{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NQBNU4RWADUOG57SDOJSB5YLZP","short_pith_number":"pith:NQBNU4RW","canonical_record":{"source":{"id":"2308.14304","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-28T04:37:38Z","cross_cats_sorted":[],"title_canon_sha256":"a10250c00d46cf750ce5528e26ac9936b9aa8fe5e5db351594152696b7ad7e76","abstract_canon_sha256":"2bb33d248267dc80f718fe02a85a07fdac0fed3d326dfa3ed49846f8a1d9a428"},"schema_version":"1.0"},"canonical_sha256":"6c02da723600e8e377f21b9320f70bcbc26dbee859a8c1c77e8fae19f5aa965c","source":{"kind":"arxiv","id":"2308.14304","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.14304","created_at":"2026-07-05T08:03:06Z"},{"alias_kind":"arxiv_version","alias_value":"2308.14304v2","created_at":"2026-07-05T08:03:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14304","created_at":"2026-07-05T08:03:06Z"},{"alias_kind":"pith_short_12","alias_value":"NQBNU4RWADUO","created_at":"2026-07-05T08:03:06Z"},{"alias_kind":"pith_short_16","alias_value":"NQBNU4RWADUOG57S","created_at":"2026-07-05T08:03:06Z"},{"alias_kind":"pith_short_8","alias_value":"NQBNU4RW","created_at":"2026-07-05T08:03:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NQBNU4RWADUOG57SDOJSB5YLZP","target":"record","payload":{"canonical_record":{"source":{"id":"2308.14304","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-28T04:37:38Z","cross_cats_sorted":[],"title_canon_sha256":"a10250c00d46cf750ce5528e26ac9936b9aa8fe5e5db351594152696b7ad7e76","abstract_canon_sha256":"2bb33d248267dc80f718fe02a85a07fdac0fed3d326dfa3ed49846f8a1d9a428"},"schema_version":"1.0"},"canonical_sha256":"6c02da723600e8e377f21b9320f70bcbc26dbee859a8c1c77e8fae19f5aa965c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:06.847913Z","signature_b64":"tbHmqsDxwv6LW/h3WX7h/AsEhHdaDGL/cRmJTYV0tbriHLjd2McjJlvC75yFe4jg/vyTrr/xnMpFhqry7kSYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c02da723600e8e377f21b9320f70bcbc26dbee859a8c1c77e8fae19f5aa965c","last_reissued_at":"2026-07-05T08:03:06.847441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:06.847441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.14304","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SACM+KWdCNq7wXfrZWrf6DgrN95eEuA0W6IlUADJcmSp5Hz8oZeJ2pskV6SYGKRuYq13tq8muY/P5iqozyXiCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:01:35.349216Z"},"content_sha256":"933c1ea5a4f85a536064bc124a70e25e844d25ba72f208380e99642d2ac2a95c","schema_version":"1.0","event_id":"sha256:933c1ea5a4f85a536064bc124a70e25e844d25ba72f208380e99642d2ac2a95c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NQBNU4RWADUOG57SDOJSB5YLZP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Solving Attention Kernel Regression Problem via Pre-conditioner","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junze Yin, Lichen Zhang, Zhao Song","submitted_at":"2023-08-28T04:37:38Z","abstract_excerpt":"The attention mechanism is the key to large language models, and the attention matrix serves as an algorithmic and computational bottleneck for such a scheme. In this paper, we define two problems, motivated by designing fast algorithms for proxy of attention matrix and solving regressions against them. Given an input matrix $A\\in \\mathbb{R}^{n\\times d}$ with $n\\gg d$ and a response vector $b$, we first consider the matrix exponential of the matrix $A^\\top A$ as a proxy, and we in turn design algorithms for two types of regression problems: $\\min_{x\\in \\mathbb{R}^d}\\|(A^\\top A)^jx-b\\|_2$ and $"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14304","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/2308.14304/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xsNb1tvmvrhMD0aVWGkGRnp1no59IYK1XYWxrtqE6dz5Jc7LDNTSGUtBC+JkAeFwG/cM2EBXwwkrgN8DE1YgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:01:35.349883Z"},"content_sha256":"5f6cf16c9c927dad678c35ab8f438bdb84e0a5d86823901b049a01c92ef0bc75","schema_version":"1.0","event_id":"sha256:5f6cf16c9c927dad678c35ab8f438bdb84e0a5d86823901b049a01c92ef0bc75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NQBNU4RWADUOG57SDOJSB5YLZP/bundle.json","state_url":"https://pith.science/pith/NQBNU4RWADUOG57SDOJSB5YLZP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NQBNU4RWADUOG57SDOJSB5YLZP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T14:01:35Z","links":{"resolver":"https://pith.science/pith/NQBNU4RWADUOG57SDOJSB5YLZP","bundle":"https://pith.science/pith/NQBNU4RWADUOG57SDOJSB5YLZP/bundle.json","state":"https://pith.science/pith/NQBNU4RWADUOG57SDOJSB5YLZP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NQBNU4RWADUOG57SDOJSB5YLZP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NQBNU4RWADUOG57SDOJSB5YLZP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2bb33d248267dc80f718fe02a85a07fdac0fed3d326dfa3ed49846f8a1d9a428","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-28T04:37:38Z","title_canon_sha256":"a10250c00d46cf750ce5528e26ac9936b9aa8fe5e5db351594152696b7ad7e76"},"schema_version":"1.0","source":{"id":"2308.14304","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.14304","created_at":"2026-07-05T08:03:06Z"},{"alias_kind":"arxiv_version","alias_value":"2308.14304v2","created_at":"2026-07-05T08:03:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14304","created_at":"2026-07-05T08:03:06Z"},{"alias_kind":"pith_short_12","alias_value":"NQBNU4RWADUO","created_at":"2026-07-05T08:03:06Z"},{"alias_kind":"pith_short_16","alias_value":"NQBNU4RWADUOG57S","created_at":"2026-07-05T08:03:06Z"},{"alias_kind":"pith_short_8","alias_value":"NQBNU4RW","created_at":"2026-07-05T08:03:06Z"}],"graph_snapshots":[{"event_id":"sha256:5f6cf16c9c927dad678c35ab8f438bdb84e0a5d86823901b049a01c92ef0bc75","target":"graph","created_at":"2026-07-05T08:03:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.14304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The attention mechanism is the key to large language models, and the attention matrix serves as an algorithmic and computational bottleneck for such a scheme. In this paper, we define two problems, motivated by designing fast algorithms for proxy of attention matrix and solving regressions against them. Given an input matrix $A\\in \\mathbb{R}^{n\\times d}$ with $n\\gg d$ and a response vector $b$, we first consider the matrix exponential of the matrix $A^\\top A$ as a proxy, and we in turn design algorithms for two types of regression problems: $\\min_{x\\in \\mathbb{R}^d}\\|(A^\\top A)^jx-b\\|_2$ and $","authors_text":"Junze Yin, Lichen Zhang, Zhao Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-28T04:37:38Z","title":"Solving Attention Kernel Regression Problem via Pre-conditioner"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14304","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:933c1ea5a4f85a536064bc124a70e25e844d25ba72f208380e99642d2ac2a95c","target":"record","created_at":"2026-07-05T08:03:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2bb33d248267dc80f718fe02a85a07fdac0fed3d326dfa3ed49846f8a1d9a428","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-28T04:37:38Z","title_canon_sha256":"a10250c00d46cf750ce5528e26ac9936b9aa8fe5e5db351594152696b7ad7e76"},"schema_version":"1.0","source":{"id":"2308.14304","kind":"arxiv","version":2}},"canonical_sha256":"6c02da723600e8e377f21b9320f70bcbc26dbee859a8c1c77e8fae19f5aa965c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c02da723600e8e377f21b9320f70bcbc26dbee859a8c1c77e8fae19f5aa965c","first_computed_at":"2026-07-05T08:03:06.847441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:06.847441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tbHmqsDxwv6LW/h3WX7h/AsEhHdaDGL/cRmJTYV0tbriHLjd2McjJlvC75yFe4jg/vyTrr/xnMpFhqry7kSYCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:06.847913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.14304","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:933c1ea5a4f85a536064bc124a70e25e844d25ba72f208380e99642d2ac2a95c","sha256:5f6cf16c9c927dad678c35ab8f438bdb84e0a5d86823901b049a01c92ef0bc75"],"state_sha256":"390ede85168752746307d39b25f04ac2363df256f3d675abfabd2b7defd019b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KqmVH0ARsPxXDAe6WILZ36VAIPPrHnDqokC04hyeaVVKCMVoD+vTt4rNvRjZEJHcTbHafet89IU5tevCd4XyAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T14:01:35.352975Z","bundle_sha256":"f254742724450b458cde46e97d02c4d15fb2b48143ee7aa92ba01a3eb550c240"}}