{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:V45OJU2QYUN6CGDZIV3ODCSMN2","short_pith_number":"pith:V45OJU2Q","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"},"canonical_sha256":"af3ae4d350c51be118794576e18a4c6e957e00bb57a82af74796fb93158d448e","source":{"kind":"arxiv","id":"1703.04213","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.04213","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"1703.04213v2","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04213","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"V45OJU2QYUN6","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"V45OJU2QYUN6CGDZ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"V45OJU2Q","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:V45OJU2QYUN6CGDZIV3ODCSMN2","target":"record","payload":{"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"},"canonical_sha256":"af3ae4d350c51be118794576e18a4c6e957e00bb57a82af74796fb93158d448e","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"},"source_kind":"arxiv","source_id":"1703.04213","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rv6JEpaUfUSdJtksWZwC3xGmLVi9jgNHl9J7NCv3IDt5YAwrWJEH9+bdnUwxL3NVISGhOlGCsogmJ7qu5x1dDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T14:43:51.282789Z"},"content_sha256":"2b9f0b48e6983a1fee5c02ed1b27097dc65254ae8500d303d12e18b3d47bdd8b","schema_version":"1.0","event_id":"sha256:2b9f0b48e6983a1fee5c02ed1b27097dc65254ae8500d303d12e18b3d47bdd8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:V45OJU2QYUN6CGDZIV3ODCSMN2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xR6Ec6rEf0tBMxyeZyjl1mwFD1yx1/vCP5AOcAsyEGc7Nh53qFGQQa+PMtNBSHGe6XpA2OhjdFXKQ+HZ4waSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T14:43:51.283137Z"},"content_sha256":"54a2a3920a038486033ac71a324b63380b49cea91c442fbe436c3a99c1ee4327","schema_version":"1.0","event_id":"sha256:54a2a3920a038486033ac71a324b63380b49cea91c442fbe436c3a99c1ee4327"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2/bundle.json","state_url":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V45OJU2QYUN6CGDZIV3ODCSMN2/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":"2026-05-20T14:43:51Z","links":{"resolver":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2","bundle":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2/bundle.json","state":"https://pith.science/pith/V45OJU2QYUN6CGDZIV3ODCSMN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V45OJU2QYUN6CGDZIV3ODCSMN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:V45OJU2QYUN6CGDZIV3ODCSMN2","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":"4c0c84634239d538168508ad001fcb182e4c15f35b7d36ac2c593c1645dc4c25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-13T01:06:19Z","title_canon_sha256":"cb3d49efe657901236371b4c771a79569528d6a9c240faccc5082e5440a4e7be"},"schema_version":"1.0","source":{"id":"1703.04213","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.04213","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"1703.04213v2","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04213","created_at":"2026-05-18T00:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"V45OJU2QYUN6","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"V45OJU2QYUN6CGDZ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"V45OJU2Q","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:54a2a3920a038486033ac71a324b63380b49cea91c442fbe436c3a99c1ee4327","target":"graph","created_at":"2026-05-18T00:48:41Z","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":"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 ","authors_text":"Jiawei Han, Jingbo Shang, Lance M. Kaplan, Meng Jiang, Taylor Cassidy, Timothy P. Hanratty, Xiang Ren","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-13T01:06:19Z","title":"MetaPAD: Meta Pattern Discovery from Massive Text Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04213","kind":"arxiv","version":2},"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":"sha256:2b9f0b48e6983a1fee5c02ed1b27097dc65254ae8500d303d12e18b3d47bdd8b","target":"record","created_at":"2026-05-18T00:48:41Z","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":"4c0c84634239d538168508ad001fcb182e4c15f35b7d36ac2c593c1645dc4c25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-13T01:06:19Z","title_canon_sha256":"cb3d49efe657901236371b4c771a79569528d6a9c240faccc5082e5440a4e7be"},"schema_version":"1.0","source":{"id":"1703.04213","kind":"arxiv","version":2}},"canonical_sha256":"af3ae4d350c51be118794576e18a4c6e957e00bb57a82af74796fb93158d448e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af3ae4d350c51be118794576e18a4c6e957e00bb57a82af74796fb93158d448e","first_computed_at":"2026-05-18T00:48:41.564029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:41.564029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p1O+LizbyhfLViqd6g2FDXKmMpqfmjLr1RNWz7xFBXEAU9HlnUaYiTCHn1w9CcGHIemq3Z7CGZth1VR6RvarDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:41.564496Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.04213","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b9f0b48e6983a1fee5c02ed1b27097dc65254ae8500d303d12e18b3d47bdd8b","sha256:54a2a3920a038486033ac71a324b63380b49cea91c442fbe436c3a99c1ee4327"],"state_sha256":"fc8b1f0e22c631fc183339560283abc5578767df24902bd466fd32616b42adbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zbJF/ujBwuHDwNarWxYVdTiLTqjO4qIHvM3OxlEzzRBRFFBPhJb3JNIq8Hec8bdG4ARkpuKQNqBPcB81T2O2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T14:43:51.285178Z","bundle_sha256":"7356e049451155fbf96d2ec3cac8f48aff7d70657d6c5cdf6e001a3caac3c76b"}}