{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T54LY4J5S7XINTMTTWFZCWHX2X","short_pith_number":"pith:T54LY4J5","schema_version":"1.0","canonical_sha256":"9f78bc713d97ee86cd939d8b9158f7d5c250094c94da79c251814811e5a3a29c","source":{"kind":"arxiv","id":"2605.23372","version":1},"attestation_state":"computed","paper":{"title":"Curriculum reinforcement learning with measurable task representation learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mingjian Fu, Peng Liu, Siyuan Li, Xun Wang, Yiqin Yang, Yongyan Wen","submitted_at":"2026-05-22T08:36:49Z","abstract_excerpt":"In curriculum reinforcement learning (CRL), an agent incrementally accumulates knowledge over a sequence of tasks (i.e., a curriculum), and the learning process is aimed at using the accumulated knowledge to finally solve a challenging target task. While early CRL works focus on sequencing candidate tasks, recent research explores automatic curriculum generation. Among the rich CRL literature, the interpolation-based CRL paradigm is a main body, which automatically generates intermediate tasks by interpolating between the initial task distribution and the target task distribution in task space"},"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":"2605.23372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:36:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26de0f2a6dc13f1759b7a09f69f4dfaea1e3b3de153829e27d17ed8d1090855c","abstract_canon_sha256":"dd0d539ac7bc25d2bdd2741e55b3af09fd3aa75eb00f76e66385be1179d47e98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:51.334305Z","signature_b64":"QW/2GV9v5zpvxGzdlLGnQkXrV5JA7YyCZEcd/p4z+ip0OJD3teiY4JQPCJhQ1Ht+cYWv9qr+nXgcxWNs/o3hCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f78bc713d97ee86cd939d8b9158f7d5c250094c94da79c251814811e5a3a29c","last_reissued_at":"2026-05-25T02:01:51.333586Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:51.333586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curriculum reinforcement learning with measurable task representation learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mingjian Fu, Peng Liu, Siyuan Li, Xun Wang, Yiqin Yang, Yongyan Wen","submitted_at":"2026-05-22T08:36:49Z","abstract_excerpt":"In curriculum reinforcement learning (CRL), an agent incrementally accumulates knowledge over a sequence of tasks (i.e., a curriculum), and the learning process is aimed at using the accumulated knowledge to finally solve a challenging target task. While early CRL works focus on sequencing candidate tasks, recent research explores automatic curriculum generation. Among the rich CRL literature, the interpolation-based CRL paradigm is a main body, which automatically generates intermediate tasks by interpolating between the initial task distribution and the target task distribution in task space"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23372","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/2605.23372/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":"2605.23372","created_at":"2026-05-25T02:01:51.333693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23372v1","created_at":"2026-05-25T02:01:51.333693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23372","created_at":"2026-05-25T02:01:51.333693+00:00"},{"alias_kind":"pith_short_12","alias_value":"T54LY4J5S7XI","created_at":"2026-05-25T02:01:51.333693+00:00"},{"alias_kind":"pith_short_16","alias_value":"T54LY4J5S7XINTMT","created_at":"2026-05-25T02:01:51.333693+00:00"},{"alias_kind":"pith_short_8","alias_value":"T54LY4J5","created_at":"2026-05-25T02:01:51.333693+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/T54LY4J5S7XINTMTTWFZCWHX2X","json":"https://pith.science/pith/T54LY4J5S7XINTMTTWFZCWHX2X.json","graph_json":"https://pith.science/api/pith-number/T54LY4J5S7XINTMTTWFZCWHX2X/graph.json","events_json":"https://pith.science/api/pith-number/T54LY4J5S7XINTMTTWFZCWHX2X/events.json","paper":"https://pith.science/paper/T54LY4J5"},"agent_actions":{"view_html":"https://pith.science/pith/T54LY4J5S7XINTMTTWFZCWHX2X","download_json":"https://pith.science/pith/T54LY4J5S7XINTMTTWFZCWHX2X.json","view_paper":"https://pith.science/paper/T54LY4J5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23372&json=true","fetch_graph":"https://pith.science/api/pith-number/T54LY4J5S7XINTMTTWFZCWHX2X/graph.json","fetch_events":"https://pith.science/api/pith-number/T54LY4J5S7XINTMTTWFZCWHX2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T54LY4J5S7XINTMTTWFZCWHX2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T54LY4J5S7XINTMTTWFZCWHX2X/action/storage_attestation","attest_author":"https://pith.science/pith/T54LY4J5S7XINTMTTWFZCWHX2X/action/author_attestation","sign_citation":"https://pith.science/pith/T54LY4J5S7XINTMTTWFZCWHX2X/action/citation_signature","submit_replication":"https://pith.science/pith/T54LY4J5S7XINTMTTWFZCWHX2X/action/replication_record"}},"created_at":"2026-05-25T02:01:51.333693+00:00","updated_at":"2026-05-25T02:01:51.333693+00:00"}