{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UI4KOKLNR3TMCVZZZQPWHYOLEB","short_pith_number":"pith:UI4KOKLN","schema_version":"1.0","canonical_sha256":"a238a7296d8ee6c15739cc1f63e1cb20791fe83095ac476e2e8bde202d08236f","source":{"kind":"arxiv","id":"2009.09796","version":1},"attestation_state":"computed","paper":{"title":"Multi-Task Learning with Deep Neural Networks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael Crawshaw","submitted_at":"2020-09-10T19:31:04Z","abstract_excerpt":"Multi-task learning (MTL) is a subfield of machine learning in which multiple tasks are simultaneously learned by a shared model. Such approaches offer advantages like improved data efficiency, reduced overfitting through shared representations, and fast learning by leveraging auxiliary information. However, the simultaneous learning of multiple tasks presents new design and optimization challenges, and choosing which tasks should be learned jointly is in itself a non-trivial problem. In this survey, we give an overview of multi-task learning methods for deep neural networks, with the aim of s"},"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":"2009.09796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T19:31:04Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"0841385ad0a9b7e69f970fd3c0bd94a22e7a32172fa93eae99bd8a205fc61729","abstract_canon_sha256":"edcdc4c28f73b3a2d79619ab220ef84f04689d2db28725d9c85742cb0713be2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:53.058421Z","signature_b64":"o2fj2yITNnnA2qdKmDGRHFAxt31iQKoqzkE3+uIArcnZq0XQC/3I4xPjz0Yqvjp6QK/05DBob7uDguYVe/3LAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a238a7296d8ee6c15739cc1f63e1cb20791fe83095ac476e2e8bde202d08236f","last_reissued_at":"2026-07-05T01:36:53.058035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:53.058035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Learning with Deep Neural Networks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael Crawshaw","submitted_at":"2020-09-10T19:31:04Z","abstract_excerpt":"Multi-task learning (MTL) is a subfield of machine learning in which multiple tasks are simultaneously learned by a shared model. Such approaches offer advantages like improved data efficiency, reduced overfitting through shared representations, and fast learning by leveraging auxiliary information. However, the simultaneous learning of multiple tasks presents new design and optimization challenges, and choosing which tasks should be learned jointly is in itself a non-trivial problem. In this survey, we give an overview of multi-task learning methods for deep neural networks, with the aim of s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09796","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/2009.09796/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":"2009.09796","created_at":"2026-07-05T01:36:53.058100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.09796v1","created_at":"2026-07-05T01:36:53.058100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09796","created_at":"2026-07-05T01:36:53.058100+00:00"},{"alias_kind":"pith_short_12","alias_value":"UI4KOKLNR3TM","created_at":"2026-07-05T01:36:53.058100+00:00"},{"alias_kind":"pith_short_16","alias_value":"UI4KOKLNR3TMCVZZ","created_at":"2026-07-05T01:36:53.058100+00:00"},{"alias_kind":"pith_short_8","alias_value":"UI4KOKLN","created_at":"2026-07-05T01:36:53.058100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26634","citing_title":"Temporally Consistent Label Interpolation for Robust Surgical Multi-Task Learning under Challenging Conditions","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23919","citing_title":"Unified Multi-Task Relevance Modeling for E-Commerce: Comparing Task Routing Architectures Across LLMs and Cross-Encoders","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18453","citing_title":"LLM Parameters for Math Across Languages: Shared or Separate?","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11508","citing_title":"Probabilistic Contrastive Pretraining for Multi-task ADME Property Prediction","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01557","citing_title":"Everywhere Learning: Artificial Intelligence with Pointwise Constraints","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14938","citing_title":"Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04000","citing_title":"SPLIT-PINN: Separable Probability Learning Technique via Physics-Informed Neural Networks for High-Dimensional Probabilistic Modeling","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30370","citing_title":"MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2512.19184","citing_title":"Operator-Based Generalization Bound for Deep Learning: Insights on Multi-Task Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18074","citing_title":"4DLidarOpen: An Open 4D FMCW Lidar Dataset for Motion-Aware Autonomous Driving","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2509.19602","citing_title":"Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2511.04320","citing_title":"MacroNav: Multi-Task Context Representation Learning Enables Efficient Navigation in Unknown Environments","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2502.21074","citing_title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00050","citing_title":"Task-Centric Personalized Federated Fine-Tuning of Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16914","citing_title":"Unified Ultrasound Intelligence Toward an End-to-End Agentic System","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UI4KOKLNR3TMCVZZZQPWHYOLEB","json":"https://pith.science/pith/UI4KOKLNR3TMCVZZZQPWHYOLEB.json","graph_json":"https://pith.science/api/pith-number/UI4KOKLNR3TMCVZZZQPWHYOLEB/graph.json","events_json":"https://pith.science/api/pith-number/UI4KOKLNR3TMCVZZZQPWHYOLEB/events.json","paper":"https://pith.science/paper/UI4KOKLN"},"agent_actions":{"view_html":"https://pith.science/pith/UI4KOKLNR3TMCVZZZQPWHYOLEB","download_json":"https://pith.science/pith/UI4KOKLNR3TMCVZZZQPWHYOLEB.json","view_paper":"https://pith.science/paper/UI4KOKLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.09796&json=true","fetch_graph":"https://pith.science/api/pith-number/UI4KOKLNR3TMCVZZZQPWHYOLEB/graph.json","fetch_events":"https://pith.science/api/pith-number/UI4KOKLNR3TMCVZZZQPWHYOLEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UI4KOKLNR3TMCVZZZQPWHYOLEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UI4KOKLNR3TMCVZZZQPWHYOLEB/action/storage_attestation","attest_author":"https://pith.science/pith/UI4KOKLNR3TMCVZZZQPWHYOLEB/action/author_attestation","sign_citation":"https://pith.science/pith/UI4KOKLNR3TMCVZZZQPWHYOLEB/action/citation_signature","submit_replication":"https://pith.science/pith/UI4KOKLNR3TMCVZZZQPWHYOLEB/action/replication_record"}},"created_at":"2026-07-05T01:36:53.058100+00:00","updated_at":"2026-07-05T01:36:53.058100+00:00"}