{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:DHCXYAFXRFILQ3WETLDRMD336E","short_pith_number":"pith:DHCXYAFX","canonical_record":{"source":{"id":"1411.0007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-31T20:04:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"352b62283f2c0f4276ef565dc5d925e47afe1f302433e907aaf29cc6c6960da3","abstract_canon_sha256":"08aada054ebb4d34695c7dfdd0ca0cef3a1afa29c77b3d8bebf3185a649576df"},"schema_version":"1.0"},"canonical_sha256":"19c57c00b78950b86ec49ac7160f7bf13f29489d77c0f66eb95b70d43256ee58","source":{"kind":"arxiv","id":"1411.0007","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1411.0007","created_at":"2026-05-18T02:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"1411.0007v1","created_at":"2026-05-18T02:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.0007","created_at":"2026-05-18T02:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"DHCXYAFXRFIL","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DHCXYAFXRFILQ3WE","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DHCXYAFX","created_at":"2026-05-18T12:28:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:DHCXYAFXRFILQ3WETLDRMD336E","target":"record","payload":{"canonical_record":{"source":{"id":"1411.0007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-31T20:04:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"352b62283f2c0f4276ef565dc5d925e47afe1f302433e907aaf29cc6c6960da3","abstract_canon_sha256":"08aada054ebb4d34695c7dfdd0ca0cef3a1afa29c77b3d8bebf3185a649576df"},"schema_version":"1.0"},"canonical_sha256":"19c57c00b78950b86ec49ac7160f7bf13f29489d77c0f66eb95b70d43256ee58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:38:52.717108Z","signature_b64":"GEa1fG7LLP8TfpDuGB3kfTsU+TjHXaqsvCw7/mNxp0RoqnUptE4G2WJawV+L7hJ/+7dAITtu4akJLifSiSk5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19c57c00b78950b86ec49ac7160f7bf13f29489d77c0f66eb95b70d43256ee58","last_reissued_at":"2026-05-18T02:38:52.716749Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:38:52.716749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1411.0007","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":"2026-05-18T02:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LiQzaC/L9Wxk9FrN4iZjq/Mcbh1vnKu5qFYWlxMRbeEXEhj0UjBQiJ4a7XcExGNaAuf0Ff9of2Bp8gF30Sl5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T05:00:15.689722Z"},"content_sha256":"575a690152df8263ad39be4c933515ad5dc60f3eb28d1b5111b6ff68bbd92f7d","schema_version":"1.0","event_id":"sha256:575a690152df8263ad39be4c933515ad5dc60f3eb28d1b5111b6ff68bbd92f7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:DHCXYAFXRFILQ3WETLDRMD336E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rapid Adaptation of POS Tagging for Domain Specific Uses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"John E. Miller, K. Vijay-Shanker, Manabu Torii, Michael Bloodgood","submitted_at":"2014-10-31T20:04:09Z","abstract_excerpt":"Part-of-speech (POS) tagging is a fundamental component for performing natural language tasks such as parsing, information extraction, and question answering. When POS taggers are trained in one domain and applied in significantly different domains, their performance can degrade dramatically. We present a methodology for rapid adaptation of POS taggers to new domains. Our technique is unsupervised in that a manually annotated corpus for the new domain is not necessary. We use suffix information gathered from large amounts of raw text as well as orthographic information to increase the lexical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.0007","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":"2026-05-18T02:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xTmEJnu7y9h68Rp+dD38pFlDC60Ohx0GST+oSJpaSF+Dr8SaYBUBzbuHA0emdZhEZf16A/eO8l/PCoLbZQxPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T05:00:15.690077Z"},"content_sha256":"7495c81a8f05a1bf25dd09587e234ea7fd48e040e5aec5d7e39bc45188abc3da","schema_version":"1.0","event_id":"sha256:7495c81a8f05a1bf25dd09587e234ea7fd48e040e5aec5d7e39bc45188abc3da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DHCXYAFXRFILQ3WETLDRMD336E/bundle.json","state_url":"https://pith.science/pith/DHCXYAFXRFILQ3WETLDRMD336E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DHCXYAFXRFILQ3WETLDRMD336E/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":"2026-05-28T05:00:15Z","links":{"resolver":"https://pith.science/pith/DHCXYAFXRFILQ3WETLDRMD336E","bundle":"https://pith.science/pith/DHCXYAFXRFILQ3WETLDRMD336E/bundle.json","state":"https://pith.science/pith/DHCXYAFXRFILQ3WETLDRMD336E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DHCXYAFXRFILQ3WETLDRMD336E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:DHCXYAFXRFILQ3WETLDRMD336E","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":"08aada054ebb4d34695c7dfdd0ca0cef3a1afa29c77b3d8bebf3185a649576df","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-31T20:04:09Z","title_canon_sha256":"352b62283f2c0f4276ef565dc5d925e47afe1f302433e907aaf29cc6c6960da3"},"schema_version":"1.0","source":{"id":"1411.0007","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1411.0007","created_at":"2026-05-18T02:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"1411.0007v1","created_at":"2026-05-18T02:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.0007","created_at":"2026-05-18T02:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"DHCXYAFXRFIL","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DHCXYAFXRFILQ3WE","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DHCXYAFX","created_at":"2026-05-18T12:28:25Z"}],"graph_snapshots":[{"event_id":"sha256:7495c81a8f05a1bf25dd09587e234ea7fd48e040e5aec5d7e39bc45188abc3da","target":"graph","created_at":"2026-05-18T02:38:52Z","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":"Part-of-speech (POS) tagging is a fundamental component for performing natural language tasks such as parsing, information extraction, and question answering. When POS taggers are trained in one domain and applied in significantly different domains, their performance can degrade dramatically. We present a methodology for rapid adaptation of POS taggers to new domains. Our technique is unsupervised in that a manually annotated corpus for the new domain is not necessary. We use suffix information gathered from large amounts of raw text as well as orthographic information to increase the lexical ","authors_text":"John E. Miller, K. Vijay-Shanker, Manabu Torii, Michael Bloodgood","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-31T20:04:09Z","title":"Rapid Adaptation of POS Tagging for Domain Specific Uses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.0007","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":"sha256:575a690152df8263ad39be4c933515ad5dc60f3eb28d1b5111b6ff68bbd92f7d","target":"record","created_at":"2026-05-18T02:38:52Z","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":"08aada054ebb4d34695c7dfdd0ca0cef3a1afa29c77b3d8bebf3185a649576df","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-10-31T20:04:09Z","title_canon_sha256":"352b62283f2c0f4276ef565dc5d925e47afe1f302433e907aaf29cc6c6960da3"},"schema_version":"1.0","source":{"id":"1411.0007","kind":"arxiv","version":1}},"canonical_sha256":"19c57c00b78950b86ec49ac7160f7bf13f29489d77c0f66eb95b70d43256ee58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19c57c00b78950b86ec49ac7160f7bf13f29489d77c0f66eb95b70d43256ee58","first_computed_at":"2026-05-18T02:38:52.716749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:38:52.716749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GEa1fG7LLP8TfpDuGB3kfTsU+TjHXaqsvCw7/mNxp0RoqnUptE4G2WJawV+L7hJ/+7dAITtu4akJLifSiSk5DA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:38:52.717108Z","signed_message":"canonical_sha256_bytes"},"source_id":"1411.0007","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:575a690152df8263ad39be4c933515ad5dc60f3eb28d1b5111b6ff68bbd92f7d","sha256:7495c81a8f05a1bf25dd09587e234ea7fd48e040e5aec5d7e39bc45188abc3da"],"state_sha256":"5168d7b5979612e6b628b53afa9d5691dd53e0068e7e48a849e27a1ee300edd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u8BHJjIVpYmw/6mxJypQIXeNPTqRpKWuhXy4UELPYEP1yyMyencuweDoOCHals1d0PmEMYj546tzEcT1b4z5Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T05:00:15.692204Z","bundle_sha256":"c37bef71ca8a112939e0ca7f0c67c3e6ebb3b1308cfd963b02f4326051721b13"}}