{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PQO4RAFKJ4XIJKBQCMFEFGTUDE","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":"f46348a572687ebf731b7a502821abe0a7612a74582cfafbe96d4ad26ee782cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-05T11:49:40Z","title_canon_sha256":"86c645b1a195691265556cd3da599e3764653d0ec72535aa388950a084b88b38"},"schema_version":"1.0","source":{"id":"1909.02339","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02339","created_at":"2026-07-05T00:55:58Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02339v2","created_at":"2026-07-05T00:55:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02339","created_at":"2026-07-05T00:55:58Z"},{"alias_kind":"pith_short_12","alias_value":"PQO4RAFKJ4XI","created_at":"2026-07-05T00:55:58Z"},{"alias_kind":"pith_short_16","alias_value":"PQO4RAFKJ4XIJKBQ","created_at":"2026-07-05T00:55:58Z"},{"alias_kind":"pith_short_8","alias_value":"PQO4RAFK","created_at":"2026-07-05T00:55:58Z"}],"graph_snapshots":[{"event_id":"sha256:026626b66e7a83cbcbdca27eecbd5391251c3b30ab895f0f782db5a2e5b2eb79","target":"graph","created_at":"2026-07-05T00:55:58Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.02339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised pretraining models have been shown to facilitate a wide range of downstream NLP applications. These models, however, retain some of the limitations of traditional static word embeddings. In particular, they encode only the distributional knowledge available in raw text corpora, incorporated through language modeling objectives. In this work, we complement such distributional knowledge with external lexical knowledge, that is, we integrate the discrete knowledge on word-level semantic similarity into pretraining. To this end, we generalize the standard BERT model to a multi-task le","authors_text":"Anna Korhonen, Anne Lauscher, Edoardo Maria Ponti, Goran Glava\\v{s}, Ivan Vuli\\'c","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-05T11:49:40Z","title":"Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02339","kind":"arxiv","version":2},"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:edd77b3644081411b0764ef55726e372f2b6d3189b958d327f031be662684509","target":"record","created_at":"2026-07-05T00:55:58Z","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":"f46348a572687ebf731b7a502821abe0a7612a74582cfafbe96d4ad26ee782cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-05T11:49:40Z","title_canon_sha256":"86c645b1a195691265556cd3da599e3764653d0ec72535aa388950a084b88b38"},"schema_version":"1.0","source":{"id":"1909.02339","kind":"arxiv","version":2}},"canonical_sha256":"7c1dc880aa4f2e84a830130a429a741926efd75193dae1070a2b28431a4c8a57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c1dc880aa4f2e84a830130a429a741926efd75193dae1070a2b28431a4c8a57","first_computed_at":"2026-07-05T00:55:58.762075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:55:58.762075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oSVjlJMpC911bJCxV7tLgwJ6UQb/UKHkoBtY6JYz6hyjqx6vC2YT/JQv7hd+OVt2lzcH2DYO7oCliIVm1deGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:55:58.762473Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.02339","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:edd77b3644081411b0764ef55726e372f2b6d3189b958d327f031be662684509","sha256:026626b66e7a83cbcbdca27eecbd5391251c3b30ab895f0f782db5a2e5b2eb79"],"state_sha256":"a98e39f45a1a113f9806f2d8579f36d925e804b7f0a8c81a92dc22366f212ad1"}