{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4JPRIXUKIZMGDD524RPAYMRADL","short_pith_number":"pith:4JPRIXUK","schema_version":"1.0","canonical_sha256":"e25f145e8a4658618fbae45e0c32201ac07c704c4df0f1b2304077b9bc300346","source":{"kind":"arxiv","id":"2501.17431","version":1},"attestation_state":"computed","paper":{"title":"Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Maxence Hussonnois, Santu Rana, Thommen George Karimpanal","submitted_at":"2025-01-29T06:14:27Z","abstract_excerpt":"Unsupervised skill discovery in Reinforcement Learning aims to mimic humans' ability to autonomously discover diverse behaviors. However, existing methods are often unconstrained, making it difficult to find useful skills, especially in complex environments, where discovered skills are frequently unsafe or impractical. We address this issue by proposing Human-aligned Skill Discovery (HaSD), a framework that incorporates human feedback to discover safer, more aligned skills. HaSD simultaneously optimises skill diversity and alignment with human values. This approach ensures that alignment is ma"},"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":"2501.17431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T06:14:27Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"519906fc1445131bbf0c39e3763e1391135aba0b70b1cbd74f6cfe848c06e9e3","abstract_canon_sha256":"76d904690d0daa95fe174cf8ba6cb05e4b9f2bf03506a3bd59171283c9df1c77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:52.749702Z","signature_b64":"UH14OmWJgn7jjVGaDy+k9gmOuj4LS7/nWEjK8+LQt8tjbV0mwsfV35z7Zg2yNgrVZt3ST3cuwQTbvhNiTq5oAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e25f145e8a4658618fbae45e0c32201ac07c704c4df0f1b2304077b9bc300346","last_reissued_at":"2026-07-05T10:06:52.749274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:52.749274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Maxence Hussonnois, Santu Rana, Thommen George Karimpanal","submitted_at":"2025-01-29T06:14:27Z","abstract_excerpt":"Unsupervised skill discovery in Reinforcement Learning aims to mimic humans' ability to autonomously discover diverse behaviors. However, existing methods are often unconstrained, making it difficult to find useful skills, especially in complex environments, where discovered skills are frequently unsafe or impractical. We address this issue by proposing Human-aligned Skill Discovery (HaSD), a framework that incorporates human feedback to discover safer, more aligned skills. HaSD simultaneously optimises skill diversity and alignment with human values. This approach ensures that alignment is ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17431","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/2501.17431/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":"2501.17431","created_at":"2026-07-05T10:06:52.749329+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.17431v1","created_at":"2026-07-05T10:06:52.749329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17431","created_at":"2026-07-05T10:06:52.749329+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JPRIXUKIZMG","created_at":"2026-07-05T10:06:52.749329+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JPRIXUKIZMGDD52","created_at":"2026-07-05T10:06:52.749329+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JPRIXUK","created_at":"2026-07-05T10:06:52.749329+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.29559","citing_title":"LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JPRIXUKIZMGDD524RPAYMRADL","json":"https://pith.science/pith/4JPRIXUKIZMGDD524RPAYMRADL.json","graph_json":"https://pith.science/api/pith-number/4JPRIXUKIZMGDD524RPAYMRADL/graph.json","events_json":"https://pith.science/api/pith-number/4JPRIXUKIZMGDD524RPAYMRADL/events.json","paper":"https://pith.science/paper/4JPRIXUK"},"agent_actions":{"view_html":"https://pith.science/pith/4JPRIXUKIZMGDD524RPAYMRADL","download_json":"https://pith.science/pith/4JPRIXUKIZMGDD524RPAYMRADL.json","view_paper":"https://pith.science/paper/4JPRIXUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.17431&json=true","fetch_graph":"https://pith.science/api/pith-number/4JPRIXUKIZMGDD524RPAYMRADL/graph.json","fetch_events":"https://pith.science/api/pith-number/4JPRIXUKIZMGDD524RPAYMRADL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JPRIXUKIZMGDD524RPAYMRADL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JPRIXUKIZMGDD524RPAYMRADL/action/storage_attestation","attest_author":"https://pith.science/pith/4JPRIXUKIZMGDD524RPAYMRADL/action/author_attestation","sign_citation":"https://pith.science/pith/4JPRIXUKIZMGDD524RPAYMRADL/action/citation_signature","submit_replication":"https://pith.science/pith/4JPRIXUKIZMGDD524RPAYMRADL/action/replication_record"}},"created_at":"2026-07-05T10:06:52.749329+00:00","updated_at":"2026-07-05T10:06:52.749329+00:00"}