{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LEIY6PFE5NDJNQILZV24PIFY36","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":"8dabe9244506cc8339589fa45858b028a05a889f4aa61a812122f6dcfa06f112","cross_cats_sorted":["stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-27T02:18:36Z","title_canon_sha256":"36d2f1f612f8cdbb178a954b585dd9cff5d923ccbf01135cc64f80bcca809fd1"},"schema_version":"1.0","source":{"id":"1703.09570","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.09570","created_at":"2026-05-18T00:16:56Z"},{"alias_kind":"arxiv_version","alias_value":"1703.09570v2","created_at":"2026-05-18T00:16:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.09570","created_at":"2026-05-18T00:16:56Z"},{"alias_kind":"pith_short_12","alias_value":"LEIY6PFE5NDJ","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LEIY6PFE5NDJNQIL","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LEIY6PFE","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:91d8b44bb5d4d43efe106db15106735852e639e777ead6ae28026138e78b3e81","target":"graph","created_at":"2026-05-18T00:16:56Z","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":"The package cleanNLP provides a set of fast tools for converting a textual corpus into a set of normalized tables. The underlying natural language processing pipeline utilizes Stanford's CoreNLP library, exposing a number of annotation tasks for text written in English, French, German, and Spanish. Annotators include tokenization, part of speech tagging, named entity recognition, entity linking, sentiment analysis, dependency parsing, coreference resolution, and information extraction.","authors_text":"Taylor Arnold","cross_cats":["stat.CO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-27T02:18:36Z","title":"A Tidy Data Model for Natural Language Processing using cleanNLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.09570","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":"sha256:3a661396da84fa950f206740554fa2659e7f9d33866ec721cc25ee126758004e","target":"record","created_at":"2026-05-18T00:16:56Z","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":"8dabe9244506cc8339589fa45858b028a05a889f4aa61a812122f6dcfa06f112","cross_cats_sorted":["stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-27T02:18:36Z","title_canon_sha256":"36d2f1f612f8cdbb178a954b585dd9cff5d923ccbf01135cc64f80bcca809fd1"},"schema_version":"1.0","source":{"id":"1703.09570","kind":"arxiv","version":2}},"canonical_sha256":"59118f3ca4eb4696c10bcd75c7a0b8df9cbec7d9c789036daeaa5f01bf7e83a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59118f3ca4eb4696c10bcd75c7a0b8df9cbec7d9c789036daeaa5f01bf7e83a9","first_computed_at":"2026-05-18T00:16:56.533962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:56.533962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"76ccT5GJgUzTT/Gp26G3OoT+Eb7N9yL4Rb2IdmYXJgC2D0z0iztAbCFCjJjwxoDz+nZwp38aujUdvUiCFp05Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:56.534620Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.09570","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a661396da84fa950f206740554fa2659e7f9d33866ec721cc25ee126758004e","sha256:91d8b44bb5d4d43efe106db15106735852e639e777ead6ae28026138e78b3e81"],"state_sha256":"99a73d0072b1d72ce8fd226eb4e5d6aacec0417555068f226f1e3e5a4aa7aeef"}