{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TKXVOTXQMGABX2LYY7Q6CXOY4O","short_pith_number":"pith:TKXVOTXQ","schema_version":"1.0","canonical_sha256":"9aaf574ef061801be978c7e1e15dd8e3a6140bea36b9ed9fd581f6b348347ff6","source":{"kind":"arxiv","id":"2606.20324","version":1},"attestation_state":"computed","paper":{"title":"A Model-Driven Approach for Developing Families of Reinforcement Learning Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Istvan David, Xiaoran Liu","submitted_at":"2026-06-18T15:02:38Z","abstract_excerpt":"Virtual training environments are software-intensive systems in which reinforcement learning (RL) agents learn, adapt, and demonstrate meaningful behavior. Virtual training environments offer a safe and cost-efficient alternative to training agents in real-world settings. However, to converge, most realistic RL problems require training in multiple, mostly similar but slightly different environments - i.e., families of environment variants. The typical development process of environment families is a labor-intensive and error-prone manual endeavor that does not scale well. To alleviate these i"},"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":"2606.20324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-18T15:02:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d5812cac4c352ab92ed53e78965e15aa64176dff7f1b4f3117eb01f9b3c5f8d4","abstract_canon_sha256":"c27d9d382cf7e2d1cfa3558faebe588ed255f2a3f345eff4e1be0fd11cef32a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:08.949413Z","signature_b64":"qU0dnD3Z4HpwvI/1mZiLGOahcQKJHsAzBE0nmuuvp95DEs5mPisyvkDQgc0GoKQU3Yu0/nY8/PGET+7/uEbPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9aaf574ef061801be978c7e1e15dd8e3a6140bea36b9ed9fd581f6b348347ff6","last_reissued_at":"2026-06-19T16:13:08.949019Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:08.949019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Model-Driven Approach for Developing Families of Reinforcement Learning Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Istvan David, Xiaoran Liu","submitted_at":"2026-06-18T15:02:38Z","abstract_excerpt":"Virtual training environments are software-intensive systems in which reinforcement learning (RL) agents learn, adapt, and demonstrate meaningful behavior. Virtual training environments offer a safe and cost-efficient alternative to training agents in real-world settings. However, to converge, most realistic RL problems require training in multiple, mostly similar but slightly different environments - i.e., families of environment variants. The typical development process of environment families is a labor-intensive and error-prone manual endeavor that does not scale well. To alleviate these i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20324","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/2606.20324/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":"2606.20324","created_at":"2026-06-19T16:13:08.949084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20324v1","created_at":"2026-06-19T16:13:08.949084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20324","created_at":"2026-06-19T16:13:08.949084+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKXVOTXQMGAB","created_at":"2026-06-19T16:13:08.949084+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKXVOTXQMGABX2LY","created_at":"2026-06-19T16:13:08.949084+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKXVOTXQ","created_at":"2026-06-19T16:13:08.949084+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/TKXVOTXQMGABX2LYY7Q6CXOY4O","json":"https://pith.science/pith/TKXVOTXQMGABX2LYY7Q6CXOY4O.json","graph_json":"https://pith.science/api/pith-number/TKXVOTXQMGABX2LYY7Q6CXOY4O/graph.json","events_json":"https://pith.science/api/pith-number/TKXVOTXQMGABX2LYY7Q6CXOY4O/events.json","paper":"https://pith.science/paper/TKXVOTXQ"},"agent_actions":{"view_html":"https://pith.science/pith/TKXVOTXQMGABX2LYY7Q6CXOY4O","download_json":"https://pith.science/pith/TKXVOTXQMGABX2LYY7Q6CXOY4O.json","view_paper":"https://pith.science/paper/TKXVOTXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20324&json=true","fetch_graph":"https://pith.science/api/pith-number/TKXVOTXQMGABX2LYY7Q6CXOY4O/graph.json","fetch_events":"https://pith.science/api/pith-number/TKXVOTXQMGABX2LYY7Q6CXOY4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKXVOTXQMGABX2LYY7Q6CXOY4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKXVOTXQMGABX2LYY7Q6CXOY4O/action/storage_attestation","attest_author":"https://pith.science/pith/TKXVOTXQMGABX2LYY7Q6CXOY4O/action/author_attestation","sign_citation":"https://pith.science/pith/TKXVOTXQMGABX2LYY7Q6CXOY4O/action/citation_signature","submit_replication":"https://pith.science/pith/TKXVOTXQMGABX2LYY7Q6CXOY4O/action/replication_record"}},"created_at":"2026-06-19T16:13:08.949084+00:00","updated_at":"2026-06-19T16:13:08.949084+00:00"}