{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:H4BTXLX2SCUC4PI7ZQHI7OV4EO","short_pith_number":"pith:H4BTXLX2","schema_version":"1.0","canonical_sha256":"3f033baefa90a82e3d1fcc0e8fbabc23bb5a6d6ed03359eac5028e576ac58a71","source":{"kind":"arxiv","id":"1708.00260","version":3},"attestation_state":"computed","paper":{"title":"Deep Asymmetric Multi-task Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eunho Yang, Hae Beom Lee, Sung Ju Hwang","submitted_at":"2017-08-01T11:44:33Z","abstract_excerpt":"We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can learn deep representations shared across multiple tasks while effectively preventing negative transfer that may happen in the feature sharing process. Specifically, we introduce an asymmetric autoencoder term that allows reliable predictors for the easy tasks to have high contribution to the feature learning while suppressing the influences of unreliable predictors for more difficult tasks. This allows the learning of less noisy representations, and enables unreliable predictors to exploit knowledge from the reliable "},"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":"1708.00260","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-01T11:44:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2143b9456a0a1a7381a9d4c89c971517dd464ec5b6795affa0fa0520827faee4","abstract_canon_sha256":"51e44430a43f7242fb8d6dc9f01d31b52fdbc75b8c706ce1444fe47af6367ab9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:58.061462Z","signature_b64":"a34jQnYARgWV0pY4ULNeVGbCLOm7YsHidEa7LwYyQq05HbPKydUhko+G+QB69cOBayimYu3af1cmYdvHhTgBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f033baefa90a82e3d1fcc0e8fbabc23bb5a6d6ed03359eac5028e576ac58a71","last_reissued_at":"2026-05-18T00:11:58.060977Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:58.060977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Asymmetric Multi-task Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eunho Yang, Hae Beom Lee, Sung Ju Hwang","submitted_at":"2017-08-01T11:44:33Z","abstract_excerpt":"We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can learn deep representations shared across multiple tasks while effectively preventing negative transfer that may happen in the feature sharing process. Specifically, we introduce an asymmetric autoencoder term that allows reliable predictors for the easy tasks to have high contribution to the feature learning while suppressing the influences of unreliable predictors for more difficult tasks. This allows the learning of less noisy representations, and enables unreliable predictors to exploit knowledge from the reliable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00260","kind":"arxiv","version":3},"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":"1708.00260","created_at":"2026-05-18T00:11:58.061052+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.00260v3","created_at":"2026-05-18T00:11:58.061052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00260","created_at":"2026-05-18T00:11:58.061052+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4BTXLX2SCUC","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4BTXLX2SCUC4PI7","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4BTXLX2","created_at":"2026-05-18T12:31:18.294218+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/H4BTXLX2SCUC4PI7ZQHI7OV4EO","json":"https://pith.science/pith/H4BTXLX2SCUC4PI7ZQHI7OV4EO.json","graph_json":"https://pith.science/api/pith-number/H4BTXLX2SCUC4PI7ZQHI7OV4EO/graph.json","events_json":"https://pith.science/api/pith-number/H4BTXLX2SCUC4PI7ZQHI7OV4EO/events.json","paper":"https://pith.science/paper/H4BTXLX2"},"agent_actions":{"view_html":"https://pith.science/pith/H4BTXLX2SCUC4PI7ZQHI7OV4EO","download_json":"https://pith.science/pith/H4BTXLX2SCUC4PI7ZQHI7OV4EO.json","view_paper":"https://pith.science/paper/H4BTXLX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.00260&json=true","fetch_graph":"https://pith.science/api/pith-number/H4BTXLX2SCUC4PI7ZQHI7OV4EO/graph.json","fetch_events":"https://pith.science/api/pith-number/H4BTXLX2SCUC4PI7ZQHI7OV4EO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4BTXLX2SCUC4PI7ZQHI7OV4EO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4BTXLX2SCUC4PI7ZQHI7OV4EO/action/storage_attestation","attest_author":"https://pith.science/pith/H4BTXLX2SCUC4PI7ZQHI7OV4EO/action/author_attestation","sign_citation":"https://pith.science/pith/H4BTXLX2SCUC4PI7ZQHI7OV4EO/action/citation_signature","submit_replication":"https://pith.science/pith/H4BTXLX2SCUC4PI7ZQHI7OV4EO/action/replication_record"}},"created_at":"2026-05-18T00:11:58.061052+00:00","updated_at":"2026-05-18T00:11:58.061052+00:00"}