{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IO6JUUWJT46YIPCWT5EPMRTETW","short_pith_number":"pith:IO6JUUWJ","schema_version":"1.0","canonical_sha256":"43bc9a52c99f3d843c569f48f646649db68d51f5f07317bcc8784962facf6a5f","source":{"kind":"arxiv","id":"2607.05773","version":1},"attestation_state":"computed","paper":{"title":"Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akshay Arora, Ashutosh Aggarwal, Ishan Nigam, Krishna Singh, Nikhil Mittal, Shariq Farhan, Shefali Bansal, Siddarth Malreddy, Sweta Kumari","submitted_at":"2026-07-07T02:56:27Z","abstract_excerpt":"As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making. We introduce AgenticAI-Supervisor, an API and UI-driven RL Gym environment that decouples environment creation from scalable execution. By moving to verifiable execution outcomes, the platform generates high-fidelity traces and applies multi-dimensional reward shaping. Critically, our framework mitigates reward hacking through rigorous internal state validation and testing. This work provides a first look at our platform's core capabilities through a Custome"},"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":"2607.05773","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T02:56:27Z","cross_cats_sorted":[],"title_canon_sha256":"206bbdc958881ddb20d13c887f2ccc219c72c4d5690930fe6abebf4ab42442f4","abstract_canon_sha256":"1e0663d2b80ef6a9a2a5336df3071694c898f49bde85482ff57f3dcbbc29bbce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:44.650182Z","signature_b64":"arYI0FRj+cg0DH/XfmJIaC0R3b+hwd28KFUtUFoabJxE1+1TP0nqBj8yKj56B+B4lD09C+GyDVuNgVJ4a0mEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43bc9a52c99f3d843c569f48f646649db68d51f5f07317bcc8784962facf6a5f","last_reissued_at":"2026-07-08T01:18:44.649757Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:44.649757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akshay Arora, Ashutosh Aggarwal, Ishan Nigam, Krishna Singh, Nikhil Mittal, Shariq Farhan, Shefali Bansal, Siddarth Malreddy, Sweta Kumari","submitted_at":"2026-07-07T02:56:27Z","abstract_excerpt":"As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making. We introduce AgenticAI-Supervisor, an API and UI-driven RL Gym environment that decouples environment creation from scalable execution. By moving to verifiable execution outcomes, the platform generates high-fidelity traces and applies multi-dimensional reward shaping. Critically, our framework mitigates reward hacking through rigorous internal state validation and testing. This work provides a first look at our platform's core capabilities through a Custome"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05773","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/2607.05773/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":"2607.05773","created_at":"2026-07-08T01:18:44.649823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05773v1","created_at":"2026-07-08T01:18:44.649823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05773","created_at":"2026-07-08T01:18:44.649823+00:00"},{"alias_kind":"pith_short_12","alias_value":"IO6JUUWJT46Y","created_at":"2026-07-08T01:18:44.649823+00:00"},{"alias_kind":"pith_short_16","alias_value":"IO6JUUWJT46YIPCW","created_at":"2026-07-08T01:18:44.649823+00:00"},{"alias_kind":"pith_short_8","alias_value":"IO6JUUWJ","created_at":"2026-07-08T01:18:44.649823+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/IO6JUUWJT46YIPCWT5EPMRTETW","json":"https://pith.science/pith/IO6JUUWJT46YIPCWT5EPMRTETW.json","graph_json":"https://pith.science/api/pith-number/IO6JUUWJT46YIPCWT5EPMRTETW/graph.json","events_json":"https://pith.science/api/pith-number/IO6JUUWJT46YIPCWT5EPMRTETW/events.json","paper":"https://pith.science/paper/IO6JUUWJ"},"agent_actions":{"view_html":"https://pith.science/pith/IO6JUUWJT46YIPCWT5EPMRTETW","download_json":"https://pith.science/pith/IO6JUUWJT46YIPCWT5EPMRTETW.json","view_paper":"https://pith.science/paper/IO6JUUWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05773&json=true","fetch_graph":"https://pith.science/api/pith-number/IO6JUUWJT46YIPCWT5EPMRTETW/graph.json","fetch_events":"https://pith.science/api/pith-number/IO6JUUWJT46YIPCWT5EPMRTETW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IO6JUUWJT46YIPCWT5EPMRTETW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IO6JUUWJT46YIPCWT5EPMRTETW/action/storage_attestation","attest_author":"https://pith.science/pith/IO6JUUWJT46YIPCWT5EPMRTETW/action/author_attestation","sign_citation":"https://pith.science/pith/IO6JUUWJT46YIPCWT5EPMRTETW/action/citation_signature","submit_replication":"https://pith.science/pith/IO6JUUWJT46YIPCWT5EPMRTETW/action/replication_record"}},"created_at":"2026-07-08T01:18:44.649823+00:00","updated_at":"2026-07-08T01:18:44.649823+00:00"}