{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6ZHSF7LRCRINQBL52YWOVMG7RC","short_pith_number":"pith:6ZHSF7LR","schema_version":"1.0","canonical_sha256":"f64f22fd711450d8057dd62ceab0df88ba7da6deb2fbb09954dbea8fed02b44a","source":{"kind":"arxiv","id":"2208.06150","version":2},"attestation_state":"computed","paper":{"title":"Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bo Long, Chenyu Zhao, Han Zhang, Jingwei Zhuo, Songlin Wang, Sulong Xu, Tianhao Li, Wen-Yun Yang, Xiaowei Zhang, Yiming Qiu","submitted_at":"2022-08-12T07:35:38Z","abstract_excerpt":"BERT-style models pre-trained on the general corpus (e.g., Wikipedia) and fine-tuned on specific task corpus, have recently emerged as breakthrough techniques in many NLP tasks: question answering, text classification, sequence labeling and so on. However, this technique may not always work, especially for two scenarios: a corpus that contains very different text from the general corpus Wikipedia, or a task that learns embedding spacial distribution for a specific purpose (e.g., approximate nearest neighbor search). In this paper, to tackle the above two scenarios that we have encountered in a"},"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":"2208.06150","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2022-08-12T07:35:38Z","cross_cats_sorted":[],"title_canon_sha256":"c1f606c6cd25a6feeca1ff6ea3b0722db43903304ac1b140db06b126d9323019","abstract_canon_sha256":"765bd5d4bf65fde631df7f6292612cd72a1b8f341e00d9de0c9eff7b668e5241"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:50:19.646155Z","signature_b64":"yEYNYuti6E8d1jjiRxKDVx6ivg+bm+dLZk0ZnLC2aKKJhirruyV/YLPLS0uxUs6oTBKPK1D+1rLCCfjVON+XBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f64f22fd711450d8057dd62ceab0df88ba7da6deb2fbb09954dbea8fed02b44a","last_reissued_at":"2026-07-05T04:50:19.645616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:50:19.645616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bo Long, Chenyu Zhao, Han Zhang, Jingwei Zhuo, Songlin Wang, Sulong Xu, Tianhao Li, Wen-Yun Yang, Xiaowei Zhang, Yiming Qiu","submitted_at":"2022-08-12T07:35:38Z","abstract_excerpt":"BERT-style models pre-trained on the general corpus (e.g., Wikipedia) and fine-tuned on specific task corpus, have recently emerged as breakthrough techniques in many NLP tasks: question answering, text classification, sequence labeling and so on. However, this technique may not always work, especially for two scenarios: a corpus that contains very different text from the general corpus Wikipedia, or a task that learns embedding spacial distribution for a specific purpose (e.g., approximate nearest neighbor search). In this paper, to tackle the above two scenarios that we have encountered in a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06150","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/2208.06150/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":"2208.06150","created_at":"2026-07-05T04:50:19.645685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.06150v2","created_at":"2026-07-05T04:50:19.645685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06150","created_at":"2026-07-05T04:50:19.645685+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZHSF7LRCRIN","created_at":"2026-07-05T04:50:19.645685+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZHSF7LRCRINQBL5","created_at":"2026-07-05T04:50:19.645685+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZHSF7LR","created_at":"2026-07-05T04:50:19.645685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20330","citing_title":"Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZHSF7LRCRINQBL52YWOVMG7RC","json":"https://pith.science/pith/6ZHSF7LRCRINQBL52YWOVMG7RC.json","graph_json":"https://pith.science/api/pith-number/6ZHSF7LRCRINQBL52YWOVMG7RC/graph.json","events_json":"https://pith.science/api/pith-number/6ZHSF7LRCRINQBL52YWOVMG7RC/events.json","paper":"https://pith.science/paper/6ZHSF7LR"},"agent_actions":{"view_html":"https://pith.science/pith/6ZHSF7LRCRINQBL52YWOVMG7RC","download_json":"https://pith.science/pith/6ZHSF7LRCRINQBL52YWOVMG7RC.json","view_paper":"https://pith.science/paper/6ZHSF7LR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.06150&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZHSF7LRCRINQBL52YWOVMG7RC/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZHSF7LRCRINQBL52YWOVMG7RC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZHSF7LRCRINQBL52YWOVMG7RC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZHSF7LRCRINQBL52YWOVMG7RC/action/storage_attestation","attest_author":"https://pith.science/pith/6ZHSF7LRCRINQBL52YWOVMG7RC/action/author_attestation","sign_citation":"https://pith.science/pith/6ZHSF7LRCRINQBL52YWOVMG7RC/action/citation_signature","submit_replication":"https://pith.science/pith/6ZHSF7LRCRINQBL52YWOVMG7RC/action/replication_record"}},"created_at":"2026-07-05T04:50:19.645685+00:00","updated_at":"2026-07-05T04:50:19.645685+00:00"}