{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DSZF373EDLS66KNSKOFEURLDSB","short_pith_number":"pith:DSZF373E","schema_version":"1.0","canonical_sha256":"1cb25dff641ae5ef29b2538a4a456390531bbdbb24b128ff41b4ae4afc9b4a31","source":{"kind":"arxiv","id":"1808.09308","version":1},"attestation_state":"computed","paper":{"title":"Card-660: Cambridge Rare Word Dataset - a Reliable Benchmark for Infrequent Word Representation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dimitri Kartsaklis, Mohammad Taher Pilehvar, Nigel Collier, Victor Prokhorov","submitted_at":"2018-08-28T14:01:07Z","abstract_excerpt":"Rare word representation has recently enjoyed a surge of interest, owing to the crucial role that effective handling of infrequent words can play in accurate semantic understanding. However, there is a paucity of reliable benchmarks for evaluation and comparison of these techniques. We show in this paper that the only existing benchmark (the Stanford Rare Word dataset) suffers from low-confidence annotations and limited vocabulary; hence, it does not constitute a solid comparison framework. In order to fill this evaluation gap, we propose CAmbridge Rare word Dataset (Card-660), an expert-annot"},"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":"1808.09308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T14:01:07Z","cross_cats_sorted":[],"title_canon_sha256":"c11999ab1feb9557acdefccf907e3ee31cd7a37d9eb3f4bb4de55c75e2c33831","abstract_canon_sha256":"f3be5058776118ad8ce89e80b17bee99139b8c10dfefbad3246b8452cfb02b10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:01.736378Z","signature_b64":"JPp7AcH/FSWBKQoTyjO5T/A2IdLsTZxFdp8fBCO/WxeGdFTSA85/YzOBQnX9JtGd4CXzPtwt1e68xDnUx+hiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cb25dff641ae5ef29b2538a4a456390531bbdbb24b128ff41b4ae4afc9b4a31","last_reissued_at":"2026-05-18T00:07:01.735752Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:01.735752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Card-660: Cambridge Rare Word Dataset - a Reliable Benchmark for Infrequent Word Representation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dimitri Kartsaklis, Mohammad Taher Pilehvar, Nigel Collier, Victor Prokhorov","submitted_at":"2018-08-28T14:01:07Z","abstract_excerpt":"Rare word representation has recently enjoyed a surge of interest, owing to the crucial role that effective handling of infrequent words can play in accurate semantic understanding. However, there is a paucity of reliable benchmarks for evaluation and comparison of these techniques. We show in this paper that the only existing benchmark (the Stanford Rare Word dataset) suffers from low-confidence annotations and limited vocabulary; hence, it does not constitute a solid comparison framework. In order to fill this evaluation gap, we propose CAmbridge Rare word Dataset (Card-660), an expert-annot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09308","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":""},"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":"1808.09308","created_at":"2026-05-18T00:07:01.735860+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09308v1","created_at":"2026-05-18T00:07:01.735860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09308","created_at":"2026-05-18T00:07:01.735860+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSZF373EDLS6","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSZF373EDLS66KNS","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSZF373E","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB","json":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB.json","graph_json":"https://pith.science/api/pith-number/DSZF373EDLS66KNSKOFEURLDSB/graph.json","events_json":"https://pith.science/api/pith-number/DSZF373EDLS66KNSKOFEURLDSB/events.json","paper":"https://pith.science/paper/DSZF373E"},"agent_actions":{"view_html":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB","download_json":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB.json","view_paper":"https://pith.science/paper/DSZF373E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09308&json=true","fetch_graph":"https://pith.science/api/pith-number/DSZF373EDLS66KNSKOFEURLDSB/graph.json","fetch_events":"https://pith.science/api/pith-number/DSZF373EDLS66KNSKOFEURLDSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB/action/storage_attestation","attest_author":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB/action/author_attestation","sign_citation":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB/action/citation_signature","submit_replication":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB/action/replication_record"}},"created_at":"2026-05-18T00:07:01.735860+00:00","updated_at":"2026-05-18T00:07:01.735860+00:00"}