{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ADB4B4OMBBSHAETFESZ2AWLF7K","short_pith_number":"pith:ADB4B4OM","schema_version":"1.0","canonical_sha256":"00c3c0f1cc086470126524b3a05965fa8319e99f11703c89f86b4209b818cac2","source":{"kind":"arxiv","id":"2010.01494","version":1},"attestation_state":"computed","paper":{"title":"PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chuhan Wu, Fangzhao Wu, Jianxun Lian, Tao Qi, Xing Xie, Yongfeng Huang","submitted_at":"2020-10-04T07:01:23Z","abstract_excerpt":"User modeling is critical for many personalized web services. Many existing methods model users based on their behaviors and the labeled data of target tasks. However, these methods cannot exploit useful information in unlabeled user behavior data, and their performance may be not optimal when labeled data is scarce. Motivated by pre-trained language models which are pre-trained on large-scale unlabeled corpus to empower many downstream tasks, in this paper we propose to pre-train user models from large-scale unlabeled user behaviors data. We propose two self-supervision tasks for user model p"},"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":"2010.01494","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-10-04T07:01:23Z","cross_cats_sorted":[],"title_canon_sha256":"a62b3351526d1f76a81303b9a7bdce425b4801165449227b9bc3be69ab78994c","abstract_canon_sha256":"0bfd1890bd8d6622c3cb0b3a8e8a5594821d29316e05b2370dddafab2c69fcaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:06.140224Z","signature_b64":"44DoKm/dOgyjGBXTzdZldP+N9h08orIB/rGik6pjzQ9VKaGqYvz+LC760+5n47e+PfjJLIKONUe/Y+H2krq5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00c3c0f1cc086470126524b3a05965fa8319e99f11703c89f86b4209b818cac2","last_reissued_at":"2026-07-05T01:40:06.139740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:06.139740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chuhan Wu, Fangzhao Wu, Jianxun Lian, Tao Qi, Xing Xie, Yongfeng Huang","submitted_at":"2020-10-04T07:01:23Z","abstract_excerpt":"User modeling is critical for many personalized web services. Many existing methods model users based on their behaviors and the labeled data of target tasks. However, these methods cannot exploit useful information in unlabeled user behavior data, and their performance may be not optimal when labeled data is scarce. Motivated by pre-trained language models which are pre-trained on large-scale unlabeled corpus to empower many downstream tasks, in this paper we propose to pre-train user models from large-scale unlabeled user behaviors data. We propose two self-supervision tasks for user model p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01494","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/2010.01494/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":"2010.01494","created_at":"2026-07-05T01:40:06.139801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01494v1","created_at":"2026-07-05T01:40:06.139801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01494","created_at":"2026-07-05T01:40:06.139801+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADB4B4OMBBSH","created_at":"2026-07-05T01:40:06.139801+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADB4B4OMBBSHAETF","created_at":"2026-07-05T01:40:06.139801+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADB4B4OM","created_at":"2026-07-05T01:40:06.139801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11053","citing_title":"Bootstrapping your behavior: a new pretraining strategy for user behavior sequence data","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADB4B4OMBBSHAETFESZ2AWLF7K","json":"https://pith.science/pith/ADB4B4OMBBSHAETFESZ2AWLF7K.json","graph_json":"https://pith.science/api/pith-number/ADB4B4OMBBSHAETFESZ2AWLF7K/graph.json","events_json":"https://pith.science/api/pith-number/ADB4B4OMBBSHAETFESZ2AWLF7K/events.json","paper":"https://pith.science/paper/ADB4B4OM"},"agent_actions":{"view_html":"https://pith.science/pith/ADB4B4OMBBSHAETFESZ2AWLF7K","download_json":"https://pith.science/pith/ADB4B4OMBBSHAETFESZ2AWLF7K.json","view_paper":"https://pith.science/paper/ADB4B4OM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01494&json=true","fetch_graph":"https://pith.science/api/pith-number/ADB4B4OMBBSHAETFESZ2AWLF7K/graph.json","fetch_events":"https://pith.science/api/pith-number/ADB4B4OMBBSHAETFESZ2AWLF7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADB4B4OMBBSHAETFESZ2AWLF7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADB4B4OMBBSHAETFESZ2AWLF7K/action/storage_attestation","attest_author":"https://pith.science/pith/ADB4B4OMBBSHAETFESZ2AWLF7K/action/author_attestation","sign_citation":"https://pith.science/pith/ADB4B4OMBBSHAETFESZ2AWLF7K/action/citation_signature","submit_replication":"https://pith.science/pith/ADB4B4OMBBSHAETFESZ2AWLF7K/action/replication_record"}},"created_at":"2026-07-05T01:40:06.139801+00:00","updated_at":"2026-07-05T01:40:06.139801+00:00"}