{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BZA47KZA2EBKRZ63OFHVLVQVQ4","short_pith_number":"pith:BZA47KZA","schema_version":"1.0","canonical_sha256":"0e41cfab20d102a8e7db714f55d61587374dc3b62f5bfc3b7a2bde462c60f7b0","source":{"kind":"arxiv","id":"1902.00821","version":2},"attestation_state":"computed","paper":{"title":"Review Conversational Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Liu, Hu Xu, Lei Shu, Philip S. Yu","submitted_at":"2019-02-03T00:32:46Z","abstract_excerpt":"Inspired by conversational reading comprehension (CRC), this paper studies a novel task of leveraging reviews as a source to build an agent that can answer multi-turn questions from potential consumers of online businesses. We first build a review CRC dataset and then propose a novel task-aware pre-tuning step running between language model (e.g., BERT) pre-training and domain-specific fine-tuning. The proposed pre-tuning requires no data annotation, but can greatly enhance the performance on our end task. Experimental results show that the proposed approach is highly effective and has competi"},"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":"1902.00821","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-03T00:32:46Z","cross_cats_sorted":[],"title_canon_sha256":"ef0c7fa5591d10544a084b1e76cb4a14d0c1eb598a9fb546418e63f9f79fec86","abstract_canon_sha256":"319ba683b2a58a0182f98f6f3249f04bc6823e5f14b94d5176d583a9ffac125e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:25.542772Z","signature_b64":"pn9uDLTmJWdIcfpbP35Acq1/hiiSxZTKyOfwk/HYAG5+82yG4cyPbEI0bnJi47hrlj4sS4erWN2wjDs4eIPkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e41cfab20d102a8e7db714f55d61587374dc3b62f5bfc3b7a2bde462c60f7b0","last_reissued_at":"2026-07-05T00:17:25.542344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:25.542344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Review Conversational Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Liu, Hu Xu, Lei Shu, Philip S. Yu","submitted_at":"2019-02-03T00:32:46Z","abstract_excerpt":"Inspired by conversational reading comprehension (CRC), this paper studies a novel task of leveraging reviews as a source to build an agent that can answer multi-turn questions from potential consumers of online businesses. We first build a review CRC dataset and then propose a novel task-aware pre-tuning step running between language model (e.g., BERT) pre-training and domain-specific fine-tuning. The proposed pre-tuning requires no data annotation, but can greatly enhance the performance on our end task. Experimental results show that the proposed approach is highly effective and has competi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00821","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/1902.00821/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":"1902.00821","created_at":"2026-07-05T00:17:25.542414+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00821v2","created_at":"2026-07-05T00:17:25.542414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00821","created_at":"2026-07-05T00:17:25.542414+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZA47KZA2EBK","created_at":"2026-07-05T00:17:25.542414+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZA47KZA2EBKRZ63","created_at":"2026-07-05T00:17:25.542414+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZA47KZA","created_at":"2026-07-05T00:17:25.542414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09166","citing_title":"Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey","ref_index":222,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZA47KZA2EBKRZ63OFHVLVQVQ4","json":"https://pith.science/pith/BZA47KZA2EBKRZ63OFHVLVQVQ4.json","graph_json":"https://pith.science/api/pith-number/BZA47KZA2EBKRZ63OFHVLVQVQ4/graph.json","events_json":"https://pith.science/api/pith-number/BZA47KZA2EBKRZ63OFHVLVQVQ4/events.json","paper":"https://pith.science/paper/BZA47KZA"},"agent_actions":{"view_html":"https://pith.science/pith/BZA47KZA2EBKRZ63OFHVLVQVQ4","download_json":"https://pith.science/pith/BZA47KZA2EBKRZ63OFHVLVQVQ4.json","view_paper":"https://pith.science/paper/BZA47KZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00821&json=true","fetch_graph":"https://pith.science/api/pith-number/BZA47KZA2EBKRZ63OFHVLVQVQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/BZA47KZA2EBKRZ63OFHVLVQVQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZA47KZA2EBKRZ63OFHVLVQVQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZA47KZA2EBKRZ63OFHVLVQVQ4/action/storage_attestation","attest_author":"https://pith.science/pith/BZA47KZA2EBKRZ63OFHVLVQVQ4/action/author_attestation","sign_citation":"https://pith.science/pith/BZA47KZA2EBKRZ63OFHVLVQVQ4/action/citation_signature","submit_replication":"https://pith.science/pith/BZA47KZA2EBKRZ63OFHVLVQVQ4/action/replication_record"}},"created_at":"2026-07-05T00:17:25.542414+00:00","updated_at":"2026-07-05T00:17:25.542414+00:00"}