7NF2PV5/events.json","paper":"https://pith.science/paper/UICPL3IM"},"agent_actions":{"view_html":"https://pith.science/pith/UICPL3IMDA2GYP6PPGW7NF2PV5","download_json":"https://pith.science/pith/UICPL3IMDA2GYP6PPGW7NF2PV5.json","view_paper":"https://pith.science/paper/UICPL3IM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.09139&json=true","fetch_graph":"https://pith.science/api/pith-number/UICPL3IMDA2GYP6PPGW7NF2PV5/graph.json","fetch_events":"https://pith.science/api/pith-number/UICPL3IMDA2GYP6PPGW7NF2PV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UICPL3IMDA2GYP6PPGW7NF2PV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UICPL3IMDA2GYP6PPGW7NF2PV5/action/storage_attestation","attest_author":"https://pith.science/pith/UICPL3IMDA2GYP6PPGW7NF2PV5/action/author_attestation","sign_citation":"https://pith.science/pith/UICPL3IMDA2GYP6PPGW7NF2PV5/action/citation_signature","submit_replication":"https://pith.science/pith/UICPL3IMDA2GYP6PPGW7NF2PV5/action/replication_record"}},"created_at":"2026-07-05T04:16:34.498471+00:00","updated_at":"2026-07-05T04:16:34.498471+00:00"}