{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:B6TVBRW5S32I3ZSTNG77DU3ENY","short_pith_number":"pith:B6TVBRW5","schema_version":"1.0","canonical_sha256":"0fa750c6dd96f48de65369bff1d3646e139d78970b7e361aef448fd039e07eaa","source":{"kind":"arxiv","id":"1909.04630","version":1},"attestation_state":"computed","paper":{"title":"Meta-Learning with Implicit Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aravind Rajeswaran, Chelsea Finn, Sergey Levine, Sham Kakade","submitted_at":"2019-09-10T17:14:14Z","abstract_excerpt":"A core capability of intelligent systems is the ability to quickly learn new tasks by drawing on prior experience. Gradient (or optimization) based meta-learning has recently emerged as an effective approach for few-shot learning. In this formulation, meta-parameters are learned in the outer loop, while task-specific models are learned in the inner-loop, by using only a small amount of data from the current task. A key challenge in scaling these approaches is the need to differentiate through the inner loop learning process, which can impose considerable computational and memory burdens. By dr"},"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":"1909.04630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-10T17:14:14Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"053c0c136e86af9b97171b80442235108c7049c0d9ad05356f1fec5935698389","abstract_canon_sha256":"9e581f1f8aaf55846ed231f08f001b48e1949c936921e04d0b2ad7145faa2f67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:23.898323Z","signature_b64":"uiPyYx9SIXbjVZTybaYxZl723p5Mr1OUvppDLY5meSP3Uh1v702bJKvvQGEVmMFR/IUHKWVaTYB8FSv0lBQ3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fa750c6dd96f48de65369bff1d3646e139d78970b7e361aef448fd039e07eaa","last_reissued_at":"2026-07-05T00:03:23.897854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:23.897854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning with Implicit Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aravind Rajeswaran, Chelsea Finn, Sergey Levine, Sham Kakade","submitted_at":"2019-09-10T17:14:14Z","abstract_excerpt":"A core capability of intelligent systems is the ability to quickly learn new tasks by drawing on prior experience. Gradient (or optimization) based meta-learning has recently emerged as an effective approach for few-shot learning. In this formulation, meta-parameters are learned in the outer loop, while task-specific models are learned in the inner-loop, by using only a small amount of data from the current task. A key challenge in scaling these approaches is the need to differentiate through the inner loop learning process, which can impose considerable computational and memory burdens. By dr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04630","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/1909.04630/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":"1909.04630","created_at":"2026-07-05T00:03:23.897912+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.04630v1","created_at":"2026-07-05T00:03:23.897912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04630","created_at":"2026-07-05T00:03:23.897912+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6TVBRW5S32I","created_at":"2026-07-05T00:03:23.897912+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6TVBRW5S32I3ZST","created_at":"2026-07-05T00:03:23.897912+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6TVBRW5","created_at":"2026-07-05T00:03:23.897912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13130","citing_title":"Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updates","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6TVBRW5S32I3ZSTNG77DU3ENY","json":"https://pith.science/pith/B6TVBRW5S32I3ZSTNG77DU3ENY.json","graph_json":"https://pith.science/api/pith-number/B6TVBRW5S32I3ZSTNG77DU3ENY/graph.json","events_json":"https://pith.science/api/pith-number/B6TVBRW5S32I3ZSTNG77DU3ENY/events.json","paper":"https://pith.science/paper/B6TVBRW5"},"agent_actions":{"view_html":"https://pith.science/pith/B6TVBRW5S32I3ZSTNG77DU3ENY","download_json":"https://pith.science/pith/B6TVBRW5S32I3ZSTNG77DU3ENY.json","view_paper":"https://pith.science/paper/B6TVBRW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.04630&json=true","fetch_graph":"https://pith.science/api/pith-number/B6TVBRW5S32I3ZSTNG77DU3ENY/graph.json","fetch_events":"https://pith.science/api/pith-number/B6TVBRW5S32I3ZSTNG77DU3ENY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6TVBRW5S32I3ZSTNG77DU3ENY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6TVBRW5S32I3ZSTNG77DU3ENY/action/storage_attestation","attest_author":"https://pith.science/pith/B6TVBRW5S32I3ZSTNG77DU3ENY/action/author_attestation","sign_citation":"https://pith.science/pith/B6TVBRW5S32I3ZSTNG77DU3ENY/action/citation_signature","submit_replication":"https://pith.science/pith/B6TVBRW5S32I3ZSTNG77DU3ENY/action/replication_record"}},"created_at":"2026-07-05T00:03:23.897912+00:00","updated_at":"2026-07-05T00:03:23.897912+00:00"}