{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DM55SWHHWQ2UNBXJFEMFZKGJSZ","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":"9d533a51b95205683d6bb5ecf01667eba06a1411cd693a0cdf6a638f1bda0399","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-15T23:25:11Z","title_canon_sha256":"a5e0cc7b7136151a06c252edd03b8ba09e6934b672115f208bf9fce4ecefcfb4"},"schema_version":"1.0","source":{"id":"2503.12295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12295","created_at":"2026-07-05T10:32:43Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12295v1","created_at":"2026-07-05T10:32:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12295","created_at":"2026-07-05T10:32:43Z"},{"alias_kind":"pith_short_12","alias_value":"DM55SWHHWQ2U","created_at":"2026-07-05T10:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"DM55SWHHWQ2UNBXJ","created_at":"2026-07-05T10:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"DM55SWHH","created_at":"2026-07-05T10:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:e3048e5823834aa56cc498bb4a799f33edcb64a1b426179f194ccbdb496e8f56","target":"graph","created_at":"2026-07-05T10:32:43Z","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/2503.12295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates whether sequence models can learn to perform numerical algorithms, e.g. gradient descent, on the fundamental problem of least squares. Our goal is to inherit two properties of standard algorithms from numerical analysis: (1) machine precision, i.e. we want to obtain solutions that are accurate to near floating point error, and (2) numerical generality, i.e. we want them to apply broadly across problem instances. We find that prior approaches using Transformers fail to meet these criteria, and identify limitations present in existing architectures and training procedures","authors_text":"Ashish Rao, Atri Rudra, Christopher R\\'e, Jerry Liu, Jessica Grogan, Owen Dugan, Simran Arora","cross_cats":["cs.NA","math.NA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-15T23:25:11Z","title":"Towards Learning High-Precision Least Squares Algorithms with Sequence Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12295","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":"sha256:104db9342f1a36d298074ca016a85cfe0c14575c9572dc8e3fa2ea7f7ed007b5","target":"record","created_at":"2026-07-05T10:32:43Z","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":"9d533a51b95205683d6bb5ecf01667eba06a1411cd693a0cdf6a638f1bda0399","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-15T23:25:11Z","title_canon_sha256":"a5e0cc7b7136151a06c252edd03b8ba09e6934b672115f208bf9fce4ecefcfb4"},"schema_version":"1.0","source":{"id":"2503.12295","kind":"arxiv","version":1}},"canonical_sha256":"1b3bd958e7b4354686e929185ca8c99658f218d31a4cde2f54513708010c7c65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b3bd958e7b4354686e929185ca8c99658f218d31a4cde2f54513708010c7c65","first_computed_at":"2026-07-05T10:32:43.036409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:43.036409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mT7jWyQZpNlmMbKJ7iX7rjhG0ej/E6y8Pb9MM1uC7c+UatUOGXHgKW4NKi88ll1NQ+cOW9vI956ekBK4PN1jCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:43.037086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:104db9342f1a36d298074ca016a85cfe0c14575c9572dc8e3fa2ea7f7ed007b5","sha256:e3048e5823834aa56cc498bb4a799f33edcb64a1b426179f194ccbdb496e8f56"],"state_sha256":"10973397dc2e50be04d0c1197fd66609c44e75d04b95192c27c8894b12ee68c3"}