{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:CMTJXUCIP3XPNVYAMOYHXRUWSR","short_pith_number":"pith:CMTJXUCI","schema_version":"1.0","canonical_sha256":"13269bd0487eeef6d70063b07bc696944b4b5afea07acb67b5364a54e98b4593","source":{"kind":"arxiv","id":"1611.05377","version":1},"attestation_state":"computed","paper":{"title":"Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhishek Kumar, Rogerio Feris, Shuangfei Zhai, Tara Javidi, Yongxi Lu, Yu Cheng","submitted_at":"2016-11-16T17:31:44Z","abstract_excerpt":"Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them. In the context of deep neural networks, this idea is often realized by hand-designed network architectures with layers that are shared across tasks and branches that encode task-specific features. However, the space of possible multi-task deep architectures is combinatorially large and often the final architecture is arrived at by manual exploration of this space subject to designer's bias, which can be both error-prone and tedious. In this work"},"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":"1611.05377","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-16T17:31:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0bc7a80f322810a067df2a264e91b74bfd3a38c7d90d2f84da90c26c625d7262","abstract_canon_sha256":"a7aff08efcc37b943fca773efd65c74c68d5b8d585a5214958b736259f3f5a1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:27.244881Z","signature_b64":"FnpiCfm+8WPU+J9hlzZE++wFTLdWSD6ipBs8J/D5DmQlywG4M9eMdu2ujVpCX9PNJc3zmqLIwjDRPFJ/PCoFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13269bd0487eeef6d70063b07bc696944b4b5afea07acb67b5364a54e98b4593","last_reissued_at":"2026-05-18T00:58:27.244158Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:27.244158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhishek Kumar, Rogerio Feris, Shuangfei Zhai, Tara Javidi, Yongxi Lu, Yu Cheng","submitted_at":"2016-11-16T17:31:44Z","abstract_excerpt":"Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them. In the context of deep neural networks, this idea is often realized by hand-designed network architectures with layers that are shared across tasks and branches that encode task-specific features. However, the space of possible multi-task deep architectures is combinatorially large and often the final architecture is arrived at by manual exploration of this space subject to designer's bias, which can be both error-prone and tedious. In this work"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05377","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":""},"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":"1611.05377","created_at":"2026-05-18T00:58:27.244272+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.05377v1","created_at":"2026-05-18T00:58:27.244272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05377","created_at":"2026-05-18T00:58:27.244272+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMTJXUCIP3XP","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMTJXUCIP3XPNVYA","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMTJXUCI","created_at":"2026-05-18T12:30:09.641336+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/CMTJXUCIP3XPNVYAMOYHXRUWSR","json":"https://pith.science/pith/CMTJXUCIP3XPNVYAMOYHXRUWSR.json","graph_json":"https://pith.science/api/pith-number/CMTJXUCIP3XPNVYAMOYHXRUWSR/graph.json","events_json":"https://pith.science/api/pith-number/CMTJXUCIP3XPNVYAMOYHXRUWSR/events.json","paper":"https://pith.science/paper/CMTJXUCI"},"agent_actions":{"view_html":"https://pith.science/pith/CMTJXUCIP3XPNVYAMOYHXRUWSR","download_json":"https://pith.science/pith/CMTJXUCIP3XPNVYAMOYHXRUWSR.json","view_paper":"https://pith.science/paper/CMTJXUCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.05377&json=true","fetch_graph":"https://pith.science/api/pith-number/CMTJXUCIP3XPNVYAMOYHXRUWSR/graph.json","fetch_events":"https://pith.science/api/pith-number/CMTJXUCIP3XPNVYAMOYHXRUWSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMTJXUCIP3XPNVYAMOYHXRUWSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMTJXUCIP3XPNVYAMOYHXRUWSR/action/storage_attestation","attest_author":"https://pith.science/pith/CMTJXUCIP3XPNVYAMOYHXRUWSR/action/author_attestation","sign_citation":"https://pith.science/pith/CMTJXUCIP3XPNVYAMOYHXRUWSR/action/citation_signature","submit_replication":"https://pith.science/pith/CMTJXUCIP3XPNVYAMOYHXRUWSR/action/replication_record"}},"created_at":"2026-05-18T00:58:27.244272+00:00","updated_at":"2026-05-18T00:58:27.244272+00:00"}