{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6HXF5F6QL22YZ4C2M2WW5J5Q3V","short_pith_number":"pith:6HXF5F6Q","schema_version":"1.0","canonical_sha256":"f1ee5e97d05eb58cf05a66ad6ea7b0dd44c3075f29e90566d852e440e6a9fe01","source":{"kind":"arxiv","id":"2311.14652","version":2},"attestation_state":"computed","paper":{"title":"One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chenyang Li, Chiwun Yang, Raghav Addanki, Zhao Song","submitted_at":"2023-11-24T18:35:00Z","abstract_excerpt":"Attention computation takes both the time complexity of $O(n^2)$ and the space complexity of $O(n^2)$ simultaneously, which makes deploying Large Language Models (LLMs) in streaming applications that involve long contexts requiring substantial computational resources. In recent OpenAI DevDay (Nov 6, 2023), OpenAI released a new model that is able to support a 128K-long document, in our paper, we focus on the memory-efficient issue when context length $n$ is much greater than 128K ($n \\gg 2^d$). Considering a single-layer self-attention with Query, Key, and Value matrices $Q, K, V \\in \\mathbb{R"},"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":"2311.14652","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-24T18:35:00Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"c07dc4e69b61de194144fad414d21e53fb24c03e9cfbf08e23694855e445c1d4","abstract_canon_sha256":"60f0dae8e04b5d139ca9e4c81be86b1c936fd6e48afa62da123f8876d1e21528"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:28.312126Z","signature_b64":"XGMe13BK8Q3fNCc9/P8AmGuZfPIpARavfIgm29HLoXO4rEFToyiKMaWlwH4x2vGtI4UW81/ffVBBzmWxk7x3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1ee5e97d05eb58cf05a66ad6ea7b0dd44c3075f29e90566d852e440e6a9fe01","last_reissued_at":"2026-07-05T07:41:28.311397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:28.311397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chenyang Li, Chiwun Yang, Raghav Addanki, Zhao Song","submitted_at":"2023-11-24T18:35:00Z","abstract_excerpt":"Attention computation takes both the time complexity of $O(n^2)$ and the space complexity of $O(n^2)$ simultaneously, which makes deploying Large Language Models (LLMs) in streaming applications that involve long contexts requiring substantial computational resources. In recent OpenAI DevDay (Nov 6, 2023), OpenAI released a new model that is able to support a 128K-long document, in our paper, we focus on the memory-efficient issue when context length $n$ is much greater than 128K ($n \\gg 2^d$). Considering a single-layer self-attention with Query, Key, and Value matrices $Q, K, V \\in \\mathbb{R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14652","kind":"arxiv","version":2},"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/2311.14652/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":"2311.14652","created_at":"2026-07-05T07:41:28.311515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14652v2","created_at":"2026-07-05T07:41:28.311515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14652","created_at":"2026-07-05T07:41:28.311515+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HXF5F6QL22Y","created_at":"2026-07-05T07:41:28.311515+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HXF5F6QL22YZ4C2","created_at":"2026-07-05T07:41:28.311515+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HXF5F6Q","created_at":"2026-07-05T07:41:28.311515+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/6HXF5F6QL22YZ4C2M2WW5J5Q3V","json":"https://pith.science/pith/6HXF5F6QL22YZ4C2M2WW5J5Q3V.json","graph_json":"https://pith.science/api/pith-number/6HXF5F6QL22YZ4C2M2WW5J5Q3V/graph.json","events_json":"https://pith.science/api/pith-number/6HXF5F6QL22YZ4C2M2WW5J5Q3V/events.json","paper":"https://pith.science/paper/6HXF5F6Q"},"agent_actions":{"view_html":"https://pith.science/pith/6HXF5F6QL22YZ4C2M2WW5J5Q3V","download_json":"https://pith.science/pith/6HXF5F6QL22YZ4C2M2WW5J5Q3V.json","view_paper":"https://pith.science/paper/6HXF5F6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14652&json=true","fetch_graph":"https://pith.science/api/pith-number/6HXF5F6QL22YZ4C2M2WW5J5Q3V/graph.json","fetch_events":"https://pith.science/api/pith-number/6HXF5F6QL22YZ4C2M2WW5J5Q3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HXF5F6QL22YZ4C2M2WW5J5Q3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HXF5F6QL22YZ4C2M2WW5J5Q3V/action/storage_attestation","attest_author":"https://pith.science/pith/6HXF5F6QL22YZ4C2M2WW5J5Q3V/action/author_attestation","sign_citation":"https://pith.science/pith/6HXF5F6QL22YZ4C2M2WW5J5Q3V/action/citation_signature","submit_replication":"https://pith.science/pith/6HXF5F6QL22YZ4C2M2WW5J5Q3V/action/replication_record"}},"created_at":"2026-07-05T07:41:28.311515+00:00","updated_at":"2026-07-05T07:41:28.311515+00:00"}