{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RJ36KJG7676QRCHELRR2C43XH2","short_pith_number":"pith:RJ36KJG7","schema_version":"1.0","canonical_sha256":"8a77e524dff7fd0888e45c63a173773eb44ed7e5376573babc3e6cff1aad7e31","source":{"kind":"arxiv","id":"1805.06334","version":2},"attestation_state":"computed","paper":{"title":"Auxiliary Tasks in Multi-task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lukas Liebel, Marco K\\\"orner","submitted_at":"2018-05-16T13:59:20Z","abstract_excerpt":"Multi-task convolutional neural networks (CNNs) have shown impressive results for certain combinations of tasks, such as single-image depth estimation (SIDE) and semantic segmentation. This is achieved by pushing the network towards learning a robust representation that generalizes well to different atomic tasks. We extend this concept by adding auxiliary tasks, which are of minor relevance for the application, to the set of learned tasks. As a kind of additional regularization, they are expected to boost the performance of the ultimately desired main tasks. To study the proposed approach, we "},"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":"1805.06334","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-16T13:59:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a6879b285b4f0ce6e5695493ab1b3e03291c8e39deed8b77675266b45a8bb5a8","abstract_canon_sha256":"9d4f393414040df56b788ec0270317796c7ee04d29ab2644b7039519d144adab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:43.453420Z","signature_b64":"UpJ1QPmbBbDw1vXxwtFWpKBmpnqItFnivv6vMmtrCa8If7miUjMt3FQXj365ZMdHAtFjJKj60KiQ74hmYMSKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a77e524dff7fd0888e45c63a173773eb44ed7e5376573babc3e6cff1aad7e31","last_reissued_at":"2026-05-18T00:01:43.452946Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:43.452946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auxiliary Tasks in Multi-task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lukas Liebel, Marco K\\\"orner","submitted_at":"2018-05-16T13:59:20Z","abstract_excerpt":"Multi-task convolutional neural networks (CNNs) have shown impressive results for certain combinations of tasks, such as single-image depth estimation (SIDE) and semantic segmentation. This is achieved by pushing the network towards learning a robust representation that generalizes well to different atomic tasks. We extend this concept by adding auxiliary tasks, which are of minor relevance for the application, to the set of learned tasks. As a kind of additional regularization, they are expected to boost the performance of the ultimately desired main tasks. To study the proposed approach, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.06334","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":""},"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":"1805.06334","created_at":"2026-05-18T00:01:43.453015+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.06334v2","created_at":"2026-05-18T00:01:43.453015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.06334","created_at":"2026-05-18T00:01:43.453015+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJ36KJG7676Q","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJ36KJG7676QRCHE","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJ36KJG7","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.11111","citing_title":"MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15471","citing_title":"CITYMPC: A Large-Scale Physics-Informed Benchmark and Tool for Generative Complete Multipath Wireless Channel Modeling","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02742","citing_title":"Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17477","citing_title":"Unveiling Deepfakes: A Frequency-Aware Triple Branch Network for Deepfake Detection","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RJ36KJG7676QRCHELRR2C43XH2","json":"https://pith.science/pith/RJ36KJG7676QRCHELRR2C43XH2.json","graph_json":"https://pith.science/api/pith-number/RJ36KJG7676QRCHELRR2C43XH2/graph.json","events_json":"https://pith.science/api/pith-number/RJ36KJG7676QRCHELRR2C43XH2/events.json","paper":"https://pith.science/paper/RJ36KJG7"},"agent_actions":{"view_html":"https://pith.science/pith/RJ36KJG7676QRCHELRR2C43XH2","download_json":"https://pith.science/pith/RJ36KJG7676QRCHELRR2C43XH2.json","view_paper":"https://pith.science/paper/RJ36KJG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.06334&json=true","fetch_graph":"https://pith.science/api/pith-number/RJ36KJG7676QRCHELRR2C43XH2/graph.json","fetch_events":"https://pith.science/api/pith-number/RJ36KJG7676QRCHELRR2C43XH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJ36KJG7676QRCHELRR2C43XH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJ36KJG7676QRCHELRR2C43XH2/action/storage_attestation","attest_author":"https://pith.science/pith/RJ36KJG7676QRCHELRR2C43XH2/action/author_attestation","sign_citation":"https://pith.science/pith/RJ36KJG7676QRCHELRR2C43XH2/action/citation_signature","submit_replication":"https://pith.science/pith/RJ36KJG7676QRCHELRR2C43XH2/action/replication_record"}},"created_at":"2026-05-18T00:01:43.453015+00:00","updated_at":"2026-05-18T00:01:43.453015+00:00"}