{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XDPLGU3TTIRFF6HTZVOWS2QKP5","short_pith_number":"pith:XDPLGU3T","canonical_record":{"source":{"id":"1705.08942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-24T19:44:35Z","cross_cats_sorted":[],"title_canon_sha256":"d66a8c5f2293e1e6d24c41d29583f3eb5b09708139584df062b2f3135c141ab2","abstract_canon_sha256":"e6dd79787f8226b9e3e592d3d9261d7d9a6f096499db8c59cad459d1e9e3d6b1"},"schema_version":"1.0"},"canonical_sha256":"b8deb353739a2252f8f3cd5d696a0a7f423533ab0c0990a9ec0dde1fc0291ce8","source":{"kind":"arxiv","id":"1705.08942","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08942","created_at":"2026-05-18T00:43:40Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08942v1","created_at":"2026-05-18T00:43:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08942","created_at":"2026-05-18T00:43:40Z"},{"alias_kind":"pith_short_12","alias_value":"XDPLGU3TTIRF","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XDPLGU3TTIRFF6HT","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XDPLGU3T","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XDPLGU3TTIRFF6HTZVOWS2QKP5","target":"record","payload":{"canonical_record":{"source":{"id":"1705.08942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-24T19:44:35Z","cross_cats_sorted":[],"title_canon_sha256":"d66a8c5f2293e1e6d24c41d29583f3eb5b09708139584df062b2f3135c141ab2","abstract_canon_sha256":"e6dd79787f8226b9e3e592d3d9261d7d9a6f096499db8c59cad459d1e9e3d6b1"},"schema_version":"1.0"},"canonical_sha256":"b8deb353739a2252f8f3cd5d696a0a7f423533ab0c0990a9ec0dde1fc0291ce8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:40.891484Z","signature_b64":"uNhet4pErcThDZdAlHFRfGicnxslh7boOVzWjVL6RG9hLVn+r3pom1WNzfIanctH/Kf5liru1pp6UuHUkGABBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8deb353739a2252f8f3cd5d696a0a7f423533ab0c0990a9ec0dde1fc0291ce8","last_reissued_at":"2026-05-18T00:43:40.890861Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:40.890861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.08942","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":"2026-05-18T00:43:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cROPYp/krThVsc9QhZitjbz0GzZ8Vpv9DvubV8Kd8YxlWJMPC3p0rde9kvwQQxfPZhySmO97y0iIoUT0pTJyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T02:11:28.461206Z"},"content_sha256":"df483833af687b7bd09c9a5b045dc6b3ea68ffb7f91ad87f08181a581ba51dfa","schema_version":"1.0","event_id":"sha256:df483833af687b7bd09c9a5b045dc6b3ea68ffb7f91ad87f08181a581ba51dfa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XDPLGU3TTIRFF6HTZVOWS2QKP5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint PoS Tagging and Stemming for Agglutinative Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Burcu Can, Necva B\\\"ol\\\"uc\\\"u","submitted_at":"2017-05-24T19:44:35Z","abstract_excerpt":"The number of word forms in agglutinative languages is theoretically infinite and this variety in word forms introduces sparsity in many natural language processing tasks. Part-of-speech tagging (PoS tagging) is one of these tasks that often suffers from sparsity. In this paper, we present an unsupervised Bayesian model using Hidden Markov Models (HMMs) for joint PoS tagging and stemming for agglutinative languages. We use stemming to reduce sparsity in PoS tagging. Two tasks are jointly performed to provide a mutual benefit in both tasks. Our results show that joint POS tagging and stemming i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08942","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":"2026-05-18T00:43:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7LTJ6shGs+pDRqKSLizu+zMmjitvkXTQMF0rilM8wKmrkpmLLE2DRCc9bJrlRjk9Zb3Q8AzNztN45IbClFPyDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T02:11:28.461555Z"},"content_sha256":"43faa897e1e18230ecf9a322c8d4001b8d28a72949e9ff98d6de6a476ab40183","schema_version":"1.0","event_id":"sha256:43faa897e1e18230ecf9a322c8d4001b8d28a72949e9ff98d6de6a476ab40183"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XDPLGU3TTIRFF6HTZVOWS2QKP5/bundle.json","state_url":"https://pith.science/pith/XDPLGU3TTIRFF6HTZVOWS2QKP5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XDPLGU3TTIRFF6HTZVOWS2QKP5/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":"2026-06-26T02:11:28Z","links":{"resolver":"https://pith.science/pith/XDPLGU3TTIRFF6HTZVOWS2QKP5","bundle":"https://pith.science/pith/XDPLGU3TTIRFF6HTZVOWS2QKP5/bundle.json","state":"https://pith.science/pith/XDPLGU3TTIRFF6HTZVOWS2QKP5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XDPLGU3TTIRFF6HTZVOWS2QKP5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XDPLGU3TTIRFF6HTZVOWS2QKP5","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":"e6dd79787f8226b9e3e592d3d9261d7d9a6f096499db8c59cad459d1e9e3d6b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-24T19:44:35Z","title_canon_sha256":"d66a8c5f2293e1e6d24c41d29583f3eb5b09708139584df062b2f3135c141ab2"},"schema_version":"1.0","source":{"id":"1705.08942","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08942","created_at":"2026-05-18T00:43:40Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08942v1","created_at":"2026-05-18T00:43:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08942","created_at":"2026-05-18T00:43:40Z"},{"alias_kind":"pith_short_12","alias_value":"XDPLGU3TTIRF","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XDPLGU3TTIRFF6HT","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XDPLGU3T","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:43faa897e1e18230ecf9a322c8d4001b8d28a72949e9ff98d6de6a476ab40183","target":"graph","created_at":"2026-05-18T00:43:40Z","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 number of word forms in agglutinative languages is theoretically infinite and this variety in word forms introduces sparsity in many natural language processing tasks. Part-of-speech tagging (PoS tagging) is one of these tasks that often suffers from sparsity. In this paper, we present an unsupervised Bayesian model using Hidden Markov Models (HMMs) for joint PoS tagging and stemming for agglutinative languages. We use stemming to reduce sparsity in PoS tagging. Two tasks are jointly performed to provide a mutual benefit in both tasks. Our results show that joint POS tagging and stemming i","authors_text":"Burcu Can, Necva B\\\"ol\\\"uc\\\"u","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-24T19:44:35Z","title":"Joint PoS Tagging and Stemming for Agglutinative Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08942","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:df483833af687b7bd09c9a5b045dc6b3ea68ffb7f91ad87f08181a581ba51dfa","target":"record","created_at":"2026-05-18T00:43:40Z","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":"e6dd79787f8226b9e3e592d3d9261d7d9a6f096499db8c59cad459d1e9e3d6b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-24T19:44:35Z","title_canon_sha256":"d66a8c5f2293e1e6d24c41d29583f3eb5b09708139584df062b2f3135c141ab2"},"schema_version":"1.0","source":{"id":"1705.08942","kind":"arxiv","version":1}},"canonical_sha256":"b8deb353739a2252f8f3cd5d696a0a7f423533ab0c0990a9ec0dde1fc0291ce8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8deb353739a2252f8f3cd5d696a0a7f423533ab0c0990a9ec0dde1fc0291ce8","first_computed_at":"2026-05-18T00:43:40.890861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:40.890861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uNhet4pErcThDZdAlHFRfGicnxslh7boOVzWjVL6RG9hLVn+r3pom1WNzfIanctH/Kf5liru1pp6UuHUkGABBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:40.891484Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08942","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df483833af687b7bd09c9a5b045dc6b3ea68ffb7f91ad87f08181a581ba51dfa","sha256:43faa897e1e18230ecf9a322c8d4001b8d28a72949e9ff98d6de6a476ab40183"],"state_sha256":"b63e52469f9e1736ff126c713539b5225437972ff049811b92c303d3f04ff314"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HxkcbjqDFe8XTNz6mjXJehi+v3tTzDEd6f6JMRXjYlLjflukmoYEn7uz9pkulUDVzBXQEdjjmaGzQZ4bK3HYDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T02:11:28.463430Z","bundle_sha256":"9fa71e42a6fc0a058784db67d861580bc2691e19a39d55a68730b5dc613e1f9b"}}