{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MLWTPH2DC6Z2KRBWLXIGSZ7NJV","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":"b404d95d3b31691646be5efc37aeb95859ef343aec80e1140ec461593f1ae225","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T04:19:43Z","title_canon_sha256":"4116ff160041c6027f91c352bea2c96bf4f0f30703be13cfbb6b9bf4d981220e"},"schema_version":"1.0","source":{"id":"2312.13565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.13565","created_at":"2026-07-05T07:26:46Z"},{"alias_kind":"arxiv_version","alias_value":"2312.13565v1","created_at":"2026-07-05T07:26:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13565","created_at":"2026-07-05T07:26:46Z"},{"alias_kind":"pith_short_12","alias_value":"MLWTPH2DC6Z2","created_at":"2026-07-05T07:26:46Z"},{"alias_kind":"pith_short_16","alias_value":"MLWTPH2DC6Z2KRBW","created_at":"2026-07-05T07:26:46Z"},{"alias_kind":"pith_short_8","alias_value":"MLWTPH2D","created_at":"2026-07-05T07:26:46Z"}],"graph_snapshots":[{"event_id":"sha256:2571db13e7b162d0e9d6356d06fa53a09d288feca19d63b0de0f93a6895a4377","target":"graph","created_at":"2026-07-05T07:26:46Z","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/2312.13565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the impact of using gradient norm reward signals in the context of Automatic Curriculum Learning (ACL) for deep reinforcement learning (DRL). We introduce a framework where the teacher model, utilizing the gradient norm information of a student model, dynamically adapts the learning curriculum. This approach is based on the hypothesis that gradient norms can provide a nuanced and effective measure of learning progress. Our experimental setup involves several reinforcement learning environments (PointMaze, AntMaze, and AdroitHandRelocate), to assess the efficacy of our m","authors_text":"Junsang Yoon, Ryan Campbell","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T04:19:43Z","title":"Automatic Curriculum Learning with Gradient Reward Signals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13565","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:cf27f99965387f46ed0a0929b8c290471a152f124927dc1008858edf433e12cd","target":"record","created_at":"2026-07-05T07:26:46Z","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":"b404d95d3b31691646be5efc37aeb95859ef343aec80e1140ec461593f1ae225","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T04:19:43Z","title_canon_sha256":"4116ff160041c6027f91c352bea2c96bf4f0f30703be13cfbb6b9bf4d981220e"},"schema_version":"1.0","source":{"id":"2312.13565","kind":"arxiv","version":1}},"canonical_sha256":"62ed379f4317b3a544365dd06967ed4d53500fe6b68cc4a8bc7c767453cd7c11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62ed379f4317b3a544365dd06967ed4d53500fe6b68cc4a8bc7c767453cd7c11","first_computed_at":"2026-07-05T07:26:46.611748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:26:46.611748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MC40XEr2ccgARYAds5eloJqtjX06MBGTaVVQwR/YNd2e03AxATOcPV42ZtjQrmurVWbZMp2Uytbo8ytdsycZAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:26:46.612193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.13565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf27f99965387f46ed0a0929b8c290471a152f124927dc1008858edf433e12cd","sha256:2571db13e7b162d0e9d6356d06fa53a09d288feca19d63b0de0f93a6895a4377"],"state_sha256":"28f90578c6ecc2c5e8a332e9c65c808bde40eb2adb816c0f42c414b9446a330e"}