{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:PHZXWSDYGL6K2F4MVEK2KVM7FT","short_pith_number":"pith:PHZXWSDY","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"},"canonical_sha256":"79f37b487832fcad178ca915a5559f2cd058c1a78423bff0cbcd19a6d3ab4dae","source":{"kind":"arxiv","id":"1402.6516","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.6516","created_at":"2026-05-18T02:57:44Z"},{"alias_kind":"arxiv_version","alias_value":"1402.6516v1","created_at":"2026-05-18T02:57:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.6516","created_at":"2026-05-18T02:57:44Z"},{"alias_kind":"pith_short_12","alias_value":"PHZXWSDYGL6K","created_at":"2026-05-18T12:28:43Z"},{"alias_kind":"pith_short_16","alias_value":"PHZXWSDYGL6K2F4M","created_at":"2026-05-18T12:28:43Z"},{"alias_kind":"pith_short_8","alias_value":"PHZXWSDY","created_at":"2026-05-18T12:28:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:PHZXWSDYGL6K2F4MVEK2KVM7FT","target":"record","payload":{"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"},"canonical_sha256":"79f37b487832fcad178ca915a5559f2cd058c1a78423bff0cbcd19a6d3ab4dae","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"},"source_kind":"arxiv","source_id":"1402.6516","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:57:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"76uKtULqOcobWXM8WOnIchMPBk2M7tl8xAF8mhxhErxoqDaE0I3QGu9Y1z/mbON5sR7T8ZRndj6mceuzJIwiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T21:56:02.445965Z"},"content_sha256":"781aaf34ddd1b2e5a25ec2f86313c5d806866762ee9b3d4d279a5efcd895ba01","schema_version":"1.0","event_id":"sha256:781aaf34ddd1b2e5a25ec2f86313c5d806866762ee9b3d4d279a5efcd895ba01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:PHZXWSDYGL6K2F4MVEK2KVM7FT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:57:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tEcmJJ7sOdgjKT6iB9/1MKVe31bx1THbDer0sspPacuLKhWG8T861sbY4yiztnWK4yYfAa0hAs4q+6qAJ3S9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T21:56:02.446642Z"},"content_sha256":"bd155ba785b2abd1128d7d06ea17d2b08a22d26aa5903c714b6e04617ded30ea","schema_version":"1.0","event_id":"sha256:bd155ba785b2abd1128d7d06ea17d2b08a22d26aa5903c714b6e04617ded30ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT/bundle.json","state_url":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T21:56:02Z","links":{"resolver":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT","bundle":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT/bundle.json","state":"https://pith.science/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PHZXWSDYGL6K2F4MVEK2KVM7FT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:PHZXWSDYGL6K2F4MVEK2KVM7FT","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":"66fc35bb6c4b0d17e1c010775da0b5d4457613a7b3eecf47b428fbd1f74d7065","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-02-26T12:37:04Z","title_canon_sha256":"57c1ace83669d5f5723a6e9fb4f1091d0fb6b67c901881f3f59bcee5aa0d67c2"},"schema_version":"1.0","source":{"id":"1402.6516","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.6516","created_at":"2026-05-18T02:57:44Z"},{"alias_kind":"arxiv_version","alias_value":"1402.6516v1","created_at":"2026-05-18T02:57:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.6516","created_at":"2026-05-18T02:57:44Z"},{"alias_kind":"pith_short_12","alias_value":"PHZXWSDYGL6K","created_at":"2026-05-18T12:28:43Z"},{"alias_kind":"pith_short_16","alias_value":"PHZXWSDYGL6K2F4M","created_at":"2026-05-18T12:28:43Z"},{"alias_kind":"pith_short_8","alias_value":"PHZXWSDY","created_at":"2026-05-18T12:28:43Z"}],"graph_snapshots":[{"event_id":"sha256:bd155ba785b2abd1128d7d06ea17d2b08a22d26aa5903c714b6e04617ded30ea","target":"graph","created_at":"2026-05-18T02:57:44Z","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":"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","authors_text":"Greg Dubbin, Phil Blunsom","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-02-26T12:37:04Z","title":"Modelling the Lexicon in Unsupervised Part of Speech Induction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.6516","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":"sha256:781aaf34ddd1b2e5a25ec2f86313c5d806866762ee9b3d4d279a5efcd895ba01","target":"record","created_at":"2026-05-18T02:57:44Z","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":"66fc35bb6c4b0d17e1c010775da0b5d4457613a7b3eecf47b428fbd1f74d7065","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-02-26T12:37:04Z","title_canon_sha256":"57c1ace83669d5f5723a6e9fb4f1091d0fb6b67c901881f3f59bcee5aa0d67c2"},"schema_version":"1.0","source":{"id":"1402.6516","kind":"arxiv","version":1}},"canonical_sha256":"79f37b487832fcad178ca915a5559f2cd058c1a78423bff0cbcd19a6d3ab4dae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79f37b487832fcad178ca915a5559f2cd058c1a78423bff0cbcd19a6d3ab4dae","first_computed_at":"2026-05-18T02:57:44.365577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:57:44.365577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qX/hFi2zuzD647bkJoP5EQ9c990Wsmjq7c8XLUo5Je9U0KD8PyM/jGEgHnLuQQ/DRYP8MyOW8tgySUtWbU/eCA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:57:44.366055Z","signed_message":"canonical_sha256_bytes"},"source_id":"1402.6516","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:781aaf34ddd1b2e5a25ec2f86313c5d806866762ee9b3d4d279a5efcd895ba01","sha256:bd155ba785b2abd1128d7d06ea17d2b08a22d26aa5903c714b6e04617ded30ea"],"state_sha256":"9c44aed03a2befb9ad2b384b3c38c64610aa3396dcab68314f3df10e5a193b7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B9xHhXkRs495KwRm9ft4U9bO8zpBLlqzh8n6Uza936Rnk+NYqXYWU/muF6wbB+uqxyL+GUcSicFXaGU6IHmADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T21:56:02.449915Z","bundle_sha256":"6a7f01edc50fa6a53074a2bf6bf06944add2fee60626700868027b8b52763a6e"}}