{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WGBJ4IXUXLZ4ODUHQU5FQ4WMUW","short_pith_number":"pith:WGBJ4IXU","schema_version":"1.0","canonical_sha256":"b1829e22f4baf3c70e87853a5872cca5ba3ce5c26775f1ecffa1b08f70fc9c61","source":{"kind":"arxiv","id":"2107.02192","version":3},"attestation_state":"computed","paper":{"title":"Long-Short Transformer: Efficient Transformers for Language and Vision","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Anima Anandkumar, Bryan Catanzaro, Chaowei Xiao, Chen Zhu, Mohammad Shoeybi, Tom Goldstein, Wei Ping","submitted_at":"2021-07-05T18:00:14Z","abstract_excerpt":"Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic time and memory complexities with respect to the input sequence length. In this paper, we propose Long-Short Transformer (Transformer-LS), an efficient self-attention mechanism for modeling long sequences with linear complexity for both language and vision tasks. It aggregates a novel long-range attention with dynamic projection to model distant correlations"},"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":"2107.02192","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-05T18:00:14Z","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"405feabb4d2e053be8e8970d92d791245725d0fc76a6b7e0b1414e40047109fd","abstract_canon_sha256":"32e24cf46df69225a75fbaf2a1f1d93892246a8bf01babad5211c8072c3a5a12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:22.504951Z","signature_b64":"yaDIEzjtNkGyDRYHW36zBkdXi4vBpWcSF7bVOBvm6LmYpJVQLryscLw4eEbOTWQU2fS9y80dXaU9OBp5P4QvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1829e22f4baf3c70e87853a5872cca5ba3ce5c26775f1ecffa1b08f70fc9c61","last_reissued_at":"2026-07-05T03:38:22.504443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:22.504443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-Short Transformer: Efficient Transformers for Language and Vision","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Anima Anandkumar, Bryan Catanzaro, Chaowei Xiao, Chen Zhu, Mohammad Shoeybi, Tom Goldstein, Wei Ping","submitted_at":"2021-07-05T18:00:14Z","abstract_excerpt":"Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic time and memory complexities with respect to the input sequence length. In this paper, we propose Long-Short Transformer (Transformer-LS), an efficient self-attention mechanism for modeling long sequences with linear complexity for both language and vision tasks. It aggregates a novel long-range attention with dynamic projection to model distant correlations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02192","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.02192/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":"2107.02192","created_at":"2026-07-05T03:38:22.504505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.02192v3","created_at":"2026-07-05T03:38:22.504505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02192","created_at":"2026-07-05T03:38:22.504505+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGBJ4IXUXLZ4","created_at":"2026-07-05T03:38:22.504505+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGBJ4IXUXLZ4ODUH","created_at":"2026-07-05T03:38:22.504505+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGBJ4IXU","created_at":"2026-07-05T03:38:22.504505+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/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW","json":"https://pith.science/pith/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW.json","graph_json":"https://pith.science/api/pith-number/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW/graph.json","events_json":"https://pith.science/api/pith-number/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW/events.json","paper":"https://pith.science/paper/WGBJ4IXU"},"agent_actions":{"view_html":"https://pith.science/pith/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW","download_json":"https://pith.science/pith/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW.json","view_paper":"https://pith.science/paper/WGBJ4IXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.02192&json=true","fetch_graph":"https://pith.science/api/pith-number/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW/graph.json","fetch_events":"https://pith.science/api/pith-number/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW/action/storage_attestation","attest_author":"https://pith.science/pith/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW/action/author_attestation","sign_citation":"https://pith.science/pith/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW/action/citation_signature","submit_replication":"https://pith.science/pith/WGBJ4IXUXLZ4ODUHQU5FQ4WMUW/action/replication_record"}},"created_at":"2026-07-05T03:38:22.504505+00:00","updated_at":"2026-07-05T03:38:22.504505+00:00"}