{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4XLOVX6SRH56HKF3VUM4WIAJTG","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":"6fe8345f07c03813f6ad86bb7e5a0700a6e5eebe3f9aedf8a45035a9082880c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-02T15:43:30Z","title_canon_sha256":"e3664bafdfe90e152197bda8fbd0cc347d542fc4505d8d258b27650ef8f70a78"},"schema_version":"1.0","source":{"id":"1708.00801","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00801","created_at":"2026-05-18T00:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00801v1","created_at":"2026-05-18T00:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00801","created_at":"2026-05-18T00:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"4XLOVX6SRH56","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4XLOVX6SRH56HKF3","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4XLOVX6S","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:6c6835c1adeb076bfbea19f7f57c638380d5ce5771b7e2cdf739af233213fd1f","target":"graph","created_at":"2026-05-18T00:38:44Z","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 study the impact of big models (in terms of the degree of lexicalization) and big data (in terms of the training corpus size) on dependency grammar induction. We experimented with L-DMV, a lexicalized version of Dependency Model with Valence and L-NDMV, our lexicalized extension of the Neural Dependency Model with Valence. We find that L-DMV only benefits from very small degrees of lexicalization and moderate sizes of training corpora. L-NDMV can benefit from big training data and lexicalization of greater degrees, especially when enhanced with good model initialization, and it achieves a r","authors_text":"Kewei Tu, Wenjuan Han, Yong Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-02T15:43:30Z","title":"Dependency Grammar Induction with Neural Lexicalization and Big Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00801","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":"sha256:77689c2c34ebdec9fb8ee1f8c0de35fcc8cb95c2eb6282f9b421a0e2ad58fc4e","target":"record","created_at":"2026-05-18T00:38:44Z","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":"6fe8345f07c03813f6ad86bb7e5a0700a6e5eebe3f9aedf8a45035a9082880c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-02T15:43:30Z","title_canon_sha256":"e3664bafdfe90e152197bda8fbd0cc347d542fc4505d8d258b27650ef8f70a78"},"schema_version":"1.0","source":{"id":"1708.00801","kind":"arxiv","version":1}},"canonical_sha256":"e5d6eadfd289fbe3a8bbad19cb200999adb2e767e1de510bd6408dbf91ae4e04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5d6eadfd289fbe3a8bbad19cb200999adb2e767e1de510bd6408dbf91ae4e04","first_computed_at":"2026-05-18T00:38:44.597440Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:44.597440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4gKTtqoLM/9z4ArgSwZ5QcSTRRVUFMzJXIpSB7feofBRPqUHiF/GKsJ1sZaxpCn9zIYfbzBOSpWf/FV3LovHCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:44.598028Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.00801","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77689c2c34ebdec9fb8ee1f8c0de35fcc8cb95c2eb6282f9b421a0e2ad58fc4e","sha256:6c6835c1adeb076bfbea19f7f57c638380d5ce5771b7e2cdf739af233213fd1f"],"state_sha256":"50d2f44fee0baae5cc11903fb75d8b92fea75ff2e76df745c0dd714d43036f0c"}