{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:H2TVVBESTCQ7AJRY3SMAMA2GOH","short_pith_number":"pith:H2TVVBES","schema_version":"1.0","canonical_sha256":"3ea75a849298a1f02638dc9806034671d09d1b63991ff2416f4365487736d6a7","source":{"kind":"arxiv","id":"2005.01246","version":1},"attestation_state":"computed","paper":{"title":"Generalized Reinforcement Meta Learning for Few-Shot Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Raviteja Anantha, Srinivas Chappidi, Stephen Pulman","submitted_at":"2020-05-04T03:21:05Z","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"},"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":"2005.01246","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-04T03:21:05Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"96877e3d4916be0055fe53264a8f2f1f9edfac1d2afe08f9afe342a3dec71363","abstract_canon_sha256":"477256adff5adc042564bf1abbfeaf3557babd0748840271af11b3086f15d604"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:05.933159Z","signature_b64":"aZen+1wjRL9DPJEp6s3sVu7/bkUej86l9keN89eFmQ9kcleN9ERGyDt8k7aZ3ou1MJ3IlB3in6dE0ZSYlmUmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ea75a849298a1f02638dc9806034671d09d1b63991ff2416f4365487736d6a7","last_reissued_at":"2026-07-05T01:00:05.932820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:05.932820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Reinforcement Meta Learning for Few-Shot Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Raviteja Anantha, Srinivas Chappidi, Stephen Pulman","submitted_at":"2020-05-04T03:21:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01246","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/2005.01246/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":"2005.01246","created_at":"2026-07-05T01:00:05.932880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.01246v1","created_at":"2026-07-05T01:00:05.932880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01246","created_at":"2026-07-05T01:00:05.932880+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2TVVBESTCQ7","created_at":"2026-07-05T01:00:05.932880+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2TVVBESTCQ7AJRY","created_at":"2026-07-05T01:00:05.932880+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2TVVBES","created_at":"2026-07-05T01:00:05.932880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2TVVBESTCQ7AJRY3SMAMA2GOH","json":"https://pith.science/pith/H2TVVBESTCQ7AJRY3SMAMA2GOH.json","graph_json":"https://pith.science/api/pith-number/H2TVVBESTCQ7AJRY3SMAMA2GOH/graph.json","events_json":"https://pith.science/api/pith-number/H2TVVBESTCQ7AJRY3SMAMA2GOH/events.json","paper":"https://pith.science/paper/H2TVVBES"},"agent_actions":{"view_html":"https://pith.science/pith/H2TVVBESTCQ7AJRY3SMAMA2GOH","download_json":"https://pith.science/pith/H2TVVBESTCQ7AJRY3SMAMA2GOH.json","view_paper":"https://pith.science/paper/H2TVVBES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.01246&json=true","fetch_graph":"https://pith.science/api/pith-number/H2TVVBESTCQ7AJRY3SMAMA2GOH/graph.json","fetch_events":"https://pith.science/api/pith-number/H2TVVBESTCQ7AJRY3SMAMA2GOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2TVVBESTCQ7AJRY3SMAMA2GOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2TVVBESTCQ7AJRY3SMAMA2GOH/action/storage_attestation","attest_author":"https://pith.science/pith/H2TVVBESTCQ7AJRY3SMAMA2GOH/action/author_attestation","sign_citation":"https://pith.science/pith/H2TVVBESTCQ7AJRY3SMAMA2GOH/action/citation_signature","submit_replication":"https://pith.science/pith/H2TVVBESTCQ7AJRY3SMAMA2GOH/action/replication_record"}},"created_at":"2026-07-05T01:00:05.932880+00:00","updated_at":"2026-07-05T01:00:05.932880+00:00"}