{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:H2TVVBESTCQ7AJRY3SMAMA2GOH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"477256adff5adc042564bf1abbfeaf3557babd0748840271af11b3086f15d604","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-04T03:21:05Z","title_canon_sha256":"96877e3d4916be0055fe53264a8f2f1f9edfac1d2afe08f9afe342a3dec71363"},"schema_version":"1.0","source":{"id":"2005.01246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.01246","created_at":"2026-07-05T01:00:05Z"},{"alias_kind":"arxiv_version","alias_value":"2005.01246v1","created_at":"2026-07-05T01:00:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01246","created_at":"2026-07-05T01:00:05Z"},{"alias_kind":"pith_short_12","alias_value":"H2TVVBESTCQ7","created_at":"2026-07-05T01:00:05Z"},{"alias_kind":"pith_short_16","alias_value":"H2TVVBESTCQ7AJRY","created_at":"2026-07-05T01:00:05Z"},{"alias_kind":"pith_short_8","alias_value":"H2TVVBES","created_at":"2026-07-05T01:00:05Z"}],"graph_snapshots":[{"event_id":"sha256:39f68ca44998e97e595b27ed6be76911633f41bda13172bebec61a49bf534b1a","target":"graph","created_at":"2026-07-05T01:00:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2005.01246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a generic and flexible Reinforcement Learning (RL) based meta-learning framework for the problem of few-shot learning. During training, it learns the best optimization algorithm to produce a learner (ranker/classifier, etc) by exploiting stable patterns in loss surfaces. Our method implicitly estimates the gradients of a scaled loss function while retaining the general properties intact for parameter updates. Besides providing improved performance on few-shot tasks, our framework could be easily extended to do network architecture search. We further propose a novel dual encoder, aff","authors_text":"Raviteja Anantha, Srinivas Chappidi, Stephen Pulman","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-04T03:21:05Z","title":"Generalized Reinforcement Meta Learning for Few-Shot Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01246","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0abceb6b47dd7da0af38140286fc43ee26dfd7c9b72df3529b94be2b9bb7b618","target":"record","created_at":"2026-07-05T01:00:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"477256adff5adc042564bf1abbfeaf3557babd0748840271af11b3086f15d604","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-04T03:21:05Z","title_canon_sha256":"96877e3d4916be0055fe53264a8f2f1f9edfac1d2afe08f9afe342a3dec71363"},"schema_version":"1.0","source":{"id":"2005.01246","kind":"arxiv","version":1}},"canonical_sha256":"3ea75a849298a1f02638dc9806034671d09d1b63991ff2416f4365487736d6a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ea75a849298a1f02638dc9806034671d09d1b63991ff2416f4365487736d6a7","first_computed_at":"2026-07-05T01:00:05.932820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:05.932820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aZen+1wjRL9DPJEp6s3sVu7/bkUej86l9keN89eFmQ9kcleN9ERGyDt8k7aZ3ou1MJ3IlB3in6dE0ZSYlmUmAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:05.933159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.01246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0abceb6b47dd7da0af38140286fc43ee26dfd7c9b72df3529b94be2b9bb7b618","sha256:39f68ca44998e97e595b27ed6be76911633f41bda13172bebec61a49bf534b1a"],"state_sha256":"88cb901f2d093c7aff58a1d428043419f15ae0350dc9dc06340c38fe88044e39"}