{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IP3JOISHXNA2OW6JV7GADPC4QC","short_pith_number":"pith:IP3JOISH","schema_version":"1.0","canonical_sha256":"43f6972247bb41a75bc9afcc01bc5c80ae911205df770a1936119c32f69201d2","source":{"kind":"arxiv","id":"2203.06578","version":4},"attestation_state":"computed","paper":{"title":"Symbolic Learning to Optimize: Towards Interpretability and Scalability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Tianlong Chen, Ting-Kuei Hu, Wenqing Zheng, Zhangyang Wang","submitted_at":"2022-03-13T06:04:25Z","abstract_excerpt":"Recent studies on Learning to Optimize (L2O) suggest a promising path to automating and accelerating the optimization procedure for complicated tasks. Existing L2O models parameterize optimization rules by neural networks, and learn those numerical rules via meta-training. However, they face two common pitfalls: (1) scalability: the numerical rules represented by neural networks create extra memory overhead for applying L2O models, and limit their applicability to optimizing larger tasks; (2) interpretability: it is unclear what an L2O model has learned in its black-box optimization rule, nor "},"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":"2203.06578","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-13T06:04:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff08c978fe280b7dadb5de8017aaada30ba5ad89e21eef1c08a7a8be58b87d00","abstract_canon_sha256":"433d3a88d85e3e3c5d1367f0ab717803029a0ea1d9954c353c72f9f03e51e9e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:11.031556Z","signature_b64":"mDbyJaFmFdb7NlmFGZUTYITJF/E1lfE5XUJxztf7EHYE7NxFbzQoCH6GI+c2ltHGlpMgvj8dfu9G3dL/ncWyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43f6972247bb41a75bc9afcc01bc5c80ae911205df770a1936119c32f69201d2","last_reissued_at":"2026-07-05T04:21:11.031085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:11.031085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbolic Learning to Optimize: Towards Interpretability and Scalability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Tianlong Chen, Ting-Kuei Hu, Wenqing Zheng, Zhangyang Wang","submitted_at":"2022-03-13T06:04:25Z","abstract_excerpt":"Recent studies on Learning to Optimize (L2O) suggest a promising path to automating and accelerating the optimization procedure for complicated tasks. Existing L2O models parameterize optimization rules by neural networks, and learn those numerical rules via meta-training. However, they face two common pitfalls: (1) scalability: the numerical rules represented by neural networks create extra memory overhead for applying L2O models, and limit their applicability to optimizing larger tasks; (2) interpretability: it is unclear what an L2O model has learned in its black-box optimization rule, nor "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06578","kind":"arxiv","version":4},"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/2203.06578/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":"2203.06578","created_at":"2026-07-05T04:21:11.031146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.06578v4","created_at":"2026-07-05T04:21:11.031146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06578","created_at":"2026-07-05T04:21:11.031146+00:00"},{"alias_kind":"pith_short_12","alias_value":"IP3JOISHXNA2","created_at":"2026-07-05T04:21:11.031146+00:00"},{"alias_kind":"pith_short_16","alias_value":"IP3JOISHXNA2OW6J","created_at":"2026-07-05T04:21:11.031146+00:00"},{"alias_kind":"pith_short_8","alias_value":"IP3JOISH","created_at":"2026-07-05T04:21:11.031146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17668","citing_title":"How Should We Meta-Learn Reinforcement Learning Algorithms?","ref_index":84,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IP3JOISHXNA2OW6JV7GADPC4QC","json":"https://pith.science/pith/IP3JOISHXNA2OW6JV7GADPC4QC.json","graph_json":"https://pith.science/api/pith-number/IP3JOISHXNA2OW6JV7GADPC4QC/graph.json","events_json":"https://pith.science/api/pith-number/IP3JOISHXNA2OW6JV7GADPC4QC/events.json","paper":"https://pith.science/paper/IP3JOISH"},"agent_actions":{"view_html":"https://pith.science/pith/IP3JOISHXNA2OW6JV7GADPC4QC","download_json":"https://pith.science/pith/IP3JOISHXNA2OW6JV7GADPC4QC.json","view_paper":"https://pith.science/paper/IP3JOISH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.06578&json=true","fetch_graph":"https://pith.science/api/pith-number/IP3JOISHXNA2OW6JV7GADPC4QC/graph.json","fetch_events":"https://pith.science/api/pith-number/IP3JOISHXNA2OW6JV7GADPC4QC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IP3JOISHXNA2OW6JV7GADPC4QC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IP3JOISHXNA2OW6JV7GADPC4QC/action/storage_attestation","attest_author":"https://pith.science/pith/IP3JOISHXNA2OW6JV7GADPC4QC/action/author_attestation","sign_citation":"https://pith.science/pith/IP3JOISHXNA2OW6JV7GADPC4QC/action/citation_signature","submit_replication":"https://pith.science/pith/IP3JOISHXNA2OW6JV7GADPC4QC/action/replication_record"}},"created_at":"2026-07-05T04:21:11.031146+00:00","updated_at":"2026-07-05T04:21:11.031146+00:00"}