{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:1995:JJDIIP7YVZVWMQY74L6PINDMMQ","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":"c2732f77c8eb98d685bfb0d1bacf8b835798a3f685a9c18153e1c5757b4ffcc1","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1995-02-13T13:17:20Z","title_canon_sha256":"fe222c2a5de8d9fe4a6a48b6244c7d4ef78f8be52813b78552ecda881cb06a50"},"schema_version":"1.0","source":{"id":"cmp-lg/9502012","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cmp-lg/9502012","created_at":"2026-05-18T01:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9502012v2","created_at":"2026-05-18T01:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9502012","created_at":"2026-05-18T01:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"JJDIIP7YVZVW","created_at":"2026-05-18T12:25:47Z"},{"alias_kind":"pith_short_16","alias_value":"JJDIIP7YVZVWMQY7","created_at":"2026-05-18T12:25:47Z"},{"alias_kind":"pith_short_8","alias_value":"JJDIIP7Y","created_at":"2026-05-18T12:25:47Z"}],"graph_snapshots":[{"event_id":"sha256:20bd3d4cdfe228a8377df5d21c0541d826324d37d2b38d3177a4b86f1b5360fe","target":"graph","created_at":"2026-05-18T01:07:24Z","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":"There are two main methodologies for constructing the knowledge base of a natural language analyser: the linguistic and the data-driven. Recent state-of-the-art part-of-speech taggers are based on the data-driven approach. Because of the known feasibility of the linguistic rule-based approach at related levels of description, the success of the data-driven approach in part-of-speech analysis may appear surprising. In this paper, a case is made for the syntactic nature of part-of-speech tagging. A new tagger of English that uses only linguistic distributional rules is outlined and empirically e","authors_text":"Atro Voutilainen (Research Unit for Multilingual Language Technology, Finland), University of Helsinki","cross_cats":["cs.CL"],"headline":"","license":"","primary_cat":"cmp-lg","submitted_at":"1995-02-13T13:17:20Z","title":"A syntax-based part-of-speech analyser"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9502012","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":"sha256:4a4aeb714af1dbab1a79e648df227269abc228082c9d2e83841b72e2e2eaf3aa","target":"record","created_at":"2026-05-18T01:07:24Z","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":"c2732f77c8eb98d685bfb0d1bacf8b835798a3f685a9c18153e1c5757b4ffcc1","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1995-02-13T13:17:20Z","title_canon_sha256":"fe222c2a5de8d9fe4a6a48b6244c7d4ef78f8be52813b78552ecda881cb06a50"},"schema_version":"1.0","source":{"id":"cmp-lg/9502012","kind":"arxiv","version":2}},"canonical_sha256":"4a46843ff8ae6b66431fe2fcf4346c6425381a56db81e64541180433ae5be76d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a46843ff8ae6b66431fe2fcf4346c6425381a56db81e64541180433ae5be76d","first_computed_at":"2026-05-18T01:07:24.180473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:07:24.180473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G8Gfm3YpxGhlUx8S3gKnEL9tlVS4cw/A5aTMQN375zkwiqZEodHQtztFKTl2P81B4JQ8HOhHx5RNP8l0MRINDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:07:24.180932Z","signed_message":"canonical_sha256_bytes"},"source_id":"cmp-lg/9502012","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a4aeb714af1dbab1a79e648df227269abc228082c9d2e83841b72e2e2eaf3aa","sha256:20bd3d4cdfe228a8377df5d21c0541d826324d37d2b38d3177a4b86f1b5360fe"],"state_sha256":"47404b21d442c7c9e43d10a830176cccd9630a5280a7bb7b0a98708dc20a262c"}