{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RXRZHVYDWWZO5HRIYBJ6QXDVRH","short_pith_number":"pith:RXRZHVYD","schema_version":"1.0","canonical_sha256":"8de393d703b5b2ee9e28c053e85c7589ff01eb1ac6f859f32764df2e245c2cf5","source":{"kind":"arxiv","id":"2406.03048","version":2},"attestation_state":"computed","paper":{"title":"Giving each task what it needs -- leveraging structured sparsity for tailored multi-task learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Marcus Liwicki, Rajkumar Saini, Richa Upadhyay, Ronald Phlypo","submitted_at":"2024-06-05T08:23:38Z","abstract_excerpt":"In the Multi-task Learning (MTL) framework, every task demands distinct feature representations, ranging from low-level to high-level attributes. It is vital to address the specific (feature/parameter) needs of each task, especially in computationally constrained environments. This work, therefore, introduces Layer-Optimized Multi-Task (LOMT) models that utilize structured sparsity to refine feature selection for individual tasks and enhance the performance of all tasks in a multi-task scenario. Structured or group sparsity systematically eliminates parameters from trivial channels and, someti"},"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":"2406.03048","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T08:23:38Z","cross_cats_sorted":[],"title_canon_sha256":"1ce88c1fb3981a7991eee3d4751713cdbf67e365f0a73b0b9b91b5bf8a6e0835","abstract_canon_sha256":"697a3d426d09bfb31c557790a3f25571052578ac619dfb0c7652895094967454"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:21.045093Z","signature_b64":"rA4SLpdqhgtSotVDowE79kDsgMRegvAfG4Fs/BzQnx6TToWh6YIBrrHSMGsIlMHdrahVwUfKRUJXR5/9WAbjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8de393d703b5b2ee9e28c053e85c7589ff01eb1ac6f859f32764df2e245c2cf5","last_reissued_at":"2026-07-05T09:03:21.044586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:21.044586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Giving each task what it needs -- leveraging structured sparsity for tailored multi-task learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Marcus Liwicki, Rajkumar Saini, Richa Upadhyay, Ronald Phlypo","submitted_at":"2024-06-05T08:23:38Z","abstract_excerpt":"In the Multi-task Learning (MTL) framework, every task demands distinct feature representations, ranging from low-level to high-level attributes. It is vital to address the specific (feature/parameter) needs of each task, especially in computationally constrained environments. This work, therefore, introduces Layer-Optimized Multi-Task (LOMT) models that utilize structured sparsity to refine feature selection for individual tasks and enhance the performance of all tasks in a multi-task scenario. Structured or group sparsity systematically eliminates parameters from trivial channels and, someti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03048","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/2406.03048/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":"2406.03048","created_at":"2026-07-05T09:03:21.044646+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03048v2","created_at":"2026-07-05T09:03:21.044646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03048","created_at":"2026-07-05T09:03:21.044646+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXRZHVYDWWZO","created_at":"2026-07-05T09:03:21.044646+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXRZHVYDWWZO5HRI","created_at":"2026-07-05T09:03:21.044646+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXRZHVYD","created_at":"2026-07-05T09:03:21.044646+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/RXRZHVYDWWZO5HRIYBJ6QXDVRH","json":"https://pith.science/pith/RXRZHVYDWWZO5HRIYBJ6QXDVRH.json","graph_json":"https://pith.science/api/pith-number/RXRZHVYDWWZO5HRIYBJ6QXDVRH/graph.json","events_json":"https://pith.science/api/pith-number/RXRZHVYDWWZO5HRIYBJ6QXDVRH/events.json","paper":"https://pith.science/paper/RXRZHVYD"},"agent_actions":{"view_html":"https://pith.science/pith/RXRZHVYDWWZO5HRIYBJ6QXDVRH","download_json":"https://pith.science/pith/RXRZHVYDWWZO5HRIYBJ6QXDVRH.json","view_paper":"https://pith.science/paper/RXRZHVYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03048&json=true","fetch_graph":"https://pith.science/api/pith-number/RXRZHVYDWWZO5HRIYBJ6QXDVRH/graph.json","fetch_events":"https://pith.science/api/pith-number/RXRZHVYDWWZO5HRIYBJ6QXDVRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXRZHVYDWWZO5HRIYBJ6QXDVRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXRZHVYDWWZO5HRIYBJ6QXDVRH/action/storage_attestation","attest_author":"https://pith.science/pith/RXRZHVYDWWZO5HRIYBJ6QXDVRH/action/author_attestation","sign_citation":"https://pith.science/pith/RXRZHVYDWWZO5HRIYBJ6QXDVRH/action/citation_signature","submit_replication":"https://pith.science/pith/RXRZHVYDWWZO5HRIYBJ6QXDVRH/action/replication_record"}},"created_at":"2026-07-05T09:03:21.044646+00:00","updated_at":"2026-07-05T09:03:21.044646+00:00"}