{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5ZH3KKVJOX5R54F5FZKFSGYRQV","short_pith_number":"pith:5ZH3KKVJ","schema_version":"1.0","canonical_sha256":"ee4fb52aa975fb1ef0bd2e54591b118570e9bf94e86a971688fd2b735c00f481","source":{"kind":"arxiv","id":"2403.00225","version":3},"attestation_state":"computed","paper":{"title":"Robust Policy Learning via Offline Skill Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Honguk Woo, Minjong Yoo, Woo Kyung Kim","submitted_at":"2024-03-01T02:00:44Z","abstract_excerpt":"Skill-based reinforcement learning (RL) approaches have shown considerable promise, especially in solving long-horizon tasks via hierarchical structures. These skills, learned task-agnostically from offline datasets, can accelerate the policy learning process for new tasks. Yet, the application of these skills in different domains remains restricted due to their inherent dependency on the datasets, which poses a challenge when attempting to learn a skill-based policy via RL for a target domain different from the datasets' domains. In this paper, we present a novel offline skill learning framew"},"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":"2403.00225","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-01T02:00:44Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"814cdd7cc2add4bba878a89af9df4819201d609148987f3652eff701d6904077","abstract_canon_sha256":"b795d23814708e2a19cd9d24b647d27ed5ecc5b4e6ae4155db694f19cc7483a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:55.137723Z","signature_b64":"vCXkfXQpk5X+ZJ2xa5VgiZayDikQjvA4pNG/veI4H3C6v7rBB2LGxHqajirF8DLjmJmQgWYvQ3ZHkNfWbbYWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee4fb52aa975fb1ef0bd2e54591b118570e9bf94e86a971688fd2b735c00f481","last_reissued_at":"2026-07-05T08:57:55.137217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:55.137217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Policy Learning via Offline Skill Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Honguk Woo, Minjong Yoo, Woo Kyung Kim","submitted_at":"2024-03-01T02:00:44Z","abstract_excerpt":"Skill-based reinforcement learning (RL) approaches have shown considerable promise, especially in solving long-horizon tasks via hierarchical structures. These skills, learned task-agnostically from offline datasets, can accelerate the policy learning process for new tasks. Yet, the application of these skills in different domains remains restricted due to their inherent dependency on the datasets, which poses a challenge when attempting to learn a skill-based policy via RL for a target domain different from the datasets' domains. In this paper, we present a novel offline skill learning framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00225","kind":"arxiv","version":3},"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/2403.00225/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":"2403.00225","created_at":"2026-07-05T08:57:55.137274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00225v3","created_at":"2026-07-05T08:57:55.137274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00225","created_at":"2026-07-05T08:57:55.137274+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZH3KKVJOX5R","created_at":"2026-07-05T08:57:55.137274+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZH3KKVJOX5R54F5","created_at":"2026-07-05T08:57:55.137274+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZH3KKVJ","created_at":"2026-07-05T08:57:55.137274+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/5ZH3KKVJOX5R54F5FZKFSGYRQV","json":"https://pith.science/pith/5ZH3KKVJOX5R54F5FZKFSGYRQV.json","graph_json":"https://pith.science/api/pith-number/5ZH3KKVJOX5R54F5FZKFSGYRQV/graph.json","events_json":"https://pith.science/api/pith-number/5ZH3KKVJOX5R54F5FZKFSGYRQV/events.json","paper":"https://pith.science/paper/5ZH3KKVJ"},"agent_actions":{"view_html":"https://pith.science/pith/5ZH3KKVJOX5R54F5FZKFSGYRQV","download_json":"https://pith.science/pith/5ZH3KKVJOX5R54F5FZKFSGYRQV.json","view_paper":"https://pith.science/paper/5ZH3KKVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00225&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZH3KKVJOX5R54F5FZKFSGYRQV/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZH3KKVJOX5R54F5FZKFSGYRQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZH3KKVJOX5R54F5FZKFSGYRQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZH3KKVJOX5R54F5FZKFSGYRQV/action/storage_attestation","attest_author":"https://pith.science/pith/5ZH3KKVJOX5R54F5FZKFSGYRQV/action/author_attestation","sign_citation":"https://pith.science/pith/5ZH3KKVJOX5R54F5FZKFSGYRQV/action/citation_signature","submit_replication":"https://pith.science/pith/5ZH3KKVJOX5R54F5FZKFSGYRQV/action/replication_record"}},"created_at":"2026-07-05T08:57:55.137274+00:00","updated_at":"2026-07-05T08:57:55.137274+00:00"}