{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:BH3SYVDD2TLP5NBYQQHX7YXDNM","short_pith_number":"pith:BH3SYVDD","schema_version":"1.0","canonical_sha256":"09f72c5463d4d6feb438840f7fe2e36b3595cb230c67ea40cd3b9a5e5c129593","source":{"kind":"arxiv","id":"1602.02373","version":2},"attestation_state":"computed","paper":{"title":"Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Rie Johnson, Tong Zhang","submitted_at":"2016-02-07T14:05:58Z","abstract_excerpt":"One-hot CNN (convolutional neural network) has been shown to be effective for text categorization (Johnson & Zhang, 2015). We view it as a special case of a general framework which jointly trains a linear model with a non-linear feature generator consisting of `text region embedding + pooling'. Under this framework, we explore a more sophisticated region embedding method using Long Short-Term Memory (LSTM). LSTM can embed text regions of variable (and possibly large) sizes, whereas the region size needs to be fixed in a CNN. We seek effective and efficient use of LSTM for this purpose in the s"},"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":"1602.02373","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-07T14:05:58Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"45fc68eea3ae0825638e9081f4e9ec46624dba1ca2719d2b85a8b9a22dd95925","abstract_canon_sha256":"2083c8d618806e793cab1455a85ccacc53083a3b1610f68d099c7f60dcb52f06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:37.699679Z","signature_b64":"mLUcMyttzTCdhjCWRMTuhASinTg39/i4qfTTvj03sZpHO634BHNCfaQjFv6MO7b1A65FKsgj5tXUEU4KBeCjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09f72c5463d4d6feb438840f7fe2e36b3595cb230c67ea40cd3b9a5e5c129593","last_reissued_at":"2026-05-18T01:13:37.698950Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:37.698950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Rie Johnson, Tong Zhang","submitted_at":"2016-02-07T14:05:58Z","abstract_excerpt":"One-hot CNN (convolutional neural network) has been shown to be effective for text categorization (Johnson & Zhang, 2015). We view it as a special case of a general framework which jointly trains a linear model with a non-linear feature generator consisting of `text region embedding + pooling'. Under this framework, we explore a more sophisticated region embedding method using Long Short-Term Memory (LSTM). LSTM can embed text regions of variable (and possibly large) sizes, whereas the region size needs to be fixed in a CNN. We seek effective and efficient use of LSTM for this purpose in the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02373","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":"1602.02373","created_at":"2026-05-18T01:13:37.699072+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.02373v2","created_at":"2026-05-18T01:13:37.699072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02373","created_at":"2026-05-18T01:13:37.699072+00:00"},{"alias_kind":"pith_short_12","alias_value":"BH3SYVDD2TLP","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_16","alias_value":"BH3SYVDD2TLP5NBY","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_8","alias_value":"BH3SYVDD","created_at":"2026-05-18T12:30:07.202191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.12330","citing_title":"Graph Star Net for Generalized Multi-Task Learning","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BH3SYVDD2TLP5NBYQQHX7YXDNM","json":"https://pith.science/pith/BH3SYVDD2TLP5NBYQQHX7YXDNM.json","graph_json":"https://pith.science/api/pith-number/BH3SYVDD2TLP5NBYQQHX7YXDNM/graph.json","events_json":"https://pith.science/api/pith-number/BH3SYVDD2TLP5NBYQQHX7YXDNM/events.json","paper":"https://pith.science/paper/BH3SYVDD"},"agent_actions":{"view_html":"https://pith.science/pith/BH3SYVDD2TLP5NBYQQHX7YXDNM","download_json":"https://pith.science/pith/BH3SYVDD2TLP5NBYQQHX7YXDNM.json","view_paper":"https://pith.science/paper/BH3SYVDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.02373&json=true","fetch_graph":"https://pith.science/api/pith-number/BH3SYVDD2TLP5NBYQQHX7YXDNM/graph.json","fetch_events":"https://pith.science/api/pith-number/BH3SYVDD2TLP5NBYQQHX7YXDNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BH3SYVDD2TLP5NBYQQHX7YXDNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BH3SYVDD2TLP5NBYQQHX7YXDNM/action/storage_attestation","attest_author":"https://pith.science/pith/BH3SYVDD2TLP5NBYQQHX7YXDNM/action/author_attestation","sign_citation":"https://pith.science/pith/BH3SYVDD2TLP5NBYQQHX7YXDNM/action/citation_signature","submit_replication":"https://pith.science/pith/BH3SYVDD2TLP5NBYQQHX7YXDNM/action/replication_record"}},"created_at":"2026-05-18T01:13:37.699072+00:00","updated_at":"2026-05-18T01:13:37.699072+00:00"}