{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WASPV3B63HWULXBV23O6SOM7CB","short_pith_number":"pith:WASPV3B6","schema_version":"1.0","canonical_sha256":"b024faec3ed9ed45dc35d6dde9399f106ece46e1318dbfc0add7326039027bd8","source":{"kind":"arxiv","id":"2506.04399","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Meta-Testing with Conditional Neural Processes for Hybrid Meta-Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Emre Ugur, Suzan Ece Ada","submitted_at":"2025-06-04T19:27:47Z","abstract_excerpt":"We introduce Unsupervised Meta-Testing with Conditional Neural Processes (UMCNP), a novel hybrid few-shot meta-reinforcement learning (meta-RL) method that uniquely combines, yet distinctly separates, parameterized policy gradient-based (PPG) and task inference-based few-shot meta-RL. Tailored for settings where the reward signal is missing during meta-testing, our method increases sample efficiency without requiring additional samples in meta-training. UMCNP leverages the efficiency and scalability of Conditional Neural Processes (CNPs) to reduce the number of online interactions required in "},"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":"2506.04399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T19:27:47Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"99ecdfcc722880b5f6b8e7cd539b774c35d5e8338383d69598a07c712ff2280a","abstract_canon_sha256":"b33f5e4f9b58cbe470499961ad0d9d25fd4707bc6e80b593599f9b25e5b18208"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:13.802847Z","signature_b64":"AQgiyPSFKlOtg++e+jdbKZM/Ki6hi8E3Q3IuvuTwnE45LvEKFXW0p0Y6qhL+h3DohYyt801eiBugy38gICGjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b024faec3ed9ed45dc35d6dde9399f106ece46e1318dbfc0add7326039027bd8","last_reissued_at":"2026-07-05T11:16:13.802276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:13.802276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Meta-Testing with Conditional Neural Processes for Hybrid Meta-Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Emre Ugur, Suzan Ece Ada","submitted_at":"2025-06-04T19:27:47Z","abstract_excerpt":"We introduce Unsupervised Meta-Testing with Conditional Neural Processes (UMCNP), a novel hybrid few-shot meta-reinforcement learning (meta-RL) method that uniquely combines, yet distinctly separates, parameterized policy gradient-based (PPG) and task inference-based few-shot meta-RL. Tailored for settings where the reward signal is missing during meta-testing, our method increases sample efficiency without requiring additional samples in meta-training. UMCNP leverages the efficiency and scalability of Conditional Neural Processes (CNPs) to reduce the number of online interactions required in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04399","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/2506.04399/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":"2506.04399","created_at":"2026-07-05T11:16:13.802344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04399v1","created_at":"2026-07-05T11:16:13.802344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04399","created_at":"2026-07-05T11:16:13.802344+00:00"},{"alias_kind":"pith_short_12","alias_value":"WASPV3B63HWU","created_at":"2026-07-05T11:16:13.802344+00:00"},{"alias_kind":"pith_short_16","alias_value":"WASPV3B63HWULXBV","created_at":"2026-07-05T11:16:13.802344+00:00"},{"alias_kind":"pith_short_8","alias_value":"WASPV3B6","created_at":"2026-07-05T11:16:13.802344+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/WASPV3B63HWULXBV23O6SOM7CB","json":"https://pith.science/pith/WASPV3B63HWULXBV23O6SOM7CB.json","graph_json":"https://pith.science/api/pith-number/WASPV3B63HWULXBV23O6SOM7CB/graph.json","events_json":"https://pith.science/api/pith-number/WASPV3B63HWULXBV23O6SOM7CB/events.json","paper":"https://pith.science/paper/WASPV3B6"},"agent_actions":{"view_html":"https://pith.science/pith/WASPV3B63HWULXBV23O6SOM7CB","download_json":"https://pith.science/pith/WASPV3B63HWULXBV23O6SOM7CB.json","view_paper":"https://pith.science/paper/WASPV3B6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04399&json=true","fetch_graph":"https://pith.science/api/pith-number/WASPV3B63HWULXBV23O6SOM7CB/graph.json","fetch_events":"https://pith.science/api/pith-number/WASPV3B63HWULXBV23O6SOM7CB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WASPV3B63HWULXBV23O6SOM7CB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WASPV3B63HWULXBV23O6SOM7CB/action/storage_attestation","attest_author":"https://pith.science/pith/WASPV3B63HWULXBV23O6SOM7CB/action/author_attestation","sign_citation":"https://pith.science/pith/WASPV3B63HWULXBV23O6SOM7CB/action/citation_signature","submit_replication":"https://pith.science/pith/WASPV3B63HWULXBV23O6SOM7CB/action/replication_record"}},"created_at":"2026-07-05T11:16:13.802344+00:00","updated_at":"2026-07-05T11:16:13.802344+00:00"}