{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3UC2U7FP7SBFAOLC6MJT76LWZ5","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":"65e249966b42111d98e14396fb65487a0c6d15ce694543920147a6c366cda9ca","cross_cats_sorted":["cs.CC","cs.CL","cs.DS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T00:45:31Z","title_canon_sha256":"15a8dab6ed4aa03af56c20379d21b0cce71110293f10d2c71c81fd0c248425c6"},"schema_version":"1.0","source":{"id":"2402.04497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04497","created_at":"2026-07-05T07:42:27Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04497v1","created_at":"2026-07-05T07:42:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04497","created_at":"2026-07-05T07:42:27Z"},{"alias_kind":"pith_short_12","alias_value":"3UC2U7FP7SBF","created_at":"2026-07-05T07:42:27Z"},{"alias_kind":"pith_short_16","alias_value":"3UC2U7FP7SBFAOLC","created_at":"2026-07-05T07:42:27Z"},{"alias_kind":"pith_short_8","alias_value":"3UC2U7FP","created_at":"2026-07-05T07:42:27Z"}],"graph_snapshots":[{"event_id":"sha256:bcfd87d955c6b06884391238abfff7e68247f9b4a45866d2f737e5b5914712e8","target":"graph","created_at":"2026-07-05T07:42:27Z","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/2402.04497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have made fundamental contributions over the last a few years. To train an LLM, one needs to alternatingly run `forward' computations and `backward' computations. The forward computation can be viewed as attention function evaluation, and the backward computation can be viewed as a gradient computation. In previous work by [Alman and Song, NeurIPS 2023], it was proved that the forward step can be performed in almost-linear time in certain parameter regimes, but that there is no truly sub-quadratic time algorithm in the remaining parameter regimes unless the popular","authors_text":"Josh Alman, Zhao Song","cross_cats":["cs.CC","cs.CL","cs.DS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T00:45:31Z","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04497","kind":"arxiv","version":1},"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:ae132014d5d9e673ac70f6826207c7fda939485fcc9dcc3a181635bfcc8cd590","target":"record","created_at":"2026-07-05T07:42:27Z","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":"65e249966b42111d98e14396fb65487a0c6d15ce694543920147a6c366cda9ca","cross_cats_sorted":["cs.CC","cs.CL","cs.DS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T00:45:31Z","title_canon_sha256":"15a8dab6ed4aa03af56c20379d21b0cce71110293f10d2c71c81fd0c248425c6"},"schema_version":"1.0","source":{"id":"2402.04497","kind":"arxiv","version":1}},"canonical_sha256":"dd05aa7caffc82503962f3133ff976cf78bb5c87cca03d08b6335b02d75577f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd05aa7caffc82503962f3133ff976cf78bb5c87cca03d08b6335b02d75577f3","first_computed_at":"2026-07-05T07:42:27.654575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:27.654575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L9SDplXkHHV51ljqCFi96cSsXvCPNuPu5VPqNsk7XAg8uBDnhc5A54/iP93dliVKzRMsA3QikYbJ1dY/5onhDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:27.655073Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae132014d5d9e673ac70f6826207c7fda939485fcc9dcc3a181635bfcc8cd590","sha256:bcfd87d955c6b06884391238abfff7e68247f9b4a45866d2f737e5b5914712e8"],"state_sha256":"ab2074de78d38b55dc2276e06435e4a86f99d439f44b97e936005bdf7e1ae4da"}