{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:PHZXWSDYGL6K2F4MVEK2KVM7FT","short_pith_number":"pith:PHZXWSDY","schema_version":"1.0","canonical_sha256":"79f37b487832fcad178ca915a5559f2cd058c1a78423bff0cbcd19a6d3ab4dae","source":{"kind":"arxiv","id":"1402.6516","version":1},"attestation_state":"computed","paper":{"title":"Modelling the Lexicon in Unsupervised Part of Speech Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Greg Dubbin, Phil Blunsom","submitted_at":"2014-02-26T12:37:04Z","abstract_excerpt":"Automatically inducing the syntactic part-of-speech categories for words in text is a fundamental task in Computational Linguistics. While the performance of unsupervised tagging models has been slowly improving, current state-of-the-art systems make the obviously incorrect assumption that all tokens of a given word type must share a single part-of-speech tag. This one-tag-per-type heuristic counters the tendency of Hidden Markov Model based taggers to over generate tags for a given word type. However, it is clearly incompatible with basic syntactic theory. In this paper we extend a state-of-t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1402.6516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-02-26T12:37:04Z","cross_cats_sorted":[],"title_canon_sha256":"57c1ace83669d5f5723a6e9fb4f1091d0fb6b67c901881f3f59bcee5aa0d67c2","abstract_canon_sha256":"66fc35bb6c4b0d17e1c010775da0b5d4457613a7b3eecf47b428fbd1f74d7065"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:57:44.366055Z","signature_b64":"qX/hFi2zuzD647bkJoP5EQ9c990Wsmjq7c8XLUo5Je9U0KD8PyM/jGEgHnLuQQ/DRYP8MyOW8tgySUtWbU/eCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79f37b487832fcad178ca915a5559f2cd058c1a78423bff0cbcd19a6d3ab4dae","last_reissued_at":"2026-05-18T02:57:44.365577Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:57:44.365577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modelling the Lexicon in Unsupervised Part of Speech Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Greg Dubbin, Phil Blunsom","submitted_at":"2014-02-26T12:37:04Z","abstract_excerpt":"Automatically inducing the syntactic part-of-speech categories for words in text is a fundamental task in Computational Linguistics. While the performance of unsupervised tagging models has been slowly improving, current state-of-the-art systems make the obviously incorrect assumption that all tokens of a given word type must share a single part-of-speech tag. This one-tag-per-type heuristic counters the tendency of Hidden Markov Model based taggers to over generate tags for a given word type. However, it is clearly incompatible with basic syntactic theory. In this paper we extend a state-of-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.6516","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1402.6516","created_at":"2026-05-18T02:57:44.365658+00:00"},{"alias_kind":"arxiv_version","alias_value":"1402.6516v1","created_at":"2026-05-18T02:57:44.365658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.6516","created_at":"2026-05-18T02:57:44.365658+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHZXWSDYGL6K","created_at":"2026-05-18T12:28:43.426989+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHZXWSDYGL6K2F4M","created_at":"2026-05-18T12:28:43.426989+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHZXWSDY","created_at":"2026-05-18T12:28:43.426989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT","json":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT.json","graph_json":"https://pith.science/api/pith-number/PHZXWSDYGL6K2F4MVEK2KVM7FT/graph.json","events_json":"https://pith.science/api/pith-number/PHZXWSDYGL6K2F4MVEK2KVM7FT/events.json","paper":"https://pith.science/paper/PHZXWSDY"},"agent_actions":{"view_html":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT","download_json":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT.json","view_paper":"https://pith.science/paper/PHZXWSDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1402.6516&json=true","fetch_graph":"https://pith.science/api/pith-number/PHZXWSDYGL6K2F4MVEK2KVM7FT/graph.json","fetch_events":"https://pith.science/api/pith-number/PHZXWSDYGL6K2F4MVEK2KVM7FT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT/action/storage_attestation","attest_author":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT/action/author_attestation","sign_citation":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT/action/citation_signature","submit_replication":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT/action/replication_record"}},"created_at":"2026-05-18T02:57:44.365658+00:00","updated_at":"2026-05-18T02:57:44.365658+00:00"}