{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:YBPAI5MP6XVQSOIAKOQXQJC6TI","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":"a3adfed3f5a4a7a7a4bf6e39697e4368266ac12ee31b17711cf8313b3bd0ce5b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-30T20:52:48Z","title_canon_sha256":"595a9ad73e6c77ac12c4c0927230fa65173af6e68a5bdebe7e06c1d07279f46a"},"schema_version":"1.0","source":{"id":"1410.8553","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.8553","created_at":"2026-05-18T02:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"1410.8553v1","created_at":"2026-05-18T02:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.8553","created_at":"2026-05-18T02:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"YBPAI5MP6XVQ","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_16","alias_value":"YBPAI5MP6XVQSOIA","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_8","alias_value":"YBPAI5MP","created_at":"2026-05-18T12:28:57Z"}],"graph_snapshots":[{"event_id":"sha256:ec8794984f881277033049b93862615280c2b7dc145bddf4cc442fa5d447dbd7","target":"graph","created_at":"2026-05-18T02:38:59Z","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":"When digitizing a print bilingual dictionary, whether via optical character recognition or manual entry, it is inevitable that errors are introduced into the electronic version that is created. We investigate automating the process of detecting errors in an XML representation of a digitized print dictionary using a hybrid approach that combines rule-based, feature-based, and language model-based methods. We investigate combining methods and show that using random forests is a promising approach. We find that in isolation, unsupervised methods rival the performance of supervised methods. Random","authors_text":"David Doermann, David Zajic, Michael Bloodgood, Paul Rodrigues, Peng Ye","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-30T20:52:48Z","title":"A random forest system combination approach for error detection in digital dictionaries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.8553","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:cfcaaa9131a01c4ac1bc2d16cd35922736e411a61129a8274b0323105f69bd7c","target":"record","created_at":"2026-05-18T02:38:59Z","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":"a3adfed3f5a4a7a7a4bf6e39697e4368266ac12ee31b17711cf8313b3bd0ce5b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-30T20:52:48Z","title_canon_sha256":"595a9ad73e6c77ac12c4c0927230fa65173af6e68a5bdebe7e06c1d07279f46a"},"schema_version":"1.0","source":{"id":"1410.8553","kind":"arxiv","version":1}},"canonical_sha256":"c05e04758ff5eb09390053a178245e9a0e74fc5963d03df72b02097d63bd7f57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c05e04758ff5eb09390053a178245e9a0e74fc5963d03df72b02097d63bd7f57","first_computed_at":"2026-05-18T02:38:59.038687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:38:59.038687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6vqOzqNWbwVAsoWcBp8b953HkrLDbBZWRElF/hgrn2N6N+fI8LrHCUqxJ+2JFGLsy3UEG2adIfRLGzKMOsfMCg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:38:59.039189Z","signed_message":"canonical_sha256_bytes"},"source_id":"1410.8553","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfcaaa9131a01c4ac1bc2d16cd35922736e411a61129a8274b0323105f69bd7c","sha256:ec8794984f881277033049b93862615280c2b7dc145bddf4cc442fa5d447dbd7"],"state_sha256":"411bc116555f752acae29dd7ceca8d5b961210a5d533fb26a47e98e79a1d0b0d"}