{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SQBGSVP3M2YBMM2UY37MEASUEX","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":"7e36fa0b20ee027c48120369f2c95a5feabaecc117cd1bb12740aabb54b4f631","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T03:28:45Z","title_canon_sha256":"89aca2c0236f845d56ab8aea198d1fa2bf2f9fa2b55216dff17a3daecaee28dc"},"schema_version":"1.0","source":{"id":"2502.03752","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03752","created_at":"2026-05-21T01:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03752v5","created_at":"2026-05-21T01:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03752","created_at":"2026-05-21T01:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"SQBGSVP3M2YB","created_at":"2026-05-21T01:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"SQBGSVP3M2YBMM2U","created_at":"2026-05-21T01:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"SQBGSVP3","created_at":"2026-05-21T01:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:c3275e612f96377272bfd1e109311aa0e32330a0629283df7e974c36ace2e003","target":"graph","created_at":"2026-05-21T01:04:12Z","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/2502.03752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta-reinforcement learning (Meta-RL) facilitates rapid adaptation to unseen tasks but faces challenges in long-horizon environments. Skill-based approaches tackle this by decomposing state-action sequences into reusable skills and employing hierarchical decision-making. However, these methods are highly susceptible to noisy offline demonstrations, leading to unstable skill learning and degraded performance. To address this, we propose Self-Improving Skill Learning (SISL), which performs self-guided skill refinement using decoupled high-level and skill improvement policies, while applying skil","authors_text":"Sanghyeon Lee, Sangjun Bae, Seungyul Han, Yisak Park","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T03:28:45Z","title":"Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03752","kind":"arxiv","version":5},"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:c6f01829339546e60e5b74fefef67036f953ac45ed3b1be383ec0d5c9f2294d5","target":"record","created_at":"2026-05-21T01:04:12Z","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":"7e36fa0b20ee027c48120369f2c95a5feabaecc117cd1bb12740aabb54b4f631","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T03:28:45Z","title_canon_sha256":"89aca2c0236f845d56ab8aea198d1fa2bf2f9fa2b55216dff17a3daecaee28dc"},"schema_version":"1.0","source":{"id":"2502.03752","kind":"arxiv","version":5}},"canonical_sha256":"94026955fb66b0163354c6fec2025425eefecb04d35712d6b38631ad13191a6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94026955fb66b0163354c6fec2025425eefecb04d35712d6b38631ad13191a6b","first_computed_at":"2026-05-21T01:04:12.853885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:12.853885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c+DrktXJjdVr7fCKFcxc5OH1IyWcGys1BTOeN8CaJEHAciCaD244C7A68zALE9chyFBGMYacABF3ql6KCkKlCg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:12.854712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03752","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6f01829339546e60e5b74fefef67036f953ac45ed3b1be383ec0d5c9f2294d5","sha256:c3275e612f96377272bfd1e109311aa0e32330a0629283df7e974c36ace2e003"],"state_sha256":"cb14ec20b743b75749a80793e2f389a8658c8861265f23393b91536922bfdd9a"}