{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UX7OZ4XFF62Y7TY3EY3VTEQUAR","short_pith_number":"pith:UX7OZ4XF","schema_version":"1.0","canonical_sha256":"a5feecf2e52fb58fcf1b26375992140453a4c0aad58968371e9c928b1269c7b8","source":{"kind":"arxiv","id":"2303.00039","version":1},"attestation_state":"computed","paper":{"title":"M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junjie Yang, Tianlong Chen, Xuxi Chen, Yingbin Liang, Zhangyang Wang","submitted_at":"2023-02-28T19:23:20Z","abstract_excerpt":"Learning to Optimize (L2O) has drawn increasing attention as it often remarkably accelerates the optimization procedure of complex tasks by ``overfitting\" specific task type, leading to enhanced performance compared to analytical optimizers. Generally, L2O develops a parameterized optimization method (i.e., ``optimizer\") by learning from solving sample problems. This data-driven procedure yields L2O that can efficiently solve problems similar to those seen in training, that is, drawn from the same ``task distribution\". However, such learned optimizers often struggle when new test problems come"},"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":"2303.00039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-28T19:23:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9d5f9a08f33b473e4582a017e3ff9f8de638f4b9f9dd622c45405406cdbf08a4","abstract_canon_sha256":"3aec55e0c37d4a678cf0fb687972e270faeeb6cec01d3c58715dcdd72f2aa2f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:53.867166Z","signature_b64":"+TWMmB1gxgd798WBYzyHgTUJ7l7dt+9BN8bSpIRuQuxZwti5XLXdkYAaETwIf6gkadsy+2flwqduSa0TbRMmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5feecf2e52fb58fcf1b26375992140453a4c0aad58968371e9c928b1269c7b8","last_reissued_at":"2026-07-05T05:46:53.866777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:53.866777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junjie Yang, Tianlong Chen, Xuxi Chen, Yingbin Liang, Zhangyang Wang","submitted_at":"2023-02-28T19:23:20Z","abstract_excerpt":"Learning to Optimize (L2O) has drawn increasing attention as it often remarkably accelerates the optimization procedure of complex tasks by ``overfitting\" specific task type, leading to enhanced performance compared to analytical optimizers. Generally, L2O develops a parameterized optimization method (i.e., ``optimizer\") by learning from solving sample problems. This data-driven procedure yields L2O that can efficiently solve problems similar to those seen in training, that is, drawn from the same ``task distribution\". However, such learned optimizers often struggle when new test problems come"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00039","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/2303.00039/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":"2303.00039","created_at":"2026-07-05T05:46:53.866834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.00039v1","created_at":"2026-07-05T05:46:53.866834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00039","created_at":"2026-07-05T05:46:53.866834+00:00"},{"alias_kind":"pith_short_12","alias_value":"UX7OZ4XFF62Y","created_at":"2026-07-05T05:46:53.866834+00:00"},{"alias_kind":"pith_short_16","alias_value":"UX7OZ4XFF62Y7TY3","created_at":"2026-07-05T05:46:53.866834+00:00"},{"alias_kind":"pith_short_8","alias_value":"UX7OZ4XF","created_at":"2026-07-05T05:46:53.866834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22509","citing_title":"Accelerating Optimization via Differentiable Stopping Time","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UX7OZ4XFF62Y7TY3EY3VTEQUAR","json":"https://pith.science/pith/UX7OZ4XFF62Y7TY3EY3VTEQUAR.json","graph_json":"https://pith.science/api/pith-number/UX7OZ4XFF62Y7TY3EY3VTEQUAR/graph.json","events_json":"https://pith.science/api/pith-number/UX7OZ4XFF62Y7TY3EY3VTEQUAR/events.json","paper":"https://pith.science/paper/UX7OZ4XF"},"agent_actions":{"view_html":"https://pith.science/pith/UX7OZ4XFF62Y7TY3EY3VTEQUAR","download_json":"https://pith.science/pith/UX7OZ4XFF62Y7TY3EY3VTEQUAR.json","view_paper":"https://pith.science/paper/UX7OZ4XF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.00039&json=true","fetch_graph":"https://pith.science/api/pith-number/UX7OZ4XFF62Y7TY3EY3VTEQUAR/graph.json","fetch_events":"https://pith.science/api/pith-number/UX7OZ4XFF62Y7TY3EY3VTEQUAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UX7OZ4XFF62Y7TY3EY3VTEQUAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UX7OZ4XFF62Y7TY3EY3VTEQUAR/action/storage_attestation","attest_author":"https://pith.science/pith/UX7OZ4XFF62Y7TY3EY3VTEQUAR/action/author_attestation","sign_citation":"https://pith.science/pith/UX7OZ4XFF62Y7TY3EY3VTEQUAR/action/citation_signature","submit_replication":"https://pith.science/pith/UX7OZ4XFF62Y7TY3EY3VTEQUAR/action/replication_record"}},"created_at":"2026-07-05T05:46:53.866834+00:00","updated_at":"2026-07-05T05:46:53.866834+00:00"}