{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:V45OJU2QYUN6CGDZIV3ODCSMN2","short_pith_number":"pith:V45OJU2Q","schema_version":"1.0","canonical_sha256":"af3ae4d350c51be118794576e18a4c6e957e00bb57a82af74796fb93158d448e","source":{"kind":"arxiv","id":"1703.04213","version":2},"attestation_state":"computed","paper":{"title":"MetaPAD: Meta Pattern Discovery from Massive Text Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiawei Han, Jingbo Shang, Lance M. Kaplan, Meng Jiang, Taylor Cassidy, Timothy P. Hanratty, Xiang Ren","submitted_at":"2017-03-13T01:06:19Z","abstract_excerpt":"Mining textual patterns in news, tweets, papers, and many other kinds of text corpora has been an active theme in text mining and NLP research. Previous studies adopt a dependency parsing-based pattern discovery approach. However, the parsing results lose rich context around entities in the patterns, and the process is costly for a corpus of large scale. In this study, we propose a novel typed textual pattern structure, called meta pattern, which is extended to a frequent, informative, and precise subsequence pattern in certain context. We propose an efficient framework, called MetaPAD, which "},"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":"1703.04213","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-13T01:06:19Z","cross_cats_sorted":[],"title_canon_sha256":"cb3d49efe657901236371b4c771a79569528d6a9c240faccc5082e5440a4e7be","abstract_canon_sha256":"4c0c84634239d538168508ad001fcb182e4c15f35b7d36ac2c593c1645dc4c25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:41.564496Z","signature_b64":"p1O+LizbyhfLViqd6g2FDXKmMpqfmjLr1RNWz7xFBXEAU9HlnUaYiTCHn1w9CcGHIemq3Z7CGZth1VR6RvarDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af3ae4d350c51be118794576e18a4c6e957e00bb57a82af74796fb93158d448e","last_reissued_at":"2026-05-18T00:48:41.564029Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:41.564029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaPAD: Meta Pattern Discovery from Massive Text Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiawei Han, Jingbo Shang, Lance M. Kaplan, Meng Jiang, Taylor Cassidy, Timothy P. Hanratty, Xiang Ren","submitted_at":"2017-03-13T01:06:19Z","abstract_excerpt":"Mining textual patterns in news, tweets, papers, and many other kinds of text corpora has been an active theme in text mining and NLP research. Previous studies adopt a dependency parsing-based pattern discovery approach. However, the parsing results lose rich context around entities in the patterns, and the process is costly for a corpus of large scale. In this study, we propose a novel typed textual pattern structure, called meta pattern, which is extended to a frequent, informative, and precise subsequence pattern in certain context. We propose an efficient framework, called MetaPAD, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04213","kind":"arxiv","version":2},"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":"1703.04213","created_at":"2026-05-18T00:48:41.564102+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.04213v2","created_at":"2026-05-18T00:48:41.564102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04213","created_at":"2026-05-18T00:48:41.564102+00:00"},{"alias_kind":"pith_short_12","alias_value":"V45OJU2QYUN6","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"V45OJU2QYUN6CGDZ","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"V45OJU2Q","created_at":"2026-05-18T12:31:49.984773+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/V45OJU2QYUN6CGDZIV3ODCSMN2","json":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2.json","graph_json":"https://pith.science/api/pith-number/V45OJU2QYUN6CGDZIV3ODCSMN2/graph.json","events_json":"https://pith.science/api/pith-number/V45OJU2QYUN6CGDZIV3ODCSMN2/events.json","paper":"https://pith.science/paper/V45OJU2Q"},"agent_actions":{"view_html":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2","download_json":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2.json","view_paper":"https://pith.science/paper/V45OJU2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.04213&json=true","fetch_graph":"https://pith.science/api/pith-number/V45OJU2QYUN6CGDZIV3ODCSMN2/graph.json","fetch_events":"https://pith.science/api/pith-number/V45OJU2QYUN6CGDZIV3ODCSMN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2/action/storage_attestation","attest_author":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2/action/author_attestation","sign_citation":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2/action/citation_signature","submit_replication":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2/action/replication_record"}},"created_at":"2026-05-18T00:48:41.564102+00:00","updated_at":"2026-05-18T00:48:41.564102+00:00"}