{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I7LQWTIKOAINJ32D57SK3NELV3","short_pith_number":"pith:I7LQWTIK","schema_version":"1.0","canonical_sha256":"47d70b4d0a7010d4ef43efe4adb48baed0fa7f7ab1000eb7bf0768c93899216d","source":{"kind":"arxiv","id":"2606.18132","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Reutilization in Meta-Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alois Knoll, Bo Wang, Fuchun Sun, Juan de los Rios Ruiz, Xiangtong Yao, Yuan Meng, Zhenshan Bing","submitted_at":"2026-06-16T16:32:28Z","abstract_excerpt":"Meta-reinforcement learning enables fast adaptation by extracting shared structure from related tasks, but existing end-to-end methods often couple task inference with embodiment-specific control. This coupling can obscure non-parametric task semantics, reduce sample efficiency, and limit cross-agent reuse. We propose a meta-knowledge reutilization framework that learns task-level knowledge on a dynamics-simplified agent and transfers it to heterogeneous agents. The framework uses a Bayesian non-parametric prior to organize latent task modes and a high-level policy to generate task-level magni"},"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":"2606.18132","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T16:32:28Z","cross_cats_sorted":[],"title_canon_sha256":"bd4a1f3e9a255c0d6c8d66e1b57ea41d6571cb78cb2632a7d52b5b6add2dfb6d","abstract_canon_sha256":"7e3effe5bced6d67003d8edd9c295725793b935c13ddbc19b3d0e3d1e2d4edc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:49.221408Z","signature_b64":"RvxK6jMZM3UL42NchYn8Eww0ejOHySipaPvCWaYUyWy1IOoDobr5MtBrfIfpK3SArzRn1w9+J9HlycP6p6BDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47d70b4d0a7010d4ef43efe4adb48baed0fa7f7ab1000eb7bf0768c93899216d","last_reissued_at":"2026-06-19T16:10:49.221026Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:49.221026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Reutilization in Meta-Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alois Knoll, Bo Wang, Fuchun Sun, Juan de los Rios Ruiz, Xiangtong Yao, Yuan Meng, Zhenshan Bing","submitted_at":"2026-06-16T16:32:28Z","abstract_excerpt":"Meta-reinforcement learning enables fast adaptation by extracting shared structure from related tasks, but existing end-to-end methods often couple task inference with embodiment-specific control. This coupling can obscure non-parametric task semantics, reduce sample efficiency, and limit cross-agent reuse. We propose a meta-knowledge reutilization framework that learns task-level knowledge on a dynamics-simplified agent and transfers it to heterogeneous agents. The framework uses a Bayesian non-parametric prior to organize latent task modes and a high-level policy to generate task-level magni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18132","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/2606.18132/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":"2606.18132","created_at":"2026-06-19T16:10:49.221095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18132v1","created_at":"2026-06-19T16:10:49.221095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18132","created_at":"2026-06-19T16:10:49.221095+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7LQWTIKOAIN","created_at":"2026-06-19T16:10:49.221095+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7LQWTIKOAINJ32D","created_at":"2026-06-19T16:10:49.221095+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7LQWTIK","created_at":"2026-06-19T16:10:49.221095+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/I7LQWTIKOAINJ32D57SK3NELV3","json":"https://pith.science/pith/I7LQWTIKOAINJ32D57SK3NELV3.json","graph_json":"https://pith.science/api/pith-number/I7LQWTIKOAINJ32D57SK3NELV3/graph.json","events_json":"https://pith.science/api/pith-number/I7LQWTIKOAINJ32D57SK3NELV3/events.json","paper":"https://pith.science/paper/I7LQWTIK"},"agent_actions":{"view_html":"https://pith.science/pith/I7LQWTIKOAINJ32D57SK3NELV3","download_json":"https://pith.science/pith/I7LQWTIKOAINJ32D57SK3NELV3.json","view_paper":"https://pith.science/paper/I7LQWTIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18132&json=true","fetch_graph":"https://pith.science/api/pith-number/I7LQWTIKOAINJ32D57SK3NELV3/graph.json","fetch_events":"https://pith.science/api/pith-number/I7LQWTIKOAINJ32D57SK3NELV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7LQWTIKOAINJ32D57SK3NELV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7LQWTIKOAINJ32D57SK3NELV3/action/storage_attestation","attest_author":"https://pith.science/pith/I7LQWTIKOAINJ32D57SK3NELV3/action/author_attestation","sign_citation":"https://pith.science/pith/I7LQWTIKOAINJ32D57SK3NELV3/action/citation_signature","submit_replication":"https://pith.science/pith/I7LQWTIKOAINJ32D57SK3NELV3/action/replication_record"}},"created_at":"2026-06-19T16:10:49.221095+00:00","updated_at":"2026-06-19T16:10:49.221095+00:00"}