{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RQXGNFVKS5UL6PLRLAY5E3KYJZ","short_pith_number":"pith:RQXGNFVK","schema_version":"1.0","canonical_sha256":"8c2e6696aa9768bf3d715831d26d584e703871224fef74bebe7b928a05b669ab","source":{"kind":"arxiv","id":"2410.17744","version":2},"attestation_state":"computed","paper":{"title":"Learning Versatile Skills with Curriculum Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Deheng Ye, Shuai Li, Yao Tang, Zhihui Xie, Zichuan Lin","submitted_at":"2024-10-23T10:17:13Z","abstract_excerpt":"Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified model. Despite the versatility of masked prediction, it remains unclear how to balance the learning of skills at different levels of complexity. To address this, we propose CurrMask, a curriculum masking pretraining paradigm for sequential decision making. Motivated by how humans learn by organizing knowledge in a curriculum, CurrMask adjusts its masking scheme during pretraining"},"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":"2410.17744","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T10:17:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1238740463d697105bdd62bc623bd27fa323b34f1ec1393cb640f5dea49147c1","abstract_canon_sha256":"5bd4a456f67345ac330d60ddb9408f069887879fa43f49c1ae6fe97d906f9adb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:22.786812Z","signature_b64":"8sYl2nrf09s0ar0dMHOOMCa9MbDAe41CrURaPJ3zTfv+23wLWVXE+SUaNszwvHnnJAoKlbORlKKs5GjRnLYQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c2e6696aa9768bf3d715831d26d584e703871224fef74bebe7b928a05b669ab","last_reissued_at":"2026-07-05T09:30:22.786323Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:22.786323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Versatile Skills with Curriculum Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Deheng Ye, Shuai Li, Yao Tang, Zhihui Xie, Zichuan Lin","submitted_at":"2024-10-23T10:17:13Z","abstract_excerpt":"Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified model. Despite the versatility of masked prediction, it remains unclear how to balance the learning of skills at different levels of complexity. To address this, we propose CurrMask, a curriculum masking pretraining paradigm for sequential decision making. Motivated by how humans learn by organizing knowledge in a curriculum, CurrMask adjusts its masking scheme during pretraining"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17744","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/2410.17744/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":"2410.17744","created_at":"2026-07-05T09:30:22.786384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17744v2","created_at":"2026-07-05T09:30:22.786384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17744","created_at":"2026-07-05T09:30:22.786384+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQXGNFVKS5UL","created_at":"2026-07-05T09:30:22.786384+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQXGNFVKS5UL6PLR","created_at":"2026-07-05T09:30:22.786384+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQXGNFVK","created_at":"2026-07-05T09:30:22.786384+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/RQXGNFVKS5UL6PLRLAY5E3KYJZ","json":"https://pith.science/pith/RQXGNFVKS5UL6PLRLAY5E3KYJZ.json","graph_json":"https://pith.science/api/pith-number/RQXGNFVKS5UL6PLRLAY5E3KYJZ/graph.json","events_json":"https://pith.science/api/pith-number/RQXGNFVKS5UL6PLRLAY5E3KYJZ/events.json","paper":"https://pith.science/paper/RQXGNFVK"},"agent_actions":{"view_html":"https://pith.science/pith/RQXGNFVKS5UL6PLRLAY5E3KYJZ","download_json":"https://pith.science/pith/RQXGNFVKS5UL6PLRLAY5E3KYJZ.json","view_paper":"https://pith.science/paper/RQXGNFVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17744&json=true","fetch_graph":"https://pith.science/api/pith-number/RQXGNFVKS5UL6PLRLAY5E3KYJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RQXGNFVKS5UL6PLRLAY5E3KYJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQXGNFVKS5UL6PLRLAY5E3KYJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQXGNFVKS5UL6PLRLAY5E3KYJZ/action/storage_attestation","attest_author":"https://pith.science/pith/RQXGNFVKS5UL6PLRLAY5E3KYJZ/action/author_attestation","sign_citation":"https://pith.science/pith/RQXGNFVKS5UL6PLRLAY5E3KYJZ/action/citation_signature","submit_replication":"https://pith.science/pith/RQXGNFVKS5UL6PLRLAY5E3KYJZ/action/replication_record"}},"created_at":"2026-07-05T09:30:22.786384+00:00","updated_at":"2026-07-05T09:30:22.786384+00:00"}