{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:STVWV6P2NB6PWEGELLUOW57FMF","short_pith_number":"pith:STVWV6P2","schema_version":"1.0","canonical_sha256":"94eb6af9fa687cfb10c45ae8eb77e5614d83d1b56ea49c75d3d92b535dd07d1a","source":{"kind":"arxiv","id":"2506.07563","version":3},"attestation_state":"computed","paper":{"title":"MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Aviel Ben Siman Tov, Eyal German, Ken Yaggel","submitted_at":"2025-06-09T09:03:05Z","abstract_excerpt":"Personalized recommendation systems must adapt to user interactions across different domains. Traditional approaches like MLoRA apply a single adaptation per domain but lack flexibility in handling diverse user behaviors. To address this, we propose MoE-MLoRA, a mixture-of-experts framework where each expert is first trained independently to specialize in its domain before a gating network is trained to weight their contributions dynamically. We evaluate MoE-MLoRA across eight CTR models on Movielens and Taobao, showing that it improves performance in large-scale, dynamic datasets (+1.45 Weigh"},"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":"2506.07563","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-09T09:03:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"465974ab59a573d4d0970b96862a3e9303e3192d07f15db7335fe4168335fc51","abstract_canon_sha256":"548d23a34f9cca1bc49e5ce625d739ea7c91668a35334db7fa8b999429997986"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:28.731136Z","signature_b64":"Y9vxF3UKpMvdfvPkrGcE6/zRcm6yKqhrA3UCR4tE+2fQnx6F7HrtE2SAiUIWSJsLbz8ZGu7wyomuM/9OfAOaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94eb6af9fa687cfb10c45ae8eb77e5614d83d1b56ea49c75d3d92b535dd07d1a","last_reissued_at":"2026-07-05T11:19:28.730663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:28.730663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Aviel Ben Siman Tov, Eyal German, Ken Yaggel","submitted_at":"2025-06-09T09:03:05Z","abstract_excerpt":"Personalized recommendation systems must adapt to user interactions across different domains. Traditional approaches like MLoRA apply a single adaptation per domain but lack flexibility in handling diverse user behaviors. To address this, we propose MoE-MLoRA, a mixture-of-experts framework where each expert is first trained independently to specialize in its domain before a gating network is trained to weight their contributions dynamically. We evaluate MoE-MLoRA across eight CTR models on Movielens and Taobao, showing that it improves performance in large-scale, dynamic datasets (+1.45 Weigh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07563","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.07563/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":"2506.07563","created_at":"2026-07-05T11:19:28.730721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07563v3","created_at":"2026-07-05T11:19:28.730721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07563","created_at":"2026-07-05T11:19:28.730721+00:00"},{"alias_kind":"pith_short_12","alias_value":"STVWV6P2NB6P","created_at":"2026-07-05T11:19:28.730721+00:00"},{"alias_kind":"pith_short_16","alias_value":"STVWV6P2NB6PWEGE","created_at":"2026-07-05T11:19:28.730721+00:00"},{"alias_kind":"pith_short_8","alias_value":"STVWV6P2","created_at":"2026-07-05T11:19:28.730721+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/STVWV6P2NB6PWEGELLUOW57FMF","json":"https://pith.science/pith/STVWV6P2NB6PWEGELLUOW57FMF.json","graph_json":"https://pith.science/api/pith-number/STVWV6P2NB6PWEGELLUOW57FMF/graph.json","events_json":"https://pith.science/api/pith-number/STVWV6P2NB6PWEGELLUOW57FMF/events.json","paper":"https://pith.science/paper/STVWV6P2"},"agent_actions":{"view_html":"https://pith.science/pith/STVWV6P2NB6PWEGELLUOW57FMF","download_json":"https://pith.science/pith/STVWV6P2NB6PWEGELLUOW57FMF.json","view_paper":"https://pith.science/paper/STVWV6P2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07563&json=true","fetch_graph":"https://pith.science/api/pith-number/STVWV6P2NB6PWEGELLUOW57FMF/graph.json","fetch_events":"https://pith.science/api/pith-number/STVWV6P2NB6PWEGELLUOW57FMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STVWV6P2NB6PWEGELLUOW57FMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STVWV6P2NB6PWEGELLUOW57FMF/action/storage_attestation","attest_author":"https://pith.science/pith/STVWV6P2NB6PWEGELLUOW57FMF/action/author_attestation","sign_citation":"https://pith.science/pith/STVWV6P2NB6PWEGELLUOW57FMF/action/citation_signature","submit_replication":"https://pith.science/pith/STVWV6P2NB6PWEGELLUOW57FMF/action/replication_record"}},"created_at":"2026-07-05T11:19:28.730721+00:00","updated_at":"2026-07-05T11:19:28.730721+00:00"}