{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:APAUXL4MMB23EYBTDALBGNLS3D","short_pith_number":"pith:APAUXL4M","schema_version":"1.0","canonical_sha256":"03c14baf8c6075b260331816133572d8c38db9040665ae6dba551534d74b896f","source":{"kind":"arxiv","id":"1509.01626","version":3},"attestation_state":"computed","paper":{"title":"Character-level Convolutional Networks for Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Junbo Zhao, Xiang Zhang, Yann LeCun","submitted_at":"2015-09-04T22:31:53Z","abstract_excerpt":"This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks."},"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":"1509.01626","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-04T22:31:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6ca3e9942ee823eb4d67e9c93d32bac90ce27a21fa0c327168fbb7ea6ba74327","abstract_canon_sha256":"445d697d659f3454b5dc7ae9804c05dec6e98b1b24853a7546f7a90004036878"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:52.524734Z","signature_b64":"mPyxeD8l2Rc/3Jg3IHp4cCIbG7znCjSJ2N31gYDigm34WSGOJ0e/oKv2mCMn0FVvfl+HkMrE1a/4D81joqQwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03c14baf8c6075b260331816133572d8c38db9040665ae6dba551534d74b896f","last_reissued_at":"2026-05-18T01:17:52.524053Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:52.524053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Character-level Convolutional Networks for Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Junbo Zhao, Xiang Zhang, Yann LeCun","submitted_at":"2015-09-04T22:31:53Z","abstract_excerpt":"This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.01626","kind":"arxiv","version":3},"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":"1509.01626","created_at":"2026-05-18T01:17:52.524152+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.01626v3","created_at":"2026-05-18T01:17:52.524152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.01626","created_at":"2026-05-18T01:17:52.524152+00:00"},{"alias_kind":"pith_short_12","alias_value":"APAUXL4MMB23","created_at":"2026-05-18T12:29:10.953037+00:00"},{"alias_kind":"pith_short_16","alias_value":"APAUXL4MMB23EYBT","created_at":"2026-05-18T12:29:10.953037+00:00"},{"alias_kind":"pith_short_8","alias_value":"APAUXL4M","created_at":"2026-05-18T12:29:10.953037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1907.01300","citing_title":"Learning to Reformulate the Queries on the WEB","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04286","citing_title":"UW-BHI at MEDIQA 2019: An Analysis of Representation Methods for Medical Natural Language Inference","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2503.10666","citing_title":"Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22765","citing_title":"Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2308.03958","citing_title":"Simple synthetic data reduces sycophancy in large language models","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28052","citing_title":"Meta-Harness: End-to-End Optimization of Model Harnesses","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06382","citing_title":"Rethinking Vacuity for OOD Detection in Evidential Deep Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12384","citing_title":"Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APAUXL4MMB23EYBTDALBGNLS3D","json":"https://pith.science/pith/APAUXL4MMB23EYBTDALBGNLS3D.json","graph_json":"https://pith.science/api/pith-number/APAUXL4MMB23EYBTDALBGNLS3D/graph.json","events_json":"https://pith.science/api/pith-number/APAUXL4MMB23EYBTDALBGNLS3D/events.json","paper":"https://pith.science/paper/APAUXL4M"},"agent_actions":{"view_html":"https://pith.science/pith/APAUXL4MMB23EYBTDALBGNLS3D","download_json":"https://pith.science/pith/APAUXL4MMB23EYBTDALBGNLS3D.json","view_paper":"https://pith.science/paper/APAUXL4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.01626&json=true","fetch_graph":"https://pith.science/api/pith-number/APAUXL4MMB23EYBTDALBGNLS3D/graph.json","fetch_events":"https://pith.science/api/pith-number/APAUXL4MMB23EYBTDALBGNLS3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APAUXL4MMB23EYBTDALBGNLS3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APAUXL4MMB23EYBTDALBGNLS3D/action/storage_attestation","attest_author":"https://pith.science/pith/APAUXL4MMB23EYBTDALBGNLS3D/action/author_attestation","sign_citation":"https://pith.science/pith/APAUXL4MMB23EYBTDALBGNLS3D/action/citation_signature","submit_replication":"https://pith.science/pith/APAUXL4MMB23EYBTDALBGNLS3D/action/replication_record"}},"created_at":"2026-05-18T01:17:52.524152+00:00","updated_at":"2026-05-18T01:17:52.524152+00:00"}