{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7BRVTDP5ITBO6IOVGG3PRZBTSP","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":"e3fc448cdc62efcb4b13d1ceb9a1755dcf17fbb7b1b1ab7a5ba506b34b562da5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-23T17:16:43Z","title_canon_sha256":"aa76071ada333c239508e30174d87a0598cc89a4db5507dec1853b58c65e8b14"},"schema_version":"1.0","source":{"id":"2408.13233","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13233","created_at":"2026-07-05T09:20:47Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13233v2","created_at":"2026-07-05T09:20:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13233","created_at":"2026-07-05T09:20:47Z"},{"alias_kind":"pith_short_12","alias_value":"7BRVTDP5ITBO","created_at":"2026-07-05T09:20:47Z"},{"alias_kind":"pith_short_16","alias_value":"7BRVTDP5ITBO6IOV","created_at":"2026-07-05T09:20:47Z"},{"alias_kind":"pith_short_8","alias_value":"7BRVTDP5","created_at":"2026-07-05T09:20:47Z"}],"graph_snapshots":[{"event_id":"sha256:41b97f38e1917972fe94354bbce16b6e9af48abf7f461f48e163b821135cf297","target":"graph","created_at":"2026-07-05T09:20:47Z","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/2408.13233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The computational complexity of the self-attention mechanism in popular transformer architectures poses significant challenges for training and inference, and becomes the bottleneck for long inputs. Is it possible to significantly reduce the quadratic time complexity of computing the gradients in multi-layer transformer models? This paper proves that a novel fast approximation method can calculate the gradients in almost linear time $n^{1+o(1)}$ where $n$ is the input sequence length, while it maintains a polynomially small approximation error $1 / \\mathrm{poly}(n)$ across the entire model. Ou","authors_text":"Yingyu Liang, Yufa Zhou, Zhao Song, Zhenmei Shi, Zhizhou Sha","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-23T17:16:43Z","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13233","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":"sha256:7cf7439f72bc9f6a9711906affee728816c39ca68e3bcfff33ff5085af52b2f1","target":"record","created_at":"2026-07-05T09:20:47Z","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":"e3fc448cdc62efcb4b13d1ceb9a1755dcf17fbb7b1b1ab7a5ba506b34b562da5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-23T17:16:43Z","title_canon_sha256":"aa76071ada333c239508e30174d87a0598cc89a4db5507dec1853b58c65e8b14"},"schema_version":"1.0","source":{"id":"2408.13233","kind":"arxiv","version":2}},"canonical_sha256":"f863598dfd44c2ef21d531b6f8e43393d1c43c14dcfcb9712be8c6559f6c13ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f863598dfd44c2ef21d531b6f8e43393d1c43c14dcfcb9712be8c6559f6c13ba","first_computed_at":"2026-07-05T09:20:47.245813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:47.245813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BjGPZVMJMeZOQTWrO3nY/1SuB1n48cH4MrNJ66VwxlxXSmLcHTEQXzTCb2GNRLtLIllfDVP6U77/LboAueIIAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:47.246353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.13233","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cf7439f72bc9f6a9711906affee728816c39ca68e3bcfff33ff5085af52b2f1","sha256:41b97f38e1917972fe94354bbce16b6e9af48abf7f461f48e163b821135cf297"],"state_sha256":"19fb38569c25122bd423b2c64746ed32fe1f5fa66357f31102aed8a4e2e4c036"}