{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G5MFCW6DZYG2EAOTAVTD5SZMJW","short_pith_number":"pith:G5MFCW6D","schema_version":"1.0","canonical_sha256":"3758515bc3ce0da201d305663ecb2c4da50401f3cbb330c3446c13fa6197a6a1","source":{"kind":"arxiv","id":"2406.18038","version":6},"attestation_state":"computed","paper":{"title":"MT2ST: Adaptive Multi-Task to Single-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dong Liu, Yanxuan Yu","submitted_at":"2024-06-26T03:12:07Z","abstract_excerpt":"Efficient machine learning (ML) has become increasingly important as models grow larger and data volumes expand. In this work, we address the trade-off between generalization in multi-task learning (MTL) and precision in single-task learning (STL) by introducing the Multi-Task to Single-Task (MT2ST) framework. MT2ST is designed to enhance training efficiency and accuracy in multi-modal tasks, showcasing its value as a practical application of efficient ML."},"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":"2406.18038","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T03:12:07Z","cross_cats_sorted":[],"title_canon_sha256":"9ca93c06fcc068f27dc945fe63351a00d35dfe70724f220b0b91a015ba68a803","abstract_canon_sha256":"260fbaa5fffa3e401f5589e65bc563162775172490665c2641e2823c93709646"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:33.493583Z","signature_b64":"5/cDWo5KNqPs+rm6tdTA5VoltSRzoXPvHyBAce8X1c3/JYplNriOOSmrqI9kT51UgNMPItjgZgj4wAjwC2JLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3758515bc3ce0da201d305663ecb2c4da50401f3cbb330c3446c13fa6197a6a1","last_reissued_at":"2026-07-05T10:56:33.493059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:33.493059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MT2ST: Adaptive Multi-Task to Single-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dong Liu, Yanxuan Yu","submitted_at":"2024-06-26T03:12:07Z","abstract_excerpt":"Efficient machine learning (ML) has become increasingly important as models grow larger and data volumes expand. In this work, we address the trade-off between generalization in multi-task learning (MTL) and precision in single-task learning (STL) by introducing the Multi-Task to Single-Task (MT2ST) framework. MT2ST is designed to enhance training efficiency and accuracy in multi-modal tasks, showcasing its value as a practical application of efficient ML."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18038","kind":"arxiv","version":6},"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/2406.18038/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":"2406.18038","created_at":"2026-07-05T10:56:33.493128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18038v6","created_at":"2026-07-05T10:56:33.493128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18038","created_at":"2026-07-05T10:56:33.493128+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5MFCW6DZYG2","created_at":"2026-07-05T10:56:33.493128+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5MFCW6DZYG2EAOT","created_at":"2026-07-05T10:56:33.493128+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5MFCW6D","created_at":"2026-07-05T10:56:33.493128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17900","citing_title":"Leveraging Large Language Model for Intelligent Log Processing and Autonomous Debugging in Cloud AI Platforms","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5MFCW6DZYG2EAOTAVTD5SZMJW","json":"https://pith.science/pith/G5MFCW6DZYG2EAOTAVTD5SZMJW.json","graph_json":"https://pith.science/api/pith-number/G5MFCW6DZYG2EAOTAVTD5SZMJW/graph.json","events_json":"https://pith.science/api/pith-number/G5MFCW6DZYG2EAOTAVTD5SZMJW/events.json","paper":"https://pith.science/paper/G5MFCW6D"},"agent_actions":{"view_html":"https://pith.science/pith/G5MFCW6DZYG2EAOTAVTD5SZMJW","download_json":"https://pith.science/pith/G5MFCW6DZYG2EAOTAVTD5SZMJW.json","view_paper":"https://pith.science/paper/G5MFCW6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18038&json=true","fetch_graph":"https://pith.science/api/pith-number/G5MFCW6DZYG2EAOTAVTD5SZMJW/graph.json","fetch_events":"https://pith.science/api/pith-number/G5MFCW6DZYG2EAOTAVTD5SZMJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5MFCW6DZYG2EAOTAVTD5SZMJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5MFCW6DZYG2EAOTAVTD5SZMJW/action/storage_attestation","attest_author":"https://pith.science/pith/G5MFCW6DZYG2EAOTAVTD5SZMJW/action/author_attestation","sign_citation":"https://pith.science/pith/G5MFCW6DZYG2EAOTAVTD5SZMJW/action/citation_signature","submit_replication":"https://pith.science/pith/G5MFCW6DZYG2EAOTAVTD5SZMJW/action/replication_record"}},"created_at":"2026-07-05T10:56:33.493128+00:00","updated_at":"2026-07-05T10:56:33.493128+00:00"}