{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y5UPXBDMSACBRY54VIPIMV2FWT","short_pith_number":"pith:Y5UPXBDM","schema_version":"1.0","canonical_sha256":"c768fb846c900418e3bcaa1e865745b4e10facc9aee791d53fcea019d8541eab","source":{"kind":"arxiv","id":"2410.10639","version":2},"attestation_state":"computed","paper":{"title":"Paragon: Parameter Generation for Controllable Multi-Task Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chenglei Shen, Jiahao Zhao, Jianping Fan, Ming He, Weijie Yu, Xiao Zhang","submitted_at":"2024-10-14T15:50:35Z","abstract_excerpt":"Commercial recommender systems face the challenge that task requirements from platforms or users often change dynamically (e.g., varying preferences for accuracy or diversity). Ideally, the model should be re-trained after resetting a new objective function, adapting to these changes in task requirements. However, in practice, the high computational costs associated with retraining make this process impractical for models already deployed to online environments. This raises a new challenging problem: how to efficiently adapt the learned model to different task requirements by controlling the m"},"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":"2410.10639","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-14T15:50:35Z","cross_cats_sorted":[],"title_canon_sha256":"68f8a6176af030bc681f4a44d6920268df1c29a92702ef540f0bac0ef63acbf6","abstract_canon_sha256":"e8495aff120168d2339aa28337932cd6f20718d9028ededbcf69093d8db0f548"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:31.839411Z","signature_b64":"pEIrZn9oR4ir2XuY5WJFbznHb7AnIH5RdlHXYeEmEscObzWfvGxYy+Jez1xLS2RyE5I0tumrbhIJze2uyHZnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c768fb846c900418e3bcaa1e865745b4e10facc9aee791d53fcea019d8541eab","last_reissued_at":"2026-07-05T11:49:31.838868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:31.838868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Paragon: Parameter Generation for Controllable Multi-Task Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chenglei Shen, Jiahao Zhao, Jianping Fan, Ming He, Weijie Yu, Xiao Zhang","submitted_at":"2024-10-14T15:50:35Z","abstract_excerpt":"Commercial recommender systems face the challenge that task requirements from platforms or users often change dynamically (e.g., varying preferences for accuracy or diversity). Ideally, the model should be re-trained after resetting a new objective function, adapting to these changes in task requirements. However, in practice, the high computational costs associated with retraining make this process impractical for models already deployed to online environments. This raises a new challenging problem: how to efficiently adapt the learned model to different task requirements by controlling the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10639","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/2410.10639/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":"2410.10639","created_at":"2026-07-05T11:49:31.838929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10639v2","created_at":"2026-07-05T11:49:31.838929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10639","created_at":"2026-07-05T11:49:31.838929+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5UPXBDMSACB","created_at":"2026-07-05T11:49:31.838929+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5UPXBDMSACBRY54","created_at":"2026-07-05T11:49:31.838929+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5UPXBDM","created_at":"2026-07-05T11:49:31.838929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04152","citing_title":"Bridging Search and Recommendation through Latent Cross Reasoning","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5UPXBDMSACBRY54VIPIMV2FWT","json":"https://pith.science/pith/Y5UPXBDMSACBRY54VIPIMV2FWT.json","graph_json":"https://pith.science/api/pith-number/Y5UPXBDMSACBRY54VIPIMV2FWT/graph.json","events_json":"https://pith.science/api/pith-number/Y5UPXBDMSACBRY54VIPIMV2FWT/events.json","paper":"https://pith.science/paper/Y5UPXBDM"},"agent_actions":{"view_html":"https://pith.science/pith/Y5UPXBDMSACBRY54VIPIMV2FWT","download_json":"https://pith.science/pith/Y5UPXBDMSACBRY54VIPIMV2FWT.json","view_paper":"https://pith.science/paper/Y5UPXBDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10639&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5UPXBDMSACBRY54VIPIMV2FWT/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5UPXBDMSACBRY54VIPIMV2FWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5UPXBDMSACBRY54VIPIMV2FWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5UPXBDMSACBRY54VIPIMV2FWT/action/storage_attestation","attest_author":"https://pith.science/pith/Y5UPXBDMSACBRY54VIPIMV2FWT/action/author_attestation","sign_citation":"https://pith.science/pith/Y5UPXBDMSACBRY54VIPIMV2FWT/action/citation_signature","submit_replication":"https://pith.science/pith/Y5UPXBDMSACBRY54VIPIMV2FWT/action/replication_record"}},"created_at":"2026-07-05T11:49:31.838929+00:00","updated_at":"2026-07-05T11:49:31.838929+00:00"}