{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WEIUXTM7LI3GC2WWUA2LSCMNQU","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":"c47d508226a9f4c0a9e9803b6d762be8ac5610ee9234a068b1f4b1d2211f878b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-31T11:01:02Z","title_canon_sha256":"4ec5f73c72cdb1faa6879a10109c06d7e53601c2dab62ff1b91266e8e0192d72"},"schema_version":"1.0","source":{"id":"1812.11760","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.11760","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"arxiv_version","alias_value":"1812.11760v2","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11760","created_at":"2026-05-17T23:44:21Z"},{"alias_kind":"pith_short_12","alias_value":"WEIUXTM7LI3G","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WEIUXTM7LI3GC2WW","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WEIUXTM7","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:a4dd133ba27b9d14af06658eef57139a11d21fe1fb902bca7440e42390abad86","target":"graph","created_at":"2026-05-17T23:44:21Z","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":"We show that constituency parsing benefits from unsupervised pre-training across a variety of languages and a range of pre-training conditions. We first compare the benefits of no pre-training, fastText, ELMo, and BERT for English and find that BERT outperforms ELMo, in large part due to increased model capacity, whereas ELMo in turn outperforms the non-contextual fastText embeddings. We also find that pre-training is beneficial across all 11 languages tested; however, large model sizes (more than 100 million parameters) make it computationally expensive to train separate models for each langu","authors_text":"Dan Klein, Nikita Kitaev, Steven Cao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-31T11:01:02Z","title":"Multilingual Constituency Parsing with Self-Attention and Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11760","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:f28ed3b2fada206f21d7e96f6fe22dd8f2a071063a9903ace0de90afeea4f0d1","target":"record","created_at":"2026-05-17T23:44:21Z","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":"c47d508226a9f4c0a9e9803b6d762be8ac5610ee9234a068b1f4b1d2211f878b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-31T11:01:02Z","title_canon_sha256":"4ec5f73c72cdb1faa6879a10109c06d7e53601c2dab62ff1b91266e8e0192d72"},"schema_version":"1.0","source":{"id":"1812.11760","kind":"arxiv","version":2}},"canonical_sha256":"b1114bcd9f5a36616ad6a034b9098d851268b5ef7c5cf0421c48537a58d13a8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1114bcd9f5a36616ad6a034b9098d851268b5ef7c5cf0421c48537a58d13a8c","first_computed_at":"2026-05-17T23:44:21.890949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:21.890949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dz+bxarjofTnwtF7t+Vx+McPYL6tlMulXKQSGsDK1mJzmWoiN4mWQRuePI/LySJTfcUT48pN4AogVV7qGBJCBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:21.891635Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.11760","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f28ed3b2fada206f21d7e96f6fe22dd8f2a071063a9903ace0de90afeea4f0d1","sha256:a4dd133ba27b9d14af06658eef57139a11d21fe1fb902bca7440e42390abad86"],"state_sha256":"f5bc0cf4479cdb3ecd4b84f0aaa6f90c751d261e7a0e5b32cf052cba572528cf"}