{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YPSGC3UNKAQPSSZV4HIZH5Z7D2","short_pith_number":"pith:YPSGC3UN","schema_version":"1.0","canonical_sha256":"c3e4616e8d5020f94b35e1d193f73f1ebeb45d6d4442521cc00b8041094cf925","source":{"kind":"arxiv","id":"2505.00793","version":2},"attestation_state":"computed","paper":{"title":"Scalable Meta-Learning via Mixed-Mode Differentiation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan A Calian, Gregory Farquhar, Hado van Hasselt, Iurii Kemaev, Luisa M Zintgraf","submitted_at":"2025-05-01T18:46:44Z","abstract_excerpt":"Gradient-based bilevel optimisation is a powerful technique with applications in hyperparameter optimisation, task adaptation, algorithm discovery, meta-learning more broadly, and beyond. It often requires differentiating through the gradient-based optimisation itself, leading to \"gradient-of-a-gradient\" calculations with computationally expensive second-order and mixed derivatives. While modern automatic differentiation libraries provide a convenient way to write programs for calculating these derivatives, they oftentimes cannot fully exploit the specific structure of these problems out-of-th"},"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":"2505.00793","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T18:46:44Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"96bd36ed3fe9d7cbde67e6aa52092a02d7205e7b2ad74f36477b95ae92c9716c","abstract_canon_sha256":"131b84fc05900a7a25531abda69a92951d42429887794f45576a2157c5debb31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:42.748820Z","signature_b64":"6vW9gZV0AIPF7618IJAeg87N4p9WRhKmpx7AnzMUkYxpIl7KuMeIaf4RpolDV+8FmRXqv1zS1TRqzbqaLGx4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3e4616e8d5020f94b35e1d193f73f1ebeb45d6d4442521cc00b8041094cf925","last_reissued_at":"2026-07-05T11:18:42.748351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:42.748351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Meta-Learning via Mixed-Mode Differentiation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan A Calian, Gregory Farquhar, Hado van Hasselt, Iurii Kemaev, Luisa M Zintgraf","submitted_at":"2025-05-01T18:46:44Z","abstract_excerpt":"Gradient-based bilevel optimisation is a powerful technique with applications in hyperparameter optimisation, task adaptation, algorithm discovery, meta-learning more broadly, and beyond. It often requires differentiating through the gradient-based optimisation itself, leading to \"gradient-of-a-gradient\" calculations with computationally expensive second-order and mixed derivatives. While modern automatic differentiation libraries provide a convenient way to write programs for calculating these derivatives, they oftentimes cannot fully exploit the specific structure of these problems out-of-th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00793","kind":"arxiv","version":2},"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/2505.00793/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":"2505.00793","created_at":"2026-07-05T11:18:42.748419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00793v2","created_at":"2026-07-05T11:18:42.748419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00793","created_at":"2026-07-05T11:18:42.748419+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPSGC3UNKAQP","created_at":"2026-07-05T11:18:42.748419+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPSGC3UNKAQPSSZV","created_at":"2026-07-05T11:18:42.748419+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPSGC3UN","created_at":"2026-07-05T11:18:42.748419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08144","citing_title":"NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPSGC3UNKAQPSSZV4HIZH5Z7D2","json":"https://pith.science/pith/YPSGC3UNKAQPSSZV4HIZH5Z7D2.json","graph_json":"https://pith.science/api/pith-number/YPSGC3UNKAQPSSZV4HIZH5Z7D2/graph.json","events_json":"https://pith.science/api/pith-number/YPSGC3UNKAQPSSZV4HIZH5Z7D2/events.json","paper":"https://pith.science/paper/YPSGC3UN"},"agent_actions":{"view_html":"https://pith.science/pith/YPSGC3UNKAQPSSZV4HIZH5Z7D2","download_json":"https://pith.science/pith/YPSGC3UNKAQPSSZV4HIZH5Z7D2.json","view_paper":"https://pith.science/paper/YPSGC3UN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00793&json=true","fetch_graph":"https://pith.science/api/pith-number/YPSGC3UNKAQPSSZV4HIZH5Z7D2/graph.json","fetch_events":"https://pith.science/api/pith-number/YPSGC3UNKAQPSSZV4HIZH5Z7D2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPSGC3UNKAQPSSZV4HIZH5Z7D2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPSGC3UNKAQPSSZV4HIZH5Z7D2/action/storage_attestation","attest_author":"https://pith.science/pith/YPSGC3UNKAQPSSZV4HIZH5Z7D2/action/author_attestation","sign_citation":"https://pith.science/pith/YPSGC3UNKAQPSSZV4HIZH5Z7D2/action/citation_signature","submit_replication":"https://pith.science/pith/YPSGC3UNKAQPSSZV4HIZH5Z7D2/action/replication_record"}},"created_at":"2026-07-05T11:18:42.748419+00:00","updated_at":"2026-07-05T11:18:42.748419+00:00"}