{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DALGF4DGS3GRXSENKXV27VWHHQ","short_pith_number":"pith:DALGF4DG","schema_version":"1.0","canonical_sha256":"181662f06696cd1bc88d55ebafd6c73c39453b89c3bf1652fdd736fdcd21e503","source":{"kind":"arxiv","id":"2403.20320","version":1},"attestation_state":"computed","paper":{"title":"MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ahmed Agiza, Marina Neseem, Sherief Reda","submitted_at":"2024-03-29T17:43:58Z","abstract_excerpt":"Adapting models pre-trained on large-scale datasets to a variety of downstream tasks is a common strategy in deep learning. Consequently, parameter-efficient fine-tuning methods have emerged as a promising way to adapt pre-trained models to different tasks while training only a minimal number of parameters. While most of these methods are designed for single-task adaptation, parameter-efficient training in Multi-Task Learning (MTL) architectures is still unexplored. In this paper, we introduce MTLoRA, a novel framework for parameter-efficient training of MTL models. MTLoRA employs Task-Agnosti"},"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":"2403.20320","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T17:43:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fea267514725524d4cb7a94a5e234063009df6cfe8a2b92a8eca6cca94a5cdf2","abstract_canon_sha256":"36efa97764444ed2915fdc030e3b52b68b8d54011b828bc4a03b6fb7fb21e1b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:17.634902Z","signature_b64":"kbXN4zgs+MdDlSU024k8Qnh60x5mZUovmSum6sPKuBrg3ZuTFmz6/Vws+RI0cEEfE3JJMpIRVAc67mt+lcmWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"181662f06696cd1bc88d55ebafd6c73c39453b89c3bf1652fdd736fdcd21e503","last_reissued_at":"2026-07-05T08:02:17.634486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:17.634486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ahmed Agiza, Marina Neseem, Sherief Reda","submitted_at":"2024-03-29T17:43:58Z","abstract_excerpt":"Adapting models pre-trained on large-scale datasets to a variety of downstream tasks is a common strategy in deep learning. Consequently, parameter-efficient fine-tuning methods have emerged as a promising way to adapt pre-trained models to different tasks while training only a minimal number of parameters. While most of these methods are designed for single-task adaptation, parameter-efficient training in Multi-Task Learning (MTL) architectures is still unexplored. In this paper, we introduce MTLoRA, a novel framework for parameter-efficient training of MTL models. MTLoRA employs Task-Agnosti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20320","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/2403.20320/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":"2403.20320","created_at":"2026-07-05T08:02:17.634537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.20320v1","created_at":"2026-07-05T08:02:17.634537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20320","created_at":"2026-07-05T08:02:17.634537+00:00"},{"alias_kind":"pith_short_12","alias_value":"DALGF4DGS3GR","created_at":"2026-07-05T08:02:17.634537+00:00"},{"alias_kind":"pith_short_16","alias_value":"DALGF4DGS3GRXSEN","created_at":"2026-07-05T08:02:17.634537+00:00"},{"alias_kind":"pith_short_8","alias_value":"DALGF4DG","created_at":"2026-07-05T08:02:17.634537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00125","citing_title":"Efficient Learning Content Retrieval with Knowledge Injection","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DALGF4DGS3GRXSENKXV27VWHHQ","json":"https://pith.science/pith/DALGF4DGS3GRXSENKXV27VWHHQ.json","graph_json":"https://pith.science/api/pith-number/DALGF4DGS3GRXSENKXV27VWHHQ/graph.json","events_json":"https://pith.science/api/pith-number/DALGF4DGS3GRXSENKXV27VWHHQ/events.json","paper":"https://pith.science/paper/DALGF4DG"},"agent_actions":{"view_html":"https://pith.science/pith/DALGF4DGS3GRXSENKXV27VWHHQ","download_json":"https://pith.science/pith/DALGF4DGS3GRXSENKXV27VWHHQ.json","view_paper":"https://pith.science/paper/DALGF4DG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.20320&json=true","fetch_graph":"https://pith.science/api/pith-number/DALGF4DGS3GRXSENKXV27VWHHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DALGF4DGS3GRXSENKXV27VWHHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DALGF4DGS3GRXSENKXV27VWHHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DALGF4DGS3GRXSENKXV27VWHHQ/action/storage_attestation","attest_author":"https://pith.science/pith/DALGF4DGS3GRXSENKXV27VWHHQ/action/author_attestation","sign_citation":"https://pith.science/pith/DALGF4DGS3GRXSENKXV27VWHHQ/action/citation_signature","submit_replication":"https://pith.science/pith/DALGF4DGS3GRXSENKXV27VWHHQ/action/replication_record"}},"created_at":"2026-07-05T08:02:17.634537+00:00","updated_at":"2026-07-05T08:02:17.634537+00:00"}