{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WTCL3SM7WNPHXBVKBXG7D6LTOI","short_pith_number":"pith:WTCL3SM7","canonical_record":{"source":{"id":"2506.21044","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:45:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a1c06b6dd28c5fccf8d0b47555c09e8f322ffb637f52fb998a3263c6264e61b","abstract_canon_sha256":"3741f3b8b4a1f0da67e86f843efd5ef7ebed3bbdcfb994620b4260ba8df11cda"},"schema_version":"1.0"},"canonical_sha256":"b4c4bdc99fb35e7b86aa0dcdf1f9737206728ca78951baaf0cc93f47526b07df","source":{"kind":"arxiv","id":"2506.21044","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21044","created_at":"2026-07-05T11:27:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21044v1","created_at":"2026-07-05T11:27:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21044","created_at":"2026-07-05T11:27:38Z"},{"alias_kind":"pith_short_12","alias_value":"WTCL3SM7WNPH","created_at":"2026-07-05T11:27:38Z"},{"alias_kind":"pith_short_16","alias_value":"WTCL3SM7WNPHXBVK","created_at":"2026-07-05T11:27:38Z"},{"alias_kind":"pith_short_8","alias_value":"WTCL3SM7","created_at":"2026-07-05T11:27:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WTCL3SM7WNPHXBVKBXG7D6LTOI","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21044","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:45:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a1c06b6dd28c5fccf8d0b47555c09e8f322ffb637f52fb998a3263c6264e61b","abstract_canon_sha256":"3741f3b8b4a1f0da67e86f843efd5ef7ebed3bbdcfb994620b4260ba8df11cda"},"schema_version":"1.0"},"canonical_sha256":"b4c4bdc99fb35e7b86aa0dcdf1f9737206728ca78951baaf0cc93f47526b07df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:38.644769Z","signature_b64":"Bah1c3/iDpbF1ep9Ha973Zys3qbgUQAhKUlE59eKTXBXy0P/3ED7xw7/RN8xv4ck/hQZuiKn3WrE6qZ+3eKNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4c4bdc99fb35e7b86aa0dcdf1f9737206728ca78951baaf0cc93f47526b07df","last_reissued_at":"2026-07-05T11:27:38.644241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:38.644241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21044","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALtiSZXXTLb+3AZ4hWJmGvupAor8pW+k+uEkBaJ2I1L/ZGK1dw+/c3ij7E3i0tOUcBZWFjkVNcjInvoCVUpoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:51:40.673206Z"},"content_sha256":"60535924ddea7df4377f42593a8d7f77fc25658be711404b71b6d51ee4a236cb","schema_version":"1.0","event_id":"sha256:60535924ddea7df4377f42593a8d7f77fc25658be711404b71b6d51ee4a236cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WTCL3SM7WNPHXBVKBXG7D6LTOI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Skill Discovery via Regret-Aware Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"He Zhang, Hui Xiong, Ming Zhou, Shaopeng Zhai, Ying Sun","submitted_at":"2025-06-26T06:45:59Z","abstract_excerpt":"Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For existing methods, they focus on improving diversity through pure exploration, mutual information optimization, and learning temporal representation. Despite that they perform well on exploration, they remain limited in terms of efficiency, especially for the high-dimensional situations. In this work, we frame skill discovery as a min-max game of skill generation and policy learning, proposing a regret-aware method on top of temporal representation learning that expands the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21044","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/2506.21044/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"buCO15AtTG5GoXQ6VNcTydxei8zu+FkbGJW1Nt+/s0yOerbpMpNCQawYWjkS1Kw28kY/2GT6YA/L1hg4E1AnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:51:40.673942Z"},"content_sha256":"bf11fe1ff1fcbe6572daa06f1c4d0f8108eb2a6806a96b72b4e48a9c18fcc135","schema_version":"1.0","event_id":"sha256:bf11fe1ff1fcbe6572daa06f1c4d0f8108eb2a6806a96b72b4e48a9c18fcc135"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTCL3SM7WNPHXBVKBXG7D6LTOI/bundle.json","state_url":"https://pith.science/pith/WTCL3SM7WNPHXBVKBXG7D6LTOI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTCL3SM7WNPHXBVKBXG7D6LTOI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T12:51:40Z","links":{"resolver":"https://pith.science/pith/WTCL3SM7WNPHXBVKBXG7D6LTOI","bundle":"https://pith.science/pith/WTCL3SM7WNPHXBVKBXG7D6LTOI/bundle.json","state":"https://pith.science/pith/WTCL3SM7WNPHXBVKBXG7D6LTOI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTCL3SM7WNPHXBVKBXG7D6LTOI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WTCL3SM7WNPHXBVKBXG7D6LTOI","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":"3741f3b8b4a1f0da67e86f843efd5ef7ebed3bbdcfb994620b4260ba8df11cda","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:45:59Z","title_canon_sha256":"5a1c06b6dd28c5fccf8d0b47555c09e8f322ffb637f52fb998a3263c6264e61b"},"schema_version":"1.0","source":{"id":"2506.21044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21044","created_at":"2026-07-05T11:27:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21044v1","created_at":"2026-07-05T11:27:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21044","created_at":"2026-07-05T11:27:38Z"},{"alias_kind":"pith_short_12","alias_value":"WTCL3SM7WNPH","created_at":"2026-07-05T11:27:38Z"},{"alias_kind":"pith_short_16","alias_value":"WTCL3SM7WNPHXBVK","created_at":"2026-07-05T11:27:38Z"},{"alias_kind":"pith_short_8","alias_value":"WTCL3SM7","created_at":"2026-07-05T11:27:38Z"}],"graph_snapshots":[{"event_id":"sha256:bf11fe1ff1fcbe6572daa06f1c4d0f8108eb2a6806a96b72b4e48a9c18fcc135","target":"graph","created_at":"2026-07-05T11:27:38Z","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/2506.21044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For existing methods, they focus on improving diversity through pure exploration, mutual information optimization, and learning temporal representation. Despite that they perform well on exploration, they remain limited in terms of efficiency, especially for the high-dimensional situations. In this work, we frame skill discovery as a min-max game of skill generation and policy learning, proposing a regret-aware method on top of temporal representation learning that expands the","authors_text":"He Zhang, Hui Xiong, Ming Zhou, Shaopeng Zhai, Ying Sun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:45:59Z","title":"Efficient Skill Discovery via Regret-Aware Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21044","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":"sha256:60535924ddea7df4377f42593a8d7f77fc25658be711404b71b6d51ee4a236cb","target":"record","created_at":"2026-07-05T11:27:38Z","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":"3741f3b8b4a1f0da67e86f843efd5ef7ebed3bbdcfb994620b4260ba8df11cda","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:45:59Z","title_canon_sha256":"5a1c06b6dd28c5fccf8d0b47555c09e8f322ffb637f52fb998a3263c6264e61b"},"schema_version":"1.0","source":{"id":"2506.21044","kind":"arxiv","version":1}},"canonical_sha256":"b4c4bdc99fb35e7b86aa0dcdf1f9737206728ca78951baaf0cc93f47526b07df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4c4bdc99fb35e7b86aa0dcdf1f9737206728ca78951baaf0cc93f47526b07df","first_computed_at":"2026-07-05T11:27:38.644241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:38.644241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bah1c3/iDpbF1ep9Ha973Zys3qbgUQAhKUlE59eKTXBXy0P/3ED7xw7/RN8xv4ck/hQZuiKn3WrE6qZ+3eKNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:38.644769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60535924ddea7df4377f42593a8d7f77fc25658be711404b71b6d51ee4a236cb","sha256:bf11fe1ff1fcbe6572daa06f1c4d0f8108eb2a6806a96b72b4e48a9c18fcc135"],"state_sha256":"1db488f23172ca3504fd131761cb33b2d05a83b73a52a39d3432bfb838a558cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DGnKIpzs80gtl9jVQLrRe98FpDFC2EeaEk5GKCU3cWu8LUH5ToEm6DfLt27vM7F4Dd66uMBYDRzsa4gk7yVIDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:51:40.679563Z","bundle_sha256":"0612da10c1a11396741f801061d5fdacb7bae7e374bf7c369bc2ff0047517905"}}