{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OOAXJCA5KDDZJKSDLLVGBZW5ZB","short_pith_number":"pith:OOAXJCA5","canonical_record":{"source":{"id":"1810.08567","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-19T16:09:35Z","cross_cats_sorted":[],"title_canon_sha256":"a1a4e8d6afb2b388b9bf453cb0185abcdb130f0905cf73fc795baf643b86b471","abstract_canon_sha256":"bf85a2c99bee62aa441d9843523b32b610838024b059b327ab11d344b66fedda"},"schema_version":"1.0"},"canonical_sha256":"738174881d50c794aa435aea60e6ddc848a90f367e006d02ca1d1cb5ea280e87","source":{"kind":"arxiv","id":"1810.08567","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.08567","created_at":"2026-05-18T00:02:47Z"},{"alias_kind":"arxiv_version","alias_value":"1810.08567v1","created_at":"2026-05-18T00:02:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08567","created_at":"2026-05-18T00:02:47Z"},{"alias_kind":"pith_short_12","alias_value":"OOAXJCA5KDDZ","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OOAXJCA5KDDZJKSD","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OOAXJCA5","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OOAXJCA5KDDZJKSDLLVGBZW5ZB","target":"record","payload":{"canonical_record":{"source":{"id":"1810.08567","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-19T16:09:35Z","cross_cats_sorted":[],"title_canon_sha256":"a1a4e8d6afb2b388b9bf453cb0185abcdb130f0905cf73fc795baf643b86b471","abstract_canon_sha256":"bf85a2c99bee62aa441d9843523b32b610838024b059b327ab11d344b66fedda"},"schema_version":"1.0"},"canonical_sha256":"738174881d50c794aa435aea60e6ddc848a90f367e006d02ca1d1cb5ea280e87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:47.777203Z","signature_b64":"MpN9kd6/Yw2BwaeRbq2uxufjHzvpkDRwQafyloAJ5UwnOPJERg0xgCTepgCe43MHaSJQdZswWz4X41eB1ufJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"738174881d50c794aa435aea60e6ddc848a90f367e006d02ca1d1cb5ea280e87","last_reissued_at":"2026-05-18T00:02:47.776736Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:47.776736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.08567","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":"2026-05-18T00:02:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6oB41CDkR6nOhFKeAxcb1J9TnIDKFWroG7Qmk2Lwvt5yaNyPKOooG2UJpPPMfE3Og3UTkoQlDTOYFO+Kua9GBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:28:45.623320Z"},"content_sha256":"132cc9158c226a207c6cbb611535229c5ad0c735c9f74bcff9e4adbba45d70a9","schema_version":"1.0","event_id":"sha256:132cc9158c226a207c6cbb611535229c5ad0c735c9f74bcff9e4adbba45d70a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OOAXJCA5KDDZJKSDLLVGBZW5ZB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weak Semi-Markov CRFs for NP Chunking in Informal Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aldrian Obaja Muis, Wei Lu","submitted_at":"2018-10-19T16:09:35Z","abstract_excerpt":"This paper introduces a new annotated corpus based on an existing informal text corpus: the NUS SMS Corpus (Chen and Kan, 2013). The new corpus includes 76,490 noun phrases from 26,500 SMS messages, annotated by university students. We then explored several graphical models, including a novel variant of the semi-Markov conditional random fields (semi-CRF) for the task of noun phrase chunking. We demonstrated through empirical evaluations on the new dataset that the new variant yielded similar accuracy but ran in significantly lower running time compared to the conventional semi-CRF."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08567","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":"2026-05-18T00:02:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XB2532hHeBcXPRISxFEOxSVBQ61cKFr9safduvOUT/yGyhOVPgzU5bKiRXdEhHsJImbZFlLx7yHAKlR0QR+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:28:45.623850Z"},"content_sha256":"03de70923734d78ff929b27de2765c760c8852acf1be930473b1dcf43555d885","schema_version":"1.0","event_id":"sha256:03de70923734d78ff929b27de2765c760c8852acf1be930473b1dcf43555d885"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOAXJCA5KDDZJKSDLLVGBZW5ZB/bundle.json","state_url":"https://pith.science/pith/OOAXJCA5KDDZJKSDLLVGBZW5ZB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOAXJCA5KDDZJKSDLLVGBZW5ZB/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":"2026-08-03T16:28:45Z","links":{"resolver":"https://pith.science/pith/OOAXJCA5KDDZJKSDLLVGBZW5ZB","bundle":"https://pith.science/pith/OOAXJCA5KDDZJKSDLLVGBZW5ZB/bundle.json","state":"https://pith.science/pith/OOAXJCA5KDDZJKSDLLVGBZW5ZB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOAXJCA5KDDZJKSDLLVGBZW5ZB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OOAXJCA5KDDZJKSDLLVGBZW5ZB","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":"bf85a2c99bee62aa441d9843523b32b610838024b059b327ab11d344b66fedda","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-19T16:09:35Z","title_canon_sha256":"a1a4e8d6afb2b388b9bf453cb0185abcdb130f0905cf73fc795baf643b86b471"},"schema_version":"1.0","source":{"id":"1810.08567","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.08567","created_at":"2026-05-18T00:02:47Z"},{"alias_kind":"arxiv_version","alias_value":"1810.08567v1","created_at":"2026-05-18T00:02:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08567","created_at":"2026-05-18T00:02:47Z"},{"alias_kind":"pith_short_12","alias_value":"OOAXJCA5KDDZ","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OOAXJCA5KDDZJKSD","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OOAXJCA5","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:03de70923734d78ff929b27de2765c760c8852acf1be930473b1dcf43555d885","target":"graph","created_at":"2026-05-18T00:02:47Z","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":"This paper introduces a new annotated corpus based on an existing informal text corpus: the NUS SMS Corpus (Chen and Kan, 2013). The new corpus includes 76,490 noun phrases from 26,500 SMS messages, annotated by university students. We then explored several graphical models, including a novel variant of the semi-Markov conditional random fields (semi-CRF) for the task of noun phrase chunking. We demonstrated through empirical evaluations on the new dataset that the new variant yielded similar accuracy but ran in significantly lower running time compared to the conventional semi-CRF.","authors_text":"Aldrian Obaja Muis, Wei Lu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-19T16:09:35Z","title":"Weak Semi-Markov CRFs for NP Chunking in Informal Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08567","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":"sha256:132cc9158c226a207c6cbb611535229c5ad0c735c9f74bcff9e4adbba45d70a9","target":"record","created_at":"2026-05-18T00:02:47Z","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":"bf85a2c99bee62aa441d9843523b32b610838024b059b327ab11d344b66fedda","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-19T16:09:35Z","title_canon_sha256":"a1a4e8d6afb2b388b9bf453cb0185abcdb130f0905cf73fc795baf643b86b471"},"schema_version":"1.0","source":{"id":"1810.08567","kind":"arxiv","version":1}},"canonical_sha256":"738174881d50c794aa435aea60e6ddc848a90f367e006d02ca1d1cb5ea280e87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"738174881d50c794aa435aea60e6ddc848a90f367e006d02ca1d1cb5ea280e87","first_computed_at":"2026-05-18T00:02:47.776736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:47.776736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MpN9kd6/Yw2BwaeRbq2uxufjHzvpkDRwQafyloAJ5UwnOPJERg0xgCTepgCe43MHaSJQdZswWz4X41eB1ufJBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:47.777203Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.08567","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:132cc9158c226a207c6cbb611535229c5ad0c735c9f74bcff9e4adbba45d70a9","sha256:03de70923734d78ff929b27de2765c760c8852acf1be930473b1dcf43555d885"],"state_sha256":"27d69d06ac1f9af98793c6c2acd01b5b13373f0681972039272046b0e8c28e4b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fni92ZeArpgx/3jvscYitIwn7nUwrYEAOQDRSPYXVP+ahSaIMc1RV5zNQE+xJzTlyLLfAbl2uNZp1BB4qnFkAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:28:45.628013Z","bundle_sha256":"e704b62e3b2a08d65eb1837ca3ad704ad264614ed7648d4f57526981a3ac0ce4"}}