{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EHW76FQ467H5XIOLRU2ORX44K5","short_pith_number":"pith:EHW76FQ4","schema_version":"1.0","canonical_sha256":"21edff161cf7cfdba1cb8d34e8df9c577aa20ab0bf296f59ab2fe84ce645755f","source":{"kind":"arxiv","id":"1908.04339","version":1},"attestation_state":"computed","paper":{"title":"Feature Partitioning for Efficient Multi-Task Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alejandro Newell, Chong Wang, Jia Deng, Li-Jia Li, Lu Jiang","submitted_at":"2019-08-12T19:06:32Z","abstract_excerpt":"Multi-task learning holds the promise of less data, parameters, and time than training of separate models. We propose a method to automatically search over multi-task architectures while taking resource constraints into consideration. We propose a search space that compactly represents different parameter sharing strategies. This provides more effective coverage and sampling of the space of multi-task architectures. We also present a method for quick evaluation of different architectures by using feature distillation. Together these contributions allow us to quickly optimize for efficient mult"},"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":"1908.04339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-12T19:06:32Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"da2f5f647969757abec4b82583b7e38b532e26626de27e37e0c69fed9aed11fa","abstract_canon_sha256":"d967e0bd977b35bba8c6f28d1ac7479b2a77759e01221aa0ea39af655d2ae9a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:54:29.757684Z","signature_b64":"3vuRvRVzoSq1s+U1OhBk8mTljZf+HA2Pc2r+fhaqYAuOkeTV2uaG5W5QLZtyQOXWjcP6965dNsa+dW8my8xyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21edff161cf7cfdba1cb8d34e8df9c577aa20ab0bf296f59ab2fe84ce645755f","last_reissued_at":"2026-07-04T23:54:29.757198Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:54:29.757198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Partitioning for Efficient Multi-Task Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alejandro Newell, Chong Wang, Jia Deng, Li-Jia Li, Lu Jiang","submitted_at":"2019-08-12T19:06:32Z","abstract_excerpt":"Multi-task learning holds the promise of less data, parameters, and time than training of separate models. We propose a method to automatically search over multi-task architectures while taking resource constraints into consideration. We propose a search space that compactly represents different parameter sharing strategies. This provides more effective coverage and sampling of the space of multi-task architectures. We also present a method for quick evaluation of different architectures by using feature distillation. Together these contributions allow us to quickly optimize for efficient mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04339","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/1908.04339/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":"1908.04339","created_at":"2026-07-04T23:54:29.757251+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04339v1","created_at":"2026-07-04T23:54:29.757251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04339","created_at":"2026-07-04T23:54:29.757251+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHW76FQ467H5","created_at":"2026-07-04T23:54:29.757251+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHW76FQ467H5XIOL","created_at":"2026-07-04T23:54:29.757251+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHW76FQ4","created_at":"2026-07-04T23:54:29.757251+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/EHW76FQ467H5XIOLRU2ORX44K5","json":"https://pith.science/pith/EHW76FQ467H5XIOLRU2ORX44K5.json","graph_json":"https://pith.science/api/pith-number/EHW76FQ467H5XIOLRU2ORX44K5/graph.json","events_json":"https://pith.science/api/pith-number/EHW76FQ467H5XIOLRU2ORX44K5/events.json","paper":"https://pith.science/paper/EHW76FQ4"},"agent_actions":{"view_html":"https://pith.science/pith/EHW76FQ467H5XIOLRU2ORX44K5","download_json":"https://pith.science/pith/EHW76FQ467H5XIOLRU2ORX44K5.json","view_paper":"https://pith.science/paper/EHW76FQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04339&json=true","fetch_graph":"https://pith.science/api/pith-number/EHW76FQ467H5XIOLRU2ORX44K5/graph.json","fetch_events":"https://pith.science/api/pith-number/EHW76FQ467H5XIOLRU2ORX44K5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHW76FQ467H5XIOLRU2ORX44K5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHW76FQ467H5XIOLRU2ORX44K5/action/storage_attestation","attest_author":"https://pith.science/pith/EHW76FQ467H5XIOLRU2ORX44K5/action/author_attestation","sign_citation":"https://pith.science/pith/EHW76FQ467H5XIOLRU2ORX44K5/action/citation_signature","submit_replication":"https://pith.science/pith/EHW76FQ467H5XIOLRU2ORX44K5/action/replication_record"}},"created_at":"2026-07-04T23:54:29.757251+00:00","updated_at":"2026-07-04T23:54:29.757251+00:00"}