{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:66H32YO55XGC657BTIJK23ALOF","short_pith_number":"pith:66H32YO5","schema_version":"1.0","canonical_sha256":"f78fbd61ddedcc2f77e19a12ad6c0b714224a2f648342bb0846f1632e8bad353","source":{"kind":"arxiv","id":"2602.01619","version":2},"attestation_state":"computed","paper":{"title":"SUSD: Structured Unsupervised Skill Discovery through State Factorization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mahdieh Soleymani Baghshah, Seyed Mohammad Hadi Hosseini","submitted_at":"2026-02-02T04:21:33Z","abstract_excerpt":"Unsupervised Skill Discovery (USD) aims to autonomously learn a diverse set of skills without relying on extrinsic rewards. One of the most common USD approaches is to maximize the Mutual Information (MI) between skill latent variables and states. However, MI-based methods tend to favor simple, static skills due to their invariance properties, limiting the discovery of dynamic, task-relevant behaviors. Distance-Maximizing Skill Discovery (DSD) promotes more dynamic skills by leveraging state-space distances, yet still fall short in encouraging comprehensive skill sets that engage all controlla"},"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":"2602.01619","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T04:21:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"152903513e9b3eb76d074f0ba3d4d112cc85bcb19713c2bb21163f22f3f631d0","abstract_canon_sha256":"1c115f872a7e5b843a1d5641d8f1229e015ece2e7234511de27ef38b325401ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:41.094349Z","signature_b64":"SFdcSjtXYkRqv/Gytm6yDF6GiQKRcVexwcKq+Y86gTXbHTzUgKcrC7cM8XNrdX13JgQJB0Ks9QQCDCa8pSLBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f78fbd61ddedcc2f77e19a12ad6c0b714224a2f648342bb0846f1632e8bad353","last_reissued_at":"2026-06-04T01:08:41.093725Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:41.093725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SUSD: Structured Unsupervised Skill Discovery through State Factorization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mahdieh Soleymani Baghshah, Seyed Mohammad Hadi Hosseini","submitted_at":"2026-02-02T04:21:33Z","abstract_excerpt":"Unsupervised Skill Discovery (USD) aims to autonomously learn a diverse set of skills without relying on extrinsic rewards. One of the most common USD approaches is to maximize the Mutual Information (MI) between skill latent variables and states. However, MI-based methods tend to favor simple, static skills due to their invariance properties, limiting the discovery of dynamic, task-relevant behaviors. Distance-Maximizing Skill Discovery (DSD) promotes more dynamic skills by leveraging state-space distances, yet still fall short in encouraging comprehensive skill sets that engage all controlla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01619","kind":"arxiv","version":2},"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/2602.01619/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":"2602.01619","created_at":"2026-06-04T01:08:41.093801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.01619v2","created_at":"2026-06-04T01:08:41.093801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01619","created_at":"2026-06-04T01:08:41.093801+00:00"},{"alias_kind":"pith_short_12","alias_value":"66H32YO55XGC","created_at":"2026-06-04T01:08:41.093801+00:00"},{"alias_kind":"pith_short_16","alias_value":"66H32YO55XGC657B","created_at":"2026-06-04T01:08:41.093801+00:00"},{"alias_kind":"pith_short_8","alias_value":"66H32YO5","created_at":"2026-06-04T01:08:41.093801+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/66H32YO55XGC657BTIJK23ALOF","json":"https://pith.science/pith/66H32YO55XGC657BTIJK23ALOF.json","graph_json":"https://pith.science/api/pith-number/66H32YO55XGC657BTIJK23ALOF/graph.json","events_json":"https://pith.science/api/pith-number/66H32YO55XGC657BTIJK23ALOF/events.json","paper":"https://pith.science/paper/66H32YO5"},"agent_actions":{"view_html":"https://pith.science/pith/66H32YO55XGC657BTIJK23ALOF","download_json":"https://pith.science/pith/66H32YO55XGC657BTIJK23ALOF.json","view_paper":"https://pith.science/paper/66H32YO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.01619&json=true","fetch_graph":"https://pith.science/api/pith-number/66H32YO55XGC657BTIJK23ALOF/graph.json","fetch_events":"https://pith.science/api/pith-number/66H32YO55XGC657BTIJK23ALOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66H32YO55XGC657BTIJK23ALOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66H32YO55XGC657BTIJK23ALOF/action/storage_attestation","attest_author":"https://pith.science/pith/66H32YO55XGC657BTIJK23ALOF/action/author_attestation","sign_citation":"https://pith.science/pith/66H32YO55XGC657BTIJK23ALOF/action/citation_signature","submit_replication":"https://pith.science/pith/66H32YO55XGC657BTIJK23ALOF/action/replication_record"}},"created_at":"2026-06-04T01:08:41.093801+00:00","updated_at":"2026-06-04T01:08:41.093801+00:00"}