{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PJR3B4CZAGXTYTPZB2XG7ATDIG","short_pith_number":"pith:PJR3B4CZ","schema_version":"1.0","canonical_sha256":"7a63b0f05901af3c4df90eae6f8263419149a642e0a3040fc40d93654f42a747","source":{"kind":"arxiv","id":"2104.06893","version":2},"attestation_state":"computed","paper":{"title":"I Wish I Would Have Loved This One, But I Didn't -- A Multilingual Dataset for Counterfactual Detection in Product Reviews","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Danushka Bollegala, James O'Neill, Motoko Kubota, Polina Rozenshtein, Ryuichi Kiryo","submitted_at":"2021-04-14T14:38:36Z","abstract_excerpt":"Counterfactual statements describe events that did not or cannot take place. We consider the problem of counterfactual detection (CFD) in product reviews. For this purpose, we annotate a multilingual CFD dataset from Amazon product reviews covering counterfactual statements written in English, German, and Japanese languages. The dataset is unique as it contains counterfactuals in multiple languages, covers a new application area of e-commerce reviews, and provides high quality professional annotations. We train CFD models using different text representation methods and classifiers. We find tha"},"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":"2104.06893","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T14:38:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7068b79bb4eb4f601bdd34ba41e9d0e7ac9633e18e5f5e6ddc1d6f4182b19d8b","abstract_canon_sha256":"4169795538ca6209fb072f900a94192e5bea3f6b336860ad63553fbe711bb20c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:54.924619Z","signature_b64":"HPf/tWop5BlXlt1n7neAe0SftBfcQaQR5nPDNnlW2MBNITvXfmjDk9pPu0cINN6zNZqs5lW1+iljkPQtP39cCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a63b0f05901af3c4df90eae6f8263419149a642e0a3040fc40d93654f42a747","last_reissued_at":"2026-07-05T03:14:54.924132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:54.924132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"I Wish I Would Have Loved This One, But I Didn't -- A Multilingual Dataset for Counterfactual Detection in Product Reviews","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Danushka Bollegala, James O'Neill, Motoko Kubota, Polina Rozenshtein, Ryuichi Kiryo","submitted_at":"2021-04-14T14:38:36Z","abstract_excerpt":"Counterfactual statements describe events that did not or cannot take place. We consider the problem of counterfactual detection (CFD) in product reviews. For this purpose, we annotate a multilingual CFD dataset from Amazon product reviews covering counterfactual statements written in English, German, and Japanese languages. The dataset is unique as it contains counterfactuals in multiple languages, covers a new application area of e-commerce reviews, and provides high quality professional annotations. We train CFD models using different text representation methods and classifiers. We find tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06893","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/2104.06893/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":"2104.06893","created_at":"2026-07-05T03:14:54.924188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06893v2","created_at":"2026-07-05T03:14:54.924188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06893","created_at":"2026-07-05T03:14:54.924188+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJR3B4CZAGXT","created_at":"2026-07-05T03:14:54.924188+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJR3B4CZAGXTYTPZ","created_at":"2026-07-05T03:14:54.924188+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJR3B4CZ","created_at":"2026-07-05T03:14:54.924188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25674","citing_title":"BitNet Text Embeddings","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03563","citing_title":"Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2405.17428","citing_title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","ref_index":153,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJR3B4CZAGXTYTPZB2XG7ATDIG","json":"https://pith.science/pith/PJR3B4CZAGXTYTPZB2XG7ATDIG.json","graph_json":"https://pith.science/api/pith-number/PJR3B4CZAGXTYTPZB2XG7ATDIG/graph.json","events_json":"https://pith.science/api/pith-number/PJR3B4CZAGXTYTPZB2XG7ATDIG/events.json","paper":"https://pith.science/paper/PJR3B4CZ"},"agent_actions":{"view_html":"https://pith.science/pith/PJR3B4CZAGXTYTPZB2XG7ATDIG","download_json":"https://pith.science/pith/PJR3B4CZAGXTYTPZB2XG7ATDIG.json","view_paper":"https://pith.science/paper/PJR3B4CZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06893&json=true","fetch_graph":"https://pith.science/api/pith-number/PJR3B4CZAGXTYTPZB2XG7ATDIG/graph.json","fetch_events":"https://pith.science/api/pith-number/PJR3B4CZAGXTYTPZB2XG7ATDIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJR3B4CZAGXTYTPZB2XG7ATDIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJR3B4CZAGXTYTPZB2XG7ATDIG/action/storage_attestation","attest_author":"https://pith.science/pith/PJR3B4CZAGXTYTPZB2XG7ATDIG/action/author_attestation","sign_citation":"https://pith.science/pith/PJR3B4CZAGXTYTPZB2XG7ATDIG/action/citation_signature","submit_replication":"https://pith.science/pith/PJR3B4CZAGXTYTPZB2XG7ATDIG/action/replication_record"}},"created_at":"2026-07-05T03:14:54.924188+00:00","updated_at":"2026-07-05T03:14:54.924188+00:00"}