{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4NMMUQF3YU2PJWN32HEPYPQU5D","short_pith_number":"pith:4NMMUQF3","canonical_record":{"source":{"id":"2210.03915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-08T04:50:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"73eea3766bd871f73321d31cb81d8d19dcfd48fc882e08ca715649cbfbcd2513","abstract_canon_sha256":"009fe03f148765fb81d3295e229e69a82366d77bcc23865eeb8330155dcb45cf"},"schema_version":"1.0"},"canonical_sha256":"e358ca40bbc534f4d9bbd1c8fc3e14e8fa432e3a3b31068d0979e71dbaa892cc","source":{"kind":"arxiv","id":"2210.03915","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03915","created_at":"2026-07-05T05:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03915v1","created_at":"2026-07-05T05:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03915","created_at":"2026-07-05T05:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"4NMMUQF3YU2P","created_at":"2026-07-05T05:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"4NMMUQF3YU2PJWN3","created_at":"2026-07-05T05:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"4NMMUQF3","created_at":"2026-07-05T05:04:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4NMMUQF3YU2PJWN32HEPYPQU5D","target":"record","payload":{"canonical_record":{"source":{"id":"2210.03915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-08T04:50:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"73eea3766bd871f73321d31cb81d8d19dcfd48fc882e08ca715649cbfbcd2513","abstract_canon_sha256":"009fe03f148765fb81d3295e229e69a82366d77bcc23865eeb8330155dcb45cf"},"schema_version":"1.0"},"canonical_sha256":"e358ca40bbc534f4d9bbd1c8fc3e14e8fa432e3a3b31068d0979e71dbaa892cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:33.781263Z","signature_b64":"3qikAwXhLwAzCB9XnkEN/S7gMo5LzVbugxj3SsJ/K5ZZGKKFmHvaJ+yvJ42QJnqX107XotQSIHtIQIcDAifdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e358ca40bbc534f4d9bbd1c8fc3e14e8fa432e3a3b31068d0979e71dbaa892cc","last_reissued_at":"2026-07-05T05:04:33.780846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:33.780846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.03915","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:04:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XRCQXZLH+Woo35H4NDT2J3PLZtU9uqGB1OZFa4n2/sM/S5Kl1DMnSW6FyGhD/rFQG2cIjNG79WKp6gHBm3qKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T09:25:18.593143Z"},"content_sha256":"412d0b857d55ee880a9642930737b6a73bd6f7e55714a06864132d3ce07df460","schema_version":"1.0","event_id":"sha256:412d0b857d55ee880a9642930737b6a73bd6f7e55714a06864132d3ce07df460"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4NMMUQF3YU2PJWN32HEPYPQU5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Short Text Pre-training with Extended Token Classification for E-commerce Query Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bing Yin, Chen Luo, Danqing Zhang, Haoming Jiang, Qingyu Yin, Rahul Goutam, Tianyu Cao, Xianfeng Tang, Zheng Li","submitted_at":"2022-10-08T04:50:04Z","abstract_excerpt":"E-commerce query understanding is the process of inferring the shopping intent of customers by extracting semantic meaning from their search queries. The recent progress of pre-trained masked language models (MLM) in natural language processing is extremely attractive for developing effective query understanding models. Specifically, MLM learns contextual text embedding via recovering the masked tokens in the sentences. Such a pre-training process relies on the sufficient contextual information. It is, however, less effective for search queries, which are usually short text. When applying mask"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03915","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/2210.03915/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:04:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6QyCHa3cJ6QKHVBXumesKC6KfFSF4YHZJUzP+M+YStpSOQkS1vwPoxF4tpUS7uEUeTkoPzSwvQRxs/zcESUYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T09:25:18.593535Z"},"content_sha256":"69b7ed8c771c18be30f459ff3c28784af97fee886dc65d75be310ee25e2161fb","schema_version":"1.0","event_id":"sha256:69b7ed8c771c18be30f459ff3c28784af97fee886dc65d75be310ee25e2161fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NMMUQF3YU2PJWN32HEPYPQU5D/bundle.json","state_url":"https://pith.science/pith/4NMMUQF3YU2PJWN32HEPYPQU5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NMMUQF3YU2PJWN32HEPYPQU5D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-20T09:25:18Z","links":{"resolver":"https://pith.science/pith/4NMMUQF3YU2PJWN32HEPYPQU5D","bundle":"https://pith.science/pith/4NMMUQF3YU2PJWN32HEPYPQU5D/bundle.json","state":"https://pith.science/pith/4NMMUQF3YU2PJWN32HEPYPQU5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NMMUQF3YU2PJWN32HEPYPQU5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4NMMUQF3YU2PJWN32HEPYPQU5D","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":"009fe03f148765fb81d3295e229e69a82366d77bcc23865eeb8330155dcb45cf","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-08T04:50:04Z","title_canon_sha256":"73eea3766bd871f73321d31cb81d8d19dcfd48fc882e08ca715649cbfbcd2513"},"schema_version":"1.0","source":{"id":"2210.03915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03915","created_at":"2026-07-05T05:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03915v1","created_at":"2026-07-05T05:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03915","created_at":"2026-07-05T05:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"4NMMUQF3YU2P","created_at":"2026-07-05T05:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"4NMMUQF3YU2PJWN3","created_at":"2026-07-05T05:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"4NMMUQF3","created_at":"2026-07-05T05:04:33Z"}],"graph_snapshots":[{"event_id":"sha256:69b7ed8c771c18be30f459ff3c28784af97fee886dc65d75be310ee25e2161fb","target":"graph","created_at":"2026-07-05T05:04:33Z","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/2210.03915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"E-commerce query understanding is the process of inferring the shopping intent of customers by extracting semantic meaning from their search queries. The recent progress of pre-trained masked language models (MLM) in natural language processing is extremely attractive for developing effective query understanding models. Specifically, MLM learns contextual text embedding via recovering the masked tokens in the sentences. Such a pre-training process relies on the sufficient contextual information. It is, however, less effective for search queries, which are usually short text. When applying mask","authors_text":"Bing Yin, Chen Luo, Danqing Zhang, Haoming Jiang, Qingyu Yin, Rahul Goutam, Tianyu Cao, Xianfeng Tang, Zheng Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-08T04:50:04Z","title":"Short Text Pre-training with Extended Token Classification for E-commerce Query Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03915","kind":"arxiv","version":1},"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":"sha256:412d0b857d55ee880a9642930737b6a73bd6f7e55714a06864132d3ce07df460","target":"record","created_at":"2026-07-05T05:04:33Z","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":"009fe03f148765fb81d3295e229e69a82366d77bcc23865eeb8330155dcb45cf","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-08T04:50:04Z","title_canon_sha256":"73eea3766bd871f73321d31cb81d8d19dcfd48fc882e08ca715649cbfbcd2513"},"schema_version":"1.0","source":{"id":"2210.03915","kind":"arxiv","version":1}},"canonical_sha256":"e358ca40bbc534f4d9bbd1c8fc3e14e8fa432e3a3b31068d0979e71dbaa892cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e358ca40bbc534f4d9bbd1c8fc3e14e8fa432e3a3b31068d0979e71dbaa892cc","first_computed_at":"2026-07-05T05:04:33.780846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:33.780846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3qikAwXhLwAzCB9XnkEN/S7gMo5LzVbugxj3SsJ/K5ZZGKKFmHvaJ+yvJ42QJnqX107XotQSIHtIQIcDAifdCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:33.781263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:412d0b857d55ee880a9642930737b6a73bd6f7e55714a06864132d3ce07df460","sha256:69b7ed8c771c18be30f459ff3c28784af97fee886dc65d75be310ee25e2161fb"],"state_sha256":"2c3453c03182e514f777e7093c0675f2cecdc928cd72ee05cd25a93af510efbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A0AeHazzpgDXfAJhTwCGiSylIR9iC43xU9/W3SqmKvykdIOBLnDtPDExmfokrdTAsQzQaUY03XvFZPBv4qmTCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T09:25:18.597075Z","bundle_sha256":"20561f222a9bdf632c32d4f500f6aef76782bc06b1a1941259a2255f4811ba75"}}