{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6U5CPNKZHCGY7HFRTG4YSMLMNT","short_pith_number":"pith:6U5CPNKZ","schema_version":"1.0","canonical_sha256":"f53a27b559388d8f9cb199b989316c6ce9c1ca5b9a4750a00a794283c3322ab5","source":{"kind":"arxiv","id":"2607.06772","version":1},"attestation_state":"computed","paper":{"title":"Efficient Long-Horizon Learning for Learned Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Th\\'erien, Eugene Belilovsky, James Harrison, Xiaolong Huang","submitted_at":"2026-07-07T20:05:22Z","abstract_excerpt":"Learned optimization aims to improve upon hand-designed optimizers (e.g., Adam and Muon) by meta-learning small neural network optimizers over a distribution of tasks. While recent work has greatly advanced the architectural design and inductive biases of learned optimizers (LOs), current meta-training approaches still suffer from two main difficulties: (1) they cannot efficiently scale meta-training to long-horizon inner problems and (2) they often fail to surpass comparable hand-designed optimizers. To address these limitations, we propose Efficient Long-hOrizon (ELO) learning, an efficient "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.06772","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T20:05:22Z","cross_cats_sorted":[],"title_canon_sha256":"b55060c545c0e04f6c5545daeead3dd00bfc4dfec88d0f1841c510c1ce3015de","abstract_canon_sha256":"204eb5b878e0023fb3ae705f716e423fcdc1d8bda02af161dd16432a9f1d39c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:26.088016Z","signature_b64":"vmyIIXUbwrKc8VUbkdUB9jaQxnZmdLp14LCA68aU0d2zszz6Pz3/lrc9ZLSSGmDOHFAGpXbatQaFN7q+Un15Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f53a27b559388d8f9cb199b989316c6ce9c1ca5b9a4750a00a794283c3322ab5","last_reissued_at":"2026-07-09T00:19:26.087546Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:26.087546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Long-Horizon Learning for Learned Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Th\\'erien, Eugene Belilovsky, James Harrison, Xiaolong Huang","submitted_at":"2026-07-07T20:05:22Z","abstract_excerpt":"Learned optimization aims to improve upon hand-designed optimizers (e.g., Adam and Muon) by meta-learning small neural network optimizers over a distribution of tasks. While recent work has greatly advanced the architectural design and inductive biases of learned optimizers (LOs), current meta-training approaches still suffer from two main difficulties: (1) they cannot efficiently scale meta-training to long-horizon inner problems and (2) they often fail to surpass comparable hand-designed optimizers. To address these limitations, we propose Efficient Long-hOrizon (ELO) learning, an efficient "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06772","kind":"arxiv","version":1},"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/2607.06772/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.06772","created_at":"2026-07-09T00:19:26.087614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06772v1","created_at":"2026-07-09T00:19:26.087614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06772","created_at":"2026-07-09T00:19:26.087614+00:00"},{"alias_kind":"pith_short_12","alias_value":"6U5CPNKZHCGY","created_at":"2026-07-09T00:19:26.087614+00:00"},{"alias_kind":"pith_short_16","alias_value":"6U5CPNKZHCGY7HFR","created_at":"2026-07-09T00:19:26.087614+00:00"},{"alias_kind":"pith_short_8","alias_value":"6U5CPNKZ","created_at":"2026-07-09T00:19:26.087614+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6U5CPNKZHCGY7HFRTG4YSMLMNT","json":"https://pith.science/pith/6U5CPNKZHCGY7HFRTG4YSMLMNT.json","graph_json":"https://pith.science/api/pith-number/6U5CPNKZHCGY7HFRTG4YSMLMNT/graph.json","events_json":"https://pith.science/api/pith-number/6U5CPNKZHCGY7HFRTG4YSMLMNT/events.json","paper":"https://pith.science/paper/6U5CPNKZ"},"agent_actions":{"view_html":"https://pith.science/pith/6U5CPNKZHCGY7HFRTG4YSMLMNT","download_json":"https://pith.science/pith/6U5CPNKZHCGY7HFRTG4YSMLMNT.json","view_paper":"https://pith.science/paper/6U5CPNKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06772&json=true","fetch_graph":"https://pith.science/api/pith-number/6U5CPNKZHCGY7HFRTG4YSMLMNT/graph.json","fetch_events":"https://pith.science/api/pith-number/6U5CPNKZHCGY7HFRTG4YSMLMNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6U5CPNKZHCGY7HFRTG4YSMLMNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6U5CPNKZHCGY7HFRTG4YSMLMNT/action/storage_attestation","attest_author":"https://pith.science/pith/6U5CPNKZHCGY7HFRTG4YSMLMNT/action/author_attestation","sign_citation":"https://pith.science/pith/6U5CPNKZHCGY7HFRTG4YSMLMNT/action/citation_signature","submit_replication":"https://pith.science/pith/6U5CPNKZHCGY7HFRTG4YSMLMNT/action/replication_record"}},"created_at":"2026-07-09T00:19:26.087614+00:00","updated_at":"2026-07-09T00:19:26.087614+00:00"}