{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6ZHSF7LRCRINQBL52YWOVMG7RC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"765bd5d4bf65fde631df7f6292612cd72a1b8f341e00d9de0c9eff7b668e5241","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2022-08-12T07:35:38Z","title_canon_sha256":"c1f606c6cd25a6feeca1ff6ea3b0722db43903304ac1b140db06b126d9323019"},"schema_version":"1.0","source":{"id":"2208.06150","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.06150","created_at":"2026-07-05T04:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2208.06150v2","created_at":"2026-07-05T04:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06150","created_at":"2026-07-05T04:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"6ZHSF7LRCRIN","created_at":"2026-07-05T04:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"6ZHSF7LRCRINQBL5","created_at":"2026-07-05T04:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"6ZHSF7LR","created_at":"2026-07-05T04:50:19Z"}],"graph_snapshots":[{"event_id":"sha256:8dcdce80cf70bfb2b68cda5d0ac38261fe2e672f926a80a0d881a74ac676cde9","target":"graph","created_at":"2026-07-05T04:50:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2208.06150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Long, Chenyu Zhao, Han Zhang, Jingwei Zhuo, Songlin Wang, Sulong Xu, Tianhao Li, Wen-Yun Yang, Xiaowei Zhang, Yiming Qiu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2022-08-12T07:35:38Z","title":"Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06150","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:322db8652067998cb8b49d8cd6988f697adbb22408025418b962efceeda3000d","target":"record","created_at":"2026-07-05T04:50:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"765bd5d4bf65fde631df7f6292612cd72a1b8f341e00d9de0c9eff7b668e5241","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2022-08-12T07:35:38Z","title_canon_sha256":"c1f606c6cd25a6feeca1ff6ea3b0722db43903304ac1b140db06b126d9323019"},"schema_version":"1.0","source":{"id":"2208.06150","kind":"arxiv","version":2}},"canonical_sha256":"f64f22fd711450d8057dd62ceab0df88ba7da6deb2fbb09954dbea8fed02b44a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f64f22fd711450d8057dd62ceab0df88ba7da6deb2fbb09954dbea8fed02b44a","first_computed_at":"2026-07-05T04:50:19.645616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:50:19.645616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yEYNYuti6E8d1jjiRxKDVx6ivg+bm+dLZk0ZnLC2aKKJhirruyV/YLPLS0uxUs6oTBKPK1D+1rLCCfjVON+XBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:50:19.646155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.06150","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:322db8652067998cb8b49d8cd6988f697adbb22408025418b962efceeda3000d","sha256:8dcdce80cf70bfb2b68cda5d0ac38261fe2e672f926a80a0d881a74ac676cde9"],"state_sha256":"1e78bef5c79171bd38690264849dfe28c3e4eee196970dedad2d71018e43708e"}