{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V4ZACZXQWTJXFBFYVOPKGEGWUQ","short_pith_number":"pith:V4ZACZXQ","schema_version":"1.0","canonical_sha256":"af320166f0b4d37284b8ab9ea310d6a431e9703b1f5dd5c1328ab70ef7cab903","source":{"kind":"arxiv","id":"2308.13537","version":2},"attestation_state":"computed","paper":{"title":"STEM: Unleashing the Power of Embeddings for Multi-task Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Jie Jiang, Junwei Pan, Liangcai Su, Shijie Quan, Xihua Chen, Ximei Wang, Xi Xiao","submitted_at":"2023-08-16T12:38:06Z","abstract_excerpt":"Multi-task learning (MTL) has gained significant popularity in recommender systems as it enables simultaneous optimization of multiple objectives. A key challenge in MTL is negative transfer, but existing studies explored negative transfer on all samples, overlooking the inherent complexities within them. We split the samples according to the relative amount of positive feedback among tasks. Surprisingly, negative transfer still occurs in existing MTL methods on samples that receive comparable feedback across tasks. Existing work commonly employs a shared-embedding paradigm, limiting the abili"},"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":"2308.13537","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-08-16T12:38:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b6c6f1ea3093ed1a3c69e475d0479e7633f3d77bcc731972eda44093a989ff47","abstract_canon_sha256":"034d6732bf574e3cec4acf3d518283f2a26497a0c7b84f9d7b988f30a2659f50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:52.530485Z","signature_b64":"Vu1RWg2T8Mls5qD25pAZXzA+35T+8U7Of5fTvwtJVgXl5zalaVefkCIlsF9P9EORqIgLJIpuYMZWMgPqlgABAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af320166f0b4d37284b8ab9ea310d6a431e9703b1f5dd5c1328ab70ef7cab903","last_reissued_at":"2026-07-05T07:30:52.530007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:52.530007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STEM: Unleashing the Power of Embeddings for Multi-task Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Jie Jiang, Junwei Pan, Liangcai Su, Shijie Quan, Xihua Chen, Ximei Wang, Xi Xiao","submitted_at":"2023-08-16T12:38:06Z","abstract_excerpt":"Multi-task learning (MTL) has gained significant popularity in recommender systems as it enables simultaneous optimization of multiple objectives. A key challenge in MTL is negative transfer, but existing studies explored negative transfer on all samples, overlooking the inherent complexities within them. We split the samples according to the relative amount of positive feedback among tasks. Surprisingly, negative transfer still occurs in existing MTL methods on samples that receive comparable feedback across tasks. Existing work commonly employs a shared-embedding paradigm, limiting the abili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13537","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/2308.13537/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":"2308.13537","created_at":"2026-07-05T07:30:52.530064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13537v2","created_at":"2026-07-05T07:30:52.530064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13537","created_at":"2026-07-05T07:30:52.530064+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4ZACZXQWTJX","created_at":"2026-07-05T07:30:52.530064+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4ZACZXQWTJXFBFY","created_at":"2026-07-05T07:30:52.530064+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4ZACZXQ","created_at":"2026-07-05T07:30:52.530064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12092","citing_title":"No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier Methods","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4ZACZXQWTJXFBFYVOPKGEGWUQ","json":"https://pith.science/pith/V4ZACZXQWTJXFBFYVOPKGEGWUQ.json","graph_json":"https://pith.science/api/pith-number/V4ZACZXQWTJXFBFYVOPKGEGWUQ/graph.json","events_json":"https://pith.science/api/pith-number/V4ZACZXQWTJXFBFYVOPKGEGWUQ/events.json","paper":"https://pith.science/paper/V4ZACZXQ"},"agent_actions":{"view_html":"https://pith.science/pith/V4ZACZXQWTJXFBFYVOPKGEGWUQ","download_json":"https://pith.science/pith/V4ZACZXQWTJXFBFYVOPKGEGWUQ.json","view_paper":"https://pith.science/paper/V4ZACZXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13537&json=true","fetch_graph":"https://pith.science/api/pith-number/V4ZACZXQWTJXFBFYVOPKGEGWUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/V4ZACZXQWTJXFBFYVOPKGEGWUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4ZACZXQWTJXFBFYVOPKGEGWUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4ZACZXQWTJXFBFYVOPKGEGWUQ/action/storage_attestation","attest_author":"https://pith.science/pith/V4ZACZXQWTJXFBFYVOPKGEGWUQ/action/author_attestation","sign_citation":"https://pith.science/pith/V4ZACZXQWTJXFBFYVOPKGEGWUQ/action/citation_signature","submit_replication":"https://pith.science/pith/V4ZACZXQWTJXFBFYVOPKGEGWUQ/action/replication_record"}},"created_at":"2026-07-05T07:30:52.530064+00:00","updated_at":"2026-07-05T07:30:52.530064+00:00"}