{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ANNUU2OKAIWKFZTCZQ3MBVQOEK","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":"7de14ff9dbc54259faea446b405f6100a2a147ddc37fccbb8ee300148bda5137","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T14:49:34Z","title_canon_sha256":"9a461eecbadc5599bee9345a8b47d299cf4893dfe8d982dd68673129f13c0d40"},"schema_version":"1.0","source":{"id":"2304.12877","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.12877","created_at":"2026-07-05T06:04:21Z"},{"alias_kind":"arxiv_version","alias_value":"2304.12877v1","created_at":"2026-07-05T06:04:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12877","created_at":"2026-07-05T06:04:21Z"},{"alias_kind":"pith_short_12","alias_value":"ANNUU2OKAIWK","created_at":"2026-07-05T06:04:21Z"},{"alias_kind":"pith_short_16","alias_value":"ANNUU2OKAIWKFZTC","created_at":"2026-07-05T06:04:21Z"},{"alias_kind":"pith_short_8","alias_value":"ANNUU2OK","created_at":"2026-07-05T06:04:21Z"}],"graph_snapshots":[{"event_id":"sha256:c4a0adbe9c60547c256a234d9d3d4870a0c0a9247b53ab70a94fef73b51cbea1","target":"graph","created_at":"2026-07-05T06:04:21Z","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/2304.12877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of curriculum design for reinforcement learning (RL) agents in contextual multi-task settings. Existing techniques on automatic curriculum design typically require domain-specific hyperparameter tuning or have limited theoretical underpinnings. To tackle these limitations, we design our curriculum strategy, ProCuRL, inspired by the pedagogical concept of Zone of Proximal Development (ZPD). ProCuRL captures the intuition that learning progress is maximized when picking tasks that are neither too hard nor too easy for the learner. We mathematically derive ProCuRL by analy","authors_text":"Adish Singla, B\\'arbara Gomes Ribeiro, Georgios Tzannetos, Parameswaran Kamalaruban","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T14:49:34Z","title":"Proximal Curriculum for Reinforcement Learning Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12877","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":"sha256:7be00553d57f8129b9be681c23181cc89860c483b1998d3f413b8e60c44f3b6e","target":"record","created_at":"2026-07-05T06:04:21Z","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":"7de14ff9dbc54259faea446b405f6100a2a147ddc37fccbb8ee300148bda5137","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T14:49:34Z","title_canon_sha256":"9a461eecbadc5599bee9345a8b47d299cf4893dfe8d982dd68673129f13c0d40"},"schema_version":"1.0","source":{"id":"2304.12877","kind":"arxiv","version":1}},"canonical_sha256":"035b4a69ca022ca2e662cc36c0d60e228480fa4134ea7df28d8db7398662a172","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"035b4a69ca022ca2e662cc36c0d60e228480fa4134ea7df28d8db7398662a172","first_computed_at":"2026-07-05T06:04:21.958251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:21.958251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YcJPXJOJMMoWoQiOxa8S1qqZdY6DaF0JQ4t30yYH6yepTN+ao9zstMoq60efXnqMoTX+7YKCZxQu2CRBPEwmBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:21.958680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.12877","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7be00553d57f8129b9be681c23181cc89860c483b1998d3f413b8e60c44f3b6e","sha256:c4a0adbe9c60547c256a234d9d3d4870a0c0a9247b53ab70a94fef73b51cbea1"],"state_sha256":"f700053ab946f1979776405088deda01103452687451bbcb4bb049f0e9c117cf"}