{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DSZF373EDLS66KNSKOFEURLDSB","short_pith_number":"pith:DSZF373E","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"},"canonical_sha256":"1cb25dff641ae5ef29b2538a4a456390531bbdbb24b128ff41b4ae4afc9b4a31","source":{"kind":"arxiv","id":"1808.09308","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09308","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09308v1","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09308","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"DSZF373EDLS6","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DSZF373EDLS66KNS","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DSZF373E","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DSZF373EDLS66KNSKOFEURLDSB","target":"record","payload":{"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"},"canonical_sha256":"1cb25dff641ae5ef29b2538a4a456390531bbdbb24b128ff41b4ae4afc9b4a31","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"},"source_kind":"arxiv","source_id":"1808.09308","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":"2026-05-18T00:07:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9DCVv5LBBke61/8C+jOml7hVWfMlvvBQaBb8Lq3jzAGW8A9IOSu9P1PqQAhd/Os1iFzVHXdLaqCnzEg2EIXqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T06:33:37.023537Z"},"content_sha256":"5a26878c3fa07b094a1532a8f003a841a9a9f5cfaf01620652fc2a228efce7c8","schema_version":"1.0","event_id":"sha256:5a26878c3fa07b094a1532a8f003a841a9a9f5cfaf01620652fc2a228efce7c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DSZF373EDLS66KNSKOFEURLDSB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ZXTNkaHHOgClPVz3o7pIrkyCPTwzfVfVJHdt2Y8/MuKQTkkOyX1IVt1reMzQcgRGvA7e5jbB0845lgbA0dJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T06:33:37.023881Z"},"content_sha256":"22e69947ff2a3efe03a4451ba26d42bed208729b124b6a0df736d41031589ab4","schema_version":"1.0","event_id":"sha256:22e69947ff2a3efe03a4451ba26d42bed208729b124b6a0df736d41031589ab4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB/bundle.json","state_url":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSZF373EDLS66KNSKOFEURLDSB/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":"2026-07-04T06:33:37Z","links":{"resolver":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB","bundle":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB/bundle.json","state":"https://pith.science/pith/DSZF373EDLS66KNSKOFEURLDSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSZF373EDLS66KNSKOFEURLDSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DSZF373EDLS66KNSKOFEURLDSB","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":"f3be5058776118ad8ce89e80b17bee99139b8c10dfefbad3246b8452cfb02b10","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T14:01:07Z","title_canon_sha256":"c11999ab1feb9557acdefccf907e3ee31cd7a37d9eb3f4bb4de55c75e2c33831"},"schema_version":"1.0","source":{"id":"1808.09308","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09308","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09308v1","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09308","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"DSZF373EDLS6","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DSZF373EDLS66KNS","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DSZF373E","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:22e69947ff2a3efe03a4451ba26d42bed208729b124b6a0df736d41031589ab4","target":"graph","created_at":"2026-05-18T00:07:01Z","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"},"paper":{"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","authors_text":"Dimitri Kartsaklis, Mohammad Taher Pilehvar, Nigel Collier, Victor Prokhorov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T14:01:07Z","title":"Card-660: Cambridge Rare Word Dataset - a Reliable Benchmark for Infrequent Word Representation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09308","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":"sha256:5a26878c3fa07b094a1532a8f003a841a9a9f5cfaf01620652fc2a228efce7c8","target":"record","created_at":"2026-05-18T00:07:01Z","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":"f3be5058776118ad8ce89e80b17bee99139b8c10dfefbad3246b8452cfb02b10","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T14:01:07Z","title_canon_sha256":"c11999ab1feb9557acdefccf907e3ee31cd7a37d9eb3f4bb4de55c75e2c33831"},"schema_version":"1.0","source":{"id":"1808.09308","kind":"arxiv","version":1}},"canonical_sha256":"1cb25dff641ae5ef29b2538a4a456390531bbdbb24b128ff41b4ae4afc9b4a31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cb25dff641ae5ef29b2538a4a456390531bbdbb24b128ff41b4ae4afc9b4a31","first_computed_at":"2026-05-18T00:07:01.735752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:01.735752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JPp7AcH/FSWBKQoTyjO5T/A2IdLsTZxFdp8fBCO/WxeGdFTSA85/YzOBQnX9JtGd4CXzPtwt1e68xDnUx+hiCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:01.736378Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.09308","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a26878c3fa07b094a1532a8f003a841a9a9f5cfaf01620652fc2a228efce7c8","sha256:22e69947ff2a3efe03a4451ba26d42bed208729b124b6a0df736d41031589ab4"],"state_sha256":"30392f94116a1639f3f7505062e694efcd6e1aef366f72397225da26c1295bf4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lKkGdDt0iedS+Y7kpr41mTRYE6JW8+2aXeTq/9keulH2AWF5s/4LdX2I0rv+CXUUy0/+iKhQ7sjXtpEZ43srDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T06:33:37.025896Z","bundle_sha256":"28ad0390172f7f986b850b2320ff92d69505f634599938d3cd2faf0e979d582b"}}