{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AHO6XK3E3GCRNT4FDWWEZMBABX","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":"103dc1d10b296c52c91411a5ce42147e9286ec3f002baf277bb19937d2c998e0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T11:30:04Z","title_canon_sha256":"bce8ad4637e4b6414221c5255e5ca9d7289a196fba69bac84ea68b4b4481dcfa"},"schema_version":"1.0","source":{"id":"2506.14420","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14420","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14420v1","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14420","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_12","alias_value":"AHO6XK3E3GCR","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_16","alias_value":"AHO6XK3E3GCRNT4F","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_8","alias_value":"AHO6XK3E","created_at":"2026-07-05T11:22:56Z"}],"graph_snapshots":[{"event_id":"sha256:1b569c1b2b95de33b6658473b53fd9be5012005a43b63b0c7762897d1af9e0ac","target":"graph","created_at":"2026-07-05T11:22:56Z","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/2506.14420/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However, entropy-based exploration struggles in large-scale state spaces (e.g., images), and empowerment-based methods with Mutual Information (MI) estimations have limitations in state exploration. To address these challenges, we propose a novel skill discovery objective that maximizes the deviation of the state density of one skill from the explored regions of other","authors_text":"Chenjia Bai, Jiakun Zheng, Kang Xu, Peng Liu, Qiaosheng Zhang, Rushuai Yang, Ting Xiao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T11:30:04Z","title":"Unsupervised Skill Discovery through Skill Regions Differentiation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14420","kind":"arxiv","version":1},"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":"sha256:50635909b173b178abd770fb435622885228abd0e6482c2244be91b5d392bd22","target":"record","created_at":"2026-07-05T11:22:56Z","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":"103dc1d10b296c52c91411a5ce42147e9286ec3f002baf277bb19937d2c998e0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T11:30:04Z","title_canon_sha256":"bce8ad4637e4b6414221c5255e5ca9d7289a196fba69bac84ea68b4b4481dcfa"},"schema_version":"1.0","source":{"id":"2506.14420","kind":"arxiv","version":1}},"canonical_sha256":"01ddebab64d98516cf851dac4cb0200dfadac28aa739486a1a7752a5f2523a1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01ddebab64d98516cf851dac4cb0200dfadac28aa739486a1a7752a5f2523a1a","first_computed_at":"2026-07-05T11:22:56.197681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:56.197681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GBhfUlZp2jTkzCVYkHCQw7RdmkMqEx01J2YehluXhD2lfjgDFzUIjLxcbYST+EqyXSrlhDe4gXHp7VqWpoGpBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:56.198145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14420","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50635909b173b178abd770fb435622885228abd0e6482c2244be91b5d392bd22","sha256:1b569c1b2b95de33b6658473b53fd9be5012005a43b63b0c7762897d1af9e0ac"],"state_sha256":"8581283972bb04db60c637b52957b97cc53b4ee4db8a35420f01fc184d5e7890"}