{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZXY2W3G6DHYZKTTKZIWHSFRWM3","short_pith_number":"pith:ZXY2W3G6","schema_version":"1.0","canonical_sha256":"cdf1ab6cde19f1954e6aca2c79163666deb98f793c2f657f0f317cb15fcfd88f","source":{"kind":"arxiv","id":"2303.08601","version":2},"attestation_state":"computed","paper":{"title":"GCRE-GPT: A Generative Model for Comparative Relation Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aixin Sun, Hengran Zhang, Xuying Meng, Yequan Wang","submitted_at":"2023-03-15T13:15:22Z","abstract_excerpt":"Given comparative text, comparative relation extraction aims to extract two targets (\\eg two cameras) in comparison and the aspect they are compared for (\\eg image quality). The extracted comparative relations form the basis of further opinion analysis.Existing solutions formulate this task as a sequence labeling task, to extract targets and aspects. However, they cannot directly extract comparative relation(s) from text. In this paper, we show that comparative relations can be directly extracted with high accuracy, by generative model. Based on GPT-2, we propose a Generation-based Comparative"},"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":"2303.08601","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-15T13:15:22Z","cross_cats_sorted":[],"title_canon_sha256":"a7c255c7bf915583175acf729b0f222cfc011d6e45f43ca9bd418d966ee2fbdf","abstract_canon_sha256":"2fbb8c0f30378e197ad5b01e11e378d26803687767a8ec29c38a84fe7e5d3fc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:12.880751Z","signature_b64":"CJ1IXR5FoL8VtfdYNdHlZQYypm2ya5wBxs8YzfimAjY1fx0hu73E1NehmH2l2lXTbvL00P6tOsrLgzUKlfbrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdf1ab6cde19f1954e6aca2c79163666deb98f793c2f657f0f317cb15fcfd88f","last_reissued_at":"2026-07-05T08:37:12.880402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:12.880402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GCRE-GPT: A Generative Model for Comparative Relation Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aixin Sun, Hengran Zhang, Xuying Meng, Yequan Wang","submitted_at":"2023-03-15T13:15:22Z","abstract_excerpt":"Given comparative text, comparative relation extraction aims to extract two targets (\\eg two cameras) in comparison and the aspect they are compared for (\\eg image quality). The extracted comparative relations form the basis of further opinion analysis.Existing solutions formulate this task as a sequence labeling task, to extract targets and aspects. However, they cannot directly extract comparative relation(s) from text. In this paper, we show that comparative relations can be directly extracted with high accuracy, by generative model. Based on GPT-2, we propose a Generation-based Comparative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08601","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/2303.08601/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":"2303.08601","created_at":"2026-07-05T08:37:12.880457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08601v2","created_at":"2026-07-05T08:37:12.880457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08601","created_at":"2026-07-05T08:37:12.880457+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXY2W3G6DHYZ","created_at":"2026-07-05T08:37:12.880457+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXY2W3G6DHYZKTTK","created_at":"2026-07-05T08:37:12.880457+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXY2W3G6","created_at":"2026-07-05T08:37:12.880457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04733","citing_title":"\"This Suits You the Best\": Query Focused Comparative Explainable Summarization","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXY2W3G6DHYZKTTKZIWHSFRWM3","json":"https://pith.science/pith/ZXY2W3G6DHYZKTTKZIWHSFRWM3.json","graph_json":"https://pith.science/api/pith-number/ZXY2W3G6DHYZKTTKZIWHSFRWM3/graph.json","events_json":"https://pith.science/api/pith-number/ZXY2W3G6DHYZKTTKZIWHSFRWM3/events.json","paper":"https://pith.science/paper/ZXY2W3G6"},"agent_actions":{"view_html":"https://pith.science/pith/ZXY2W3G6DHYZKTTKZIWHSFRWM3","download_json":"https://pith.science/pith/ZXY2W3G6DHYZKTTKZIWHSFRWM3.json","view_paper":"https://pith.science/paper/ZXY2W3G6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08601&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXY2W3G6DHYZKTTKZIWHSFRWM3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXY2W3G6DHYZKTTKZIWHSFRWM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXY2W3G6DHYZKTTKZIWHSFRWM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXY2W3G6DHYZKTTKZIWHSFRWM3/action/storage_attestation","attest_author":"https://pith.science/pith/ZXY2W3G6DHYZKTTKZIWHSFRWM3/action/author_attestation","sign_citation":"https://pith.science/pith/ZXY2W3G6DHYZKTTKZIWHSFRWM3/action/citation_signature","submit_replication":"https://pith.science/pith/ZXY2W3G6DHYZKTTKZIWHSFRWM3/action/replication_record"}},"created_at":"2026-07-05T08:37:12.880457+00:00","updated_at":"2026-07-05T08:37:12.880457+00:00"}