{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:YNBBOI34VBEEKBDNKKABTK3NXM","short_pith_number":"pith:YNBBOI34","schema_version":"1.0","canonical_sha256":"c34217237ca84845046d528019ab6dbb319f632440e0c4c74fd55c0d777819ae","source":{"kind":"arxiv","id":"1612.08083","version":3},"attestation_state":"computed","paper":{"title":"Language Modeling with Gated Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angela Fan, David Grangier, Michael Auli, Yann N. Dauphin","submitted_at":"2016-12-23T20:32:33Z","abstract_excerpt":"The pre-dominant approach to language modeling to date is based on recurrent neural networks. Their success on this task is often linked to their ability to capture unbounded context. In this paper we develop a finite context approach through stacked convolutions, which can be more efficient since they allow parallelization over sequential tokens. We propose a novel simplified gating mechanism that outperforms Oord et al (2016) and investigate the impact of key architectural decisions. The proposed approach achieves state-of-the-art on the WikiText-103 benchmark, even though it features long-t"},"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":"1612.08083","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-23T20:32:33Z","cross_cats_sorted":[],"title_canon_sha256":"b603c8af5845ea66f356e172367082cd9077f5e2aa454bc56dc4fe0b727642be","abstract_canon_sha256":"bb3273ebd83b8cdbb66a7c3e94f17deef8b87e89871374b3b2b67cd6dc422f43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:43.757990Z","signature_b64":"0y3QYiBBccrFti1eN5XYDuw86vwp+rSYvXxBB5gnx7mh248I3rX+QtlDQqb0av8J/uM5i+fMiZdVP0c7m2FTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c34217237ca84845046d528019ab6dbb319f632440e0c4c74fd55c0d777819ae","last_reissued_at":"2026-05-18T00:35:43.757458Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:43.757458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Modeling with Gated Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angela Fan, David Grangier, Michael Auli, Yann N. Dauphin","submitted_at":"2016-12-23T20:32:33Z","abstract_excerpt":"The pre-dominant approach to language modeling to date is based on recurrent neural networks. Their success on this task is often linked to their ability to capture unbounded context. In this paper we develop a finite context approach through stacked convolutions, which can be more efficient since they allow parallelization over sequential tokens. We propose a novel simplified gating mechanism that outperforms Oord et al (2016) and investigate the impact of key architectural decisions. The proposed approach achieves state-of-the-art on the WikiText-103 benchmark, even though it features long-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08083","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":"1612.08083","created_at":"2026-05-18T00:35:43.757537+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.08083v3","created_at":"2026-05-18T00:35:43.757537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08083","created_at":"2026-05-18T00:35:43.757537+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNBBOI34VBEE","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNBBOI34VBEEKBDN","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNBBOI34","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2511.21300","citing_title":"Data-Driven Reduction of Fault Location Errors in Onshore Wind Farm Collectors","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07347","citing_title":"Fake News Detection as Natural Language Inference","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21798","citing_title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15216","citing_title":"Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations","ref_index":106,"is_internal_anchor":true},{"citing_arxiv_id":"1911.05507","citing_title":"Compressive Transformers for Long-Range Sequence Modelling","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2311.16867","citing_title":"The Falcon Series of Open Language Models","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15183","citing_title":"When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1710.05941","citing_title":"Searching for Activation Functions","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06578","citing_title":"Resource-Efficient CSI Prediction: A Gated Fusion and Factorized Projection Approach","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07437","citing_title":"ASTRAFier: A Novel and Scalable Transformer-based Stellar Variability Classifier","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2002.05202","citing_title":"GLU Variants Improve Transformer","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YNBBOI34VBEEKBDNKKABTK3NXM","json":"https://pith.science/pith/YNBBOI34VBEEKBDNKKABTK3NXM.json","graph_json":"https://pith.science/api/pith-number/YNBBOI34VBEEKBDNKKABTK3NXM/graph.json","events_json":"https://pith.science/api/pith-number/YNBBOI34VBEEKBDNKKABTK3NXM/events.json","paper":"https://pith.science/paper/YNBBOI34"},"agent_actions":{"view_html":"https://pith.science/pith/YNBBOI34VBEEKBDNKKABTK3NXM","download_json":"https://pith.science/pith/YNBBOI34VBEEKBDNKKABTK3NXM.json","view_paper":"https://pith.science/paper/YNBBOI34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.08083&json=true","fetch_graph":"https://pith.science/api/pith-number/YNBBOI34VBEEKBDNKKABTK3NXM/graph.json","fetch_events":"https://pith.science/api/pith-number/YNBBOI34VBEEKBDNKKABTK3NXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNBBOI34VBEEKBDNKKABTK3NXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNBBOI34VBEEKBDNKKABTK3NXM/action/storage_attestation","attest_author":"https://pith.science/pith/YNBBOI34VBEEKBDNKKABTK3NXM/action/author_attestation","sign_citation":"https://pith.science/pith/YNBBOI34VBEEKBDNKKABTK3NXM/action/citation_signature","submit_replication":"https://pith.science/pith/YNBBOI34VBEEKBDNKKABTK3NXM/action/replication_record"}},"created_at":"2026-05-18T00:35:43.757537+00:00","updated_at":"2026-05-18T00:35:43.757537+00:00"}