{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V6WUGBNWBWXAMXYPFAPDURCXK7","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":"babad252ce30e3b5d5b42cd5b58d7ef975e4c0a18a9e85643b4016f4a220ef43","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T14:40:28Z","title_canon_sha256":"21fae680e63046a4b01fb1f7a2f3ee04da7e5f4286f01543149cae4575690614"},"schema_version":"1.0","source":{"id":"2302.01128","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01128","created_at":"2026-07-05T06:21:30Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01128v3","created_at":"2026-07-05T06:21:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01128","created_at":"2026-07-05T06:21:30Z"},{"alias_kind":"pith_short_12","alias_value":"V6WUGBNWBWXA","created_at":"2026-07-05T06:21:30Z"},{"alias_kind":"pith_short_16","alias_value":"V6WUGBNWBWXAMXYP","created_at":"2026-07-05T06:21:30Z"},{"alias_kind":"pith_short_8","alias_value":"V6WUGBNW","created_at":"2026-07-05T06:21:30Z"}],"graph_snapshots":[{"event_id":"sha256:a84c32cc8c51a78e250b18ebc581bd9c77595f65bd32ea2cb477476f4ade59d4","target":"graph","created_at":"2026-07-05T06:21:30Z","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/2302.01128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose a new class of learnable optimizers, called \\textit{Mnemosyne}. It is based on the novel spatio-temporal low-rank implicit attention Transformers that can learn to train entire neural network architectures, including other Transformers, without any task-specific optimizer tuning. We show that Mnemosyne: (a) outperforms popular LSTM optimizers (also with new feature engineering to mitigate catastrophic forgetting of LSTMs), (b) can successfully train Transformers while using simple meta-training strategies that require minimal computational resources, (c) matches accura","authors_text":"Avinava Dubey, Deepali Jain, Jie Tan, Krzysztof Marcin Choromanski, Sumeet Singh, Tingnan Zhang, Vikas Sindhwani","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T14:40:28Z","title":"Mnemosyne: Learning to Train Transformers with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01128","kind":"arxiv","version":3},"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":"sha256:9833d06faf139ca786ef7e533a600f2b678fca984d90b6aa092c2f65b8721c58","target":"record","created_at":"2026-07-05T06:21:30Z","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":"babad252ce30e3b5d5b42cd5b58d7ef975e4c0a18a9e85643b4016f4a220ef43","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T14:40:28Z","title_canon_sha256":"21fae680e63046a4b01fb1f7a2f3ee04da7e5f4286f01543149cae4575690614"},"schema_version":"1.0","source":{"id":"2302.01128","kind":"arxiv","version":3}},"canonical_sha256":"afad4305b60dae065f0f281e3a445757ef98cb47569d532314cfe4d4dfc00632","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afad4305b60dae065f0f281e3a445757ef98cb47569d532314cfe4d4dfc00632","first_computed_at":"2026-07-05T06:21:30.410215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:30.410215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bjp21fnkIHppOFFxzQqBs0GFQmcjDsmWjhB6eA2gLr2ROk5zNZNuMktAfYofFSWgmcv+z3RNV28VUYfQme2XDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:30.410751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.01128","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9833d06faf139ca786ef7e533a600f2b678fca984d90b6aa092c2f65b8721c58","sha256:a84c32cc8c51a78e250b18ebc581bd9c77595f65bd32ea2cb477476f4ade59d4"],"state_sha256":"faf77532451d7f42b84355b74a920ddd43ed5e2d4090346fd266d877655bc9b5"}