{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:O42JBURBI3KOENECDWI2K4LHGV","short_pith_number":"pith:O42JBURB","schema_version":"1.0","canonical_sha256":"773490d22146d4e234821d91a57167354b537df0401eb72efe5349572f1ebda3","source":{"kind":"arxiv","id":"2002.09673","version":1},"attestation_state":"computed","paper":{"title":"Incorporating Effective Global Information via Adaptive Gate Attention for Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoran Xie, Qing Li, Xianming Li, Yingbin Zhao, Zongxi Li","submitted_at":"2020-02-22T10:06:37Z","abstract_excerpt":"The dominant text classification studies focus on training classifiers using textual instances only or introducing external knowledge (e.g., hand-craft features and domain expert knowledge). In contrast, some corpus-level statistical features, like word frequency and distribution, are not well exploited. Our work shows that such simple statistical information can enhance classification performance both efficiently and significantly compared with several baseline models. In this paper, we propose a classifier with gate mechanism named Adaptive Gate Attention model with Global Information (AGA+G"},"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":"2002.09673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-22T10:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"e714dab79f8013726a77ab3b180f85e554ac8a1d84b3e7dc41f520b61bf1510f","abstract_canon_sha256":"6d5c6025f53185ac02ca311c84032c6cc20883f4f9f5f5500fe2be2bc5824774"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:10.488448Z","signature_b64":"+1fPPdDIbiYHX7nFjqwbGG35IVbyhdj5PQtCldLybgrb5d+a5NFkJ8EnCpsqk1Q+NRaYh4kodGGYBa5HjVRfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"773490d22146d4e234821d91a57167354b537df0401eb72efe5349572f1ebda3","last_reissued_at":"2026-07-05T00:43:10.488008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:10.488008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Effective Global Information via Adaptive Gate Attention for Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoran Xie, Qing Li, Xianming Li, Yingbin Zhao, Zongxi Li","submitted_at":"2020-02-22T10:06:37Z","abstract_excerpt":"The dominant text classification studies focus on training classifiers using textual instances only or introducing external knowledge (e.g., hand-craft features and domain expert knowledge). In contrast, some corpus-level statistical features, like word frequency and distribution, are not well exploited. Our work shows that such simple statistical information can enhance classification performance both efficiently and significantly compared with several baseline models. In this paper, we propose a classifier with gate mechanism named Adaptive Gate Attention model with Global Information (AGA+G"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09673","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.09673/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2002.09673","created_at":"2026-07-05T00:43:10.488067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09673v1","created_at":"2026-07-05T00:43:10.488067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09673","created_at":"2026-07-05T00:43:10.488067+00:00"},{"alias_kind":"pith_short_12","alias_value":"O42JBURBI3KO","created_at":"2026-07-05T00:43:10.488067+00:00"},{"alias_kind":"pith_short_16","alias_value":"O42JBURBI3KOENEC","created_at":"2026-07-05T00:43:10.488067+00:00"},{"alias_kind":"pith_short_8","alias_value":"O42JBURB","created_at":"2026-07-05T00:43:10.488067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2109.10616","citing_title":"Enriching and Controlling Global Semantics for Text Summarization","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O42JBURBI3KOENECDWI2K4LHGV","json":"https://pith.science/pith/O42JBURBI3KOENECDWI2K4LHGV.json","graph_json":"https://pith.science/api/pith-number/O42JBURBI3KOENECDWI2K4LHGV/graph.json","events_json":"https://pith.science/api/pith-number/O42JBURBI3KOENECDWI2K4LHGV/events.json","paper":"https://pith.science/paper/O42JBURB"},"agent_actions":{"view_html":"https://pith.science/pith/O42JBURBI3KOENECDWI2K4LHGV","download_json":"https://pith.science/pith/O42JBURBI3KOENECDWI2K4LHGV.json","view_paper":"https://pith.science/paper/O42JBURB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09673&json=true","fetch_graph":"https://pith.science/api/pith-number/O42JBURBI3KOENECDWI2K4LHGV/graph.json","fetch_events":"https://pith.science/api/pith-number/O42JBURBI3KOENECDWI2K4LHGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O42JBURBI3KOENECDWI2K4LHGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O42JBURBI3KOENECDWI2K4LHGV/action/storage_attestation","attest_author":"https://pith.science/pith/O42JBURBI3KOENECDWI2K4LHGV/action/author_attestation","sign_citation":"https://pith.science/pith/O42JBURBI3KOENECDWI2K4LHGV/action/citation_signature","submit_replication":"https://pith.science/pith/O42JBURBI3KOENECDWI2K4LHGV/action/replication_record"}},"created_at":"2026-07-05T00:43:10.488067+00:00","updated_at":"2026-07-05T00:43:10.488067+00:00"}