{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TRQVXQDFALVTD7VGTXJS3CMPIL","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":"dd936781f940cf8f81e28f4c71b52543f21b7f6fa6208f92cad360c5a877b629","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-19T22:48:20Z","title_canon_sha256":"19806871fd5cfbbddc1222af543669d385ee380fb5622ca9c6a1efeb53a74353"},"schema_version":"1.0","source":{"id":"2503.15726","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15726","created_at":"2026-07-05T10:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15726v1","created_at":"2026-07-05T10:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15726","created_at":"2026-07-05T10:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"TRQVXQDFALVT","created_at":"2026-07-05T10:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"TRQVXQDFALVTD7VG","created_at":"2026-07-05T10:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"TRQVXQDF","created_at":"2026-07-05T10:35:57Z"}],"graph_snapshots":[{"event_id":"sha256:b7dac9caf005a83a24d75f395981517722c19d324c02107528e7679de752b7af","target":"graph","created_at":"2026-07-05T10:35:57Z","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/2503.15726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The objective of this study is to design and implement a reinforcement learning (RL) environment using D\\&D 5E combat scenarios to challenge smaller RL agents through interaction with a robust adversarial agent controlled by advanced Large Language Models (LLMs) like GPT-4o and LLaMA 3 8B. This research employs Deep Q-Networks (DQN) for the smaller agents, creating a testbed for strategic AI development that also serves as an educational tool by simulating dynamic and unpredictable combat scenarios. We successfully integrated sophisticated language models into the RL framework, enhancing strat","authors_text":"Joseph Emmanuel DL Dayo, Michel Onasis S. Ogbinar, Prospero C. Naval Jr","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-19T22:48:20Z","title":"Reinforcement Learning Environment with LLM-Controlled Adversary in D&D 5th Edition Combat"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15726","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":"sha256:7651d9f03234e8f7567f26f31b50875d3d38be377396e22f3d073a14fab0808d","target":"record","created_at":"2026-07-05T10:35:57Z","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":"dd936781f940cf8f81e28f4c71b52543f21b7f6fa6208f92cad360c5a877b629","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-19T22:48:20Z","title_canon_sha256":"19806871fd5cfbbddc1222af543669d385ee380fb5622ca9c6a1efeb53a74353"},"schema_version":"1.0","source":{"id":"2503.15726","kind":"arxiv","version":1}},"canonical_sha256":"9c615bc06502eb31fea69dd32d898f42f7f9dcfd49d49049f26a62500c612750","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c615bc06502eb31fea69dd32d898f42f7f9dcfd49d49049f26a62500c612750","first_computed_at":"2026-07-05T10:35:57.369264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:57.369264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qf3mqhPVAOlqZwHidGDT0gRSL9Sd7vTCwSH8PoNPqjEGp/jPDIsOAEyksl+/Xwwqmjwk1kba3+8/YG5MSnGTBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:57.369734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15726","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7651d9f03234e8f7567f26f31b50875d3d38be377396e22f3d073a14fab0808d","sha256:b7dac9caf005a83a24d75f395981517722c19d324c02107528e7679de752b7af"],"state_sha256":"a675a2df20cd9dd407d9c0953c15047581a26a7e299f92b7f8d058e0a23d8b5e"}