{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MU4U6WE33W74CECJDPKUT375WA","short_pith_number":"pith:MU4U6WE3","schema_version":"1.0","canonical_sha256":"65394f589bddbfc110491bd549effdb00f96a60cb916b60b6d2d3de389db0b34","source":{"kind":"arxiv","id":"2501.06062","version":1},"attestation_state":"computed","paper":{"title":"Personalized Language Model Learning on Text Data Without User Identifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaoyue Niu, Fandong Meng, Fan Wu, Guihai Chen, Jie Zhou, Ning Liu, Xiangyu Liu, Yangwenjian Tan, Yucheng Ding","submitted_at":"2025-01-10T15:46:19Z","abstract_excerpt":"In many practical natural language applications, user data are highly sensitive, requiring anonymous uploads of text data from mobile devices to the cloud without user identifiers. However, the absence of user identifiers restricts the ability of cloud-based language models to provide personalized services, which are essential for catering to diverse user needs. The trivial method of replacing an explicit user identifier with a static user embedding as model input still compromises data anonymization. In this work, we propose to let each mobile device maintain a user-specific distribution to d"},"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":"2501.06062","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-10T15:46:19Z","cross_cats_sorted":[],"title_canon_sha256":"dd317cff9774ddf2070b80895fc189201f619746444ff91d7308b4fe7cbe137d","abstract_canon_sha256":"8792e7835b68662ebab46356c9a805f83a45884de0bc1c6d94dcdd4e189df5a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:32.660450Z","signature_b64":"DpQTkWtBfYN/zdDV22POc9izGNLS98mJwkSI052wci2dcnj4oIrIMT+5gQ6B78w1E7fAKNvWWnBEgre7vbrPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65394f589bddbfc110491bd549effdb00f96a60cb916b60b6d2d3de389db0b34","last_reissued_at":"2026-07-05T09:59:32.660037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:32.660037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalized Language Model Learning on Text Data Without User Identifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaoyue Niu, Fandong Meng, Fan Wu, Guihai Chen, Jie Zhou, Ning Liu, Xiangyu Liu, Yangwenjian Tan, Yucheng Ding","submitted_at":"2025-01-10T15:46:19Z","abstract_excerpt":"In many practical natural language applications, user data are highly sensitive, requiring anonymous uploads of text data from mobile devices to the cloud without user identifiers. However, the absence of user identifiers restricts the ability of cloud-based language models to provide personalized services, which are essential for catering to diverse user needs. The trivial method of replacing an explicit user identifier with a static user embedding as model input still compromises data anonymization. In this work, we propose to let each mobile device maintain a user-specific distribution to d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06062","kind":"arxiv","version":1},"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/2501.06062/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":"2501.06062","created_at":"2026-07-05T09:59:32.660101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06062v1","created_at":"2026-07-05T09:59:32.660101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06062","created_at":"2026-07-05T09:59:32.660101+00:00"},{"alias_kind":"pith_short_12","alias_value":"MU4U6WE33W74","created_at":"2026-07-05T09:59:32.660101+00:00"},{"alias_kind":"pith_short_16","alias_value":"MU4U6WE33W74CECJ","created_at":"2026-07-05T09:59:32.660101+00:00"},{"alias_kind":"pith_short_8","alias_value":"MU4U6WE3","created_at":"2026-07-05T09:59:32.660101+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/MU4U6WE33W74CECJDPKUT375WA","json":"https://pith.science/pith/MU4U6WE33W74CECJDPKUT375WA.json","graph_json":"https://pith.science/api/pith-number/MU4U6WE33W74CECJDPKUT375WA/graph.json","events_json":"https://pith.science/api/pith-number/MU4U6WE33W74CECJDPKUT375WA/events.json","paper":"https://pith.science/paper/MU4U6WE3"},"agent_actions":{"view_html":"https://pith.science/pith/MU4U6WE33W74CECJDPKUT375WA","download_json":"https://pith.science/pith/MU4U6WE33W74CECJDPKUT375WA.json","view_paper":"https://pith.science/paper/MU4U6WE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06062&json=true","fetch_graph":"https://pith.science/api/pith-number/MU4U6WE33W74CECJDPKUT375WA/graph.json","fetch_events":"https://pith.science/api/pith-number/MU4U6WE33W74CECJDPKUT375WA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MU4U6WE33W74CECJDPKUT375WA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MU4U6WE33W74CECJDPKUT375WA/action/storage_attestation","attest_author":"https://pith.science/pith/MU4U6WE33W74CECJDPKUT375WA/action/author_attestation","sign_citation":"https://pith.science/pith/MU4U6WE33W74CECJDPKUT375WA/action/citation_signature","submit_replication":"https://pith.science/pith/MU4U6WE33W74CECJDPKUT375WA/action/replication_record"}},"created_at":"2026-07-05T09:59:32.660101+00:00","updated_at":"2026-07-05T09:59:32.660101+00:00"}