{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:NHD5ETVOVDO4K7DG56JOVPYY3Q","short_pith_number":"pith:NHD5ETVO","schema_version":"1.0","canonical_sha256":"69c7d24eaea8ddc57c66ef92eabf18dc0d1404198306fdd4414a6067c0c1da04","source":{"kind":"arxiv","id":"1607.02789","version":1},"attestation_state":"computed","paper":{"title":"Charagram: Embedding Words and Sentences via Character n-grams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Wieting, Karen Livescu, Kevin Gimpel, Mohit Bansal","submitted_at":"2016-07-10T21:59:19Z","abstract_excerpt":"We present Charagram embeddings, a simple approach for learning character-based compositional models to embed textual sequences. A word or sentence is represented using a character n-gram count vector, followed by a single nonlinear transformation to yield a low-dimensional embedding. We use three tasks for evaluation: word similarity, sentence similarity, and part-of-speech tagging. We demonstrate that Charagram embeddings outperform more complex architectures based on character-level recurrent and convolutional neural networks, achieving new state-of-the-art performance on several similarity"},"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":"1607.02789","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-10T21:59:19Z","cross_cats_sorted":[],"title_canon_sha256":"0d9ddb836c6be35456b8089bf96074b8bb310fc94d4d34f55e854cc48bb4c3f7","abstract_canon_sha256":"5b5fdc8c6c72a9b86182355feb66b43d3d3e3a6b0f1044627aa822417df58760"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:16.135576Z","signature_b64":"TIMluljwzPjbqPmF0mBrnojCR0hSwShAJLzLwjiel4xBwuN2iu21y4g2vCBd5SlAG7X00mdFcbAt9iv03Zo9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69c7d24eaea8ddc57c66ef92eabf18dc0d1404198306fdd4414a6067c0c1da04","last_reissued_at":"2026-05-18T01:11:16.134904Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:16.134904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Charagram: Embedding Words and Sentences via Character n-grams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Wieting, Karen Livescu, Kevin Gimpel, Mohit Bansal","submitted_at":"2016-07-10T21:59:19Z","abstract_excerpt":"We present Charagram embeddings, a simple approach for learning character-based compositional models to embed textual sequences. A word or sentence is represented using a character n-gram count vector, followed by a single nonlinear transformation to yield a low-dimensional embedding. We use three tasks for evaluation: word similarity, sentence similarity, and part-of-speech tagging. We demonstrate that Charagram embeddings outperform more complex architectures based on character-level recurrent and convolutional neural networks, achieving new state-of-the-art performance on several similarity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.02789","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":""},"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":"1607.02789","created_at":"2026-05-18T01:11:16.135013+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.02789v1","created_at":"2026-05-18T01:11:16.135013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.02789","created_at":"2026-05-18T01:11:16.135013+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHD5ETVOVDO4","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHD5ETVOVDO4K7DG","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHD5ETVO","created_at":"2026-05-18T12:30:32.724797+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/NHD5ETVOVDO4K7DG56JOVPYY3Q","json":"https://pith.science/pith/NHD5ETVOVDO4K7DG56JOVPYY3Q.json","graph_json":"https://pith.science/api/pith-number/NHD5ETVOVDO4K7DG56JOVPYY3Q/graph.json","events_json":"https://pith.science/api/pith-number/NHD5ETVOVDO4K7DG56JOVPYY3Q/events.json","paper":"https://pith.science/paper/NHD5ETVO"},"agent_actions":{"view_html":"https://pith.science/pith/NHD5ETVOVDO4K7DG56JOVPYY3Q","download_json":"https://pith.science/pith/NHD5ETVOVDO4K7DG56JOVPYY3Q.json","view_paper":"https://pith.science/paper/NHD5ETVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.02789&json=true","fetch_graph":"https://pith.science/api/pith-number/NHD5ETVOVDO4K7DG56JOVPYY3Q/graph.json","fetch_events":"https://pith.science/api/pith-number/NHD5ETVOVDO4K7DG56JOVPYY3Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHD5ETVOVDO4K7DG56JOVPYY3Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHD5ETVOVDO4K7DG56JOVPYY3Q/action/storage_attestation","attest_author":"https://pith.science/pith/NHD5ETVOVDO4K7DG56JOVPYY3Q/action/author_attestation","sign_citation":"https://pith.science/pith/NHD5ETVOVDO4K7DG56JOVPYY3Q/action/citation_signature","submit_replication":"https://pith.science/pith/NHD5ETVOVDO4K7DG56JOVPYY3Q/action/replication_record"}},"created_at":"2026-05-18T01:11:16.135013+00:00","updated_at":"2026-05-18T01:11:16.135013+00:00"}