{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DE4MIA3IIQNASADBKFX4VRRIRZ","short_pith_number":"pith:DE4MIA3I","schema_version":"1.0","canonical_sha256":"1938c40368441a090061516fcac6288e4f986f490d8a89a9861a5e5df1148955","source":{"kind":"arxiv","id":"2004.11886","version":1},"attestation_state":"computed","paper":{"title":"Lite Transformer with Long-Short Range Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ji Lin, Song Han, Yujun Lin, Zhanghao Wu, Zhijian Liu","submitted_at":"2020-04-24T17:52:25Z","abstract_excerpt":"Transformer has become ubiquitous in natural language processing (e.g., machine translation, question answering); however, it requires enormous amount of computations to achieve high performance, which makes it not suitable for mobile applications that are tightly constrained by the hardware resources and battery. In this paper, we present an efficient mobile NLP architecture, Lite Transformer to facilitate deploying mobile NLP applications on edge devices. The key primitive is the Long-Short Range Attention (LSRA), where one group of heads specializes in the local context modeling (by convolu"},"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":"2004.11886","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-24T17:52:25Z","cross_cats_sorted":[],"title_canon_sha256":"30dba798f1f29dec0dfd339db4583684fcf1b129074b8a112862efeffaf2cf6f","abstract_canon_sha256":"93580f5aca5ec3d3983786048672de84f7789b2cf8ab5f3d489e5b61a4a82fc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:58.780302Z","signature_b64":"ADJRyVuJ/od6ZNd7xuh5sOVXptl4xpsDFWb/9XErg00AHDqiYi7jN09QmbRRhEePEipirxOUVQSfG4nc26ZGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1938c40368441a090061516fcac6288e4f986f490d8a89a9861a5e5df1148955","last_reissued_at":"2026-07-05T00:57:58.779760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:58.779760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lite Transformer with Long-Short Range Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ji Lin, Song Han, Yujun Lin, Zhanghao Wu, Zhijian Liu","submitted_at":"2020-04-24T17:52:25Z","abstract_excerpt":"Transformer has become ubiquitous in natural language processing (e.g., machine translation, question answering); however, it requires enormous amount of computations to achieve high performance, which makes it not suitable for mobile applications that are tightly constrained by the hardware resources and battery. In this paper, we present an efficient mobile NLP architecture, Lite Transformer to facilitate deploying mobile NLP applications on edge devices. The key primitive is the Long-Short Range Attention (LSRA), where one group of heads specializes in the local context modeling (by convolu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.11886","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/2004.11886/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":"2004.11886","created_at":"2026-07-05T00:57:58.779818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.11886v1","created_at":"2026-07-05T00:57:58.779818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.11886","created_at":"2026-07-05T00:57:58.779818+00:00"},{"alias_kind":"pith_short_12","alias_value":"DE4MIA3IIQNA","created_at":"2026-07-05T00:57:58.779818+00:00"},{"alias_kind":"pith_short_16","alias_value":"DE4MIA3IIQNASADB","created_at":"2026-07-05T00:57:58.779818+00:00"},{"alias_kind":"pith_short_8","alias_value":"DE4MIA3I","created_at":"2026-07-05T00:57:58.779818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04032","citing_title":"Do Transformers Need Three Projections? Systematic Study of QKV Variants","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15077","citing_title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11007","citing_title":"The Transformer as a Polar State Estimator","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02184","citing_title":"RAFNet: Region-Aware Fusion Network for Pansharpening","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DE4MIA3IIQNASADBKFX4VRRIRZ","json":"https://pith.science/pith/DE4MIA3IIQNASADBKFX4VRRIRZ.json","graph_json":"https://pith.science/api/pith-number/DE4MIA3IIQNASADBKFX4VRRIRZ/graph.json","events_json":"https://pith.science/api/pith-number/DE4MIA3IIQNASADBKFX4VRRIRZ/events.json","paper":"https://pith.science/paper/DE4MIA3I"},"agent_actions":{"view_html":"https://pith.science/pith/DE4MIA3IIQNASADBKFX4VRRIRZ","download_json":"https://pith.science/pith/DE4MIA3IIQNASADBKFX4VRRIRZ.json","view_paper":"https://pith.science/paper/DE4MIA3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.11886&json=true","fetch_graph":"https://pith.science/api/pith-number/DE4MIA3IIQNASADBKFX4VRRIRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DE4MIA3IIQNASADBKFX4VRRIRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DE4MIA3IIQNASADBKFX4VRRIRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DE4MIA3IIQNASADBKFX4VRRIRZ/action/storage_attestation","attest_author":"https://pith.science/pith/DE4MIA3IIQNASADBKFX4VRRIRZ/action/author_attestation","sign_citation":"https://pith.science/pith/DE4MIA3IIQNASADBKFX4VRRIRZ/action/citation_signature","submit_replication":"https://pith.science/pith/DE4MIA3IIQNASADBKFX4VRRIRZ/action/replication_record"}},"created_at":"2026-07-05T00:57:58.779818+00:00","updated_at":"2026-07-05T00:57:58.779818+00:00"}