{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SIPCHM5TF4HQWRTGGUZDKBLJVB","short_pith_number":"pith:SIPCHM5T","schema_version":"1.0","canonical_sha256":"921e23b3b32f0f0b46663532350569a840acdf7fc1a685ad700a4a92480fa524","source":{"kind":"arxiv","id":"2608.00677","version":1},"attestation_state":"computed","paper":{"title":"OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Li, Xia Hu, Xingjun Ma, Xin Wang, Yan Teng, Yi Liu, Yixu Wang, Yu-Gang Jiang, Yunhao Chen","submitted_at":"2026-08-01T13:51:55Z","abstract_excerpt":"AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior is mediated through a shared state that is repeatedly modified and reused across long-horizon workflows. Current safety benchmarks often fail to capture these cumulative risks because they focus on short, static tasks. To address these limitations, we introduce OpenART, an open-ended arena for scalable agent red teaming through environment evolution. OpenART provides over 10,000 validated stateful scenarios across 50"},"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":"2608.00677","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T13:51:55Z","cross_cats_sorted":[],"title_canon_sha256":"dbe72ceb91dd519098323988b35506b87128df55ceeb8c947d63093988325581","abstract_canon_sha256":"5d9b30e0392d1f095b97b605d0138176efadda475f3f544b3cb77147a92eb603"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:39:28.730000Z","signature_b64":"OWAgWcbUAdOXkcrGpaSAx7wv3Ea3ZxDqgh2KZzO/UcU2ULAsFNjkgM+2XFqW3VUwVNsobYwpH0PHPj0in+csDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"921e23b3b32f0f0b46663532350569a840acdf7fc1a685ad700a4a92480fa524","last_reissued_at":"2026-08-04T00:39:28.728573Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:39:28.728573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Li, Xia Hu, Xingjun Ma, Xin Wang, Yan Teng, Yi Liu, Yixu Wang, Yu-Gang Jiang, Yunhao Chen","submitted_at":"2026-08-01T13:51:55Z","abstract_excerpt":"AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior is mediated through a shared state that is repeatedly modified and reused across long-horizon workflows. Current safety benchmarks often fail to capture these cumulative risks because they focus on short, static tasks. To address these limitations, we introduce OpenART, an open-ended arena for scalable agent red teaming through environment evolution. OpenART provides over 10,000 validated stateful scenarios across 50"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00677","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/2608.00677/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":"2608.00677","created_at":"2026-08-04T00:39:28.729844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00677v1","created_at":"2026-08-04T00:39:28.729844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00677","created_at":"2026-08-04T00:39:28.729844+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIPCHM5TF4HQ","created_at":"2026-08-04T00:39:28.729844+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIPCHM5TF4HQWRTG","created_at":"2026-08-04T00:39:28.729844+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIPCHM5T","created_at":"2026-08-04T00:39:28.729844+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/SIPCHM5TF4HQWRTGGUZDKBLJVB","json":"https://pith.science/pith/SIPCHM5TF4HQWRTGGUZDKBLJVB.json","graph_json":"https://pith.science/api/pith-number/SIPCHM5TF4HQWRTGGUZDKBLJVB/graph.json","events_json":"https://pith.science/api/pith-number/SIPCHM5TF4HQWRTGGUZDKBLJVB/events.json","paper":"https://pith.science/paper/SIPCHM5T"},"agent_actions":{"view_html":"https://pith.science/pith/SIPCHM5TF4HQWRTGGUZDKBLJVB","download_json":"https://pith.science/pith/SIPCHM5TF4HQWRTGGUZDKBLJVB.json","view_paper":"https://pith.science/paper/SIPCHM5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00677&json=true","fetch_graph":"https://pith.science/api/pith-number/SIPCHM5TF4HQWRTGGUZDKBLJVB/graph.json","fetch_events":"https://pith.science/api/pith-number/SIPCHM5TF4HQWRTGGUZDKBLJVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIPCHM5TF4HQWRTGGUZDKBLJVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIPCHM5TF4HQWRTGGUZDKBLJVB/action/storage_attestation","attest_author":"https://pith.science/pith/SIPCHM5TF4HQWRTGGUZDKBLJVB/action/author_attestation","sign_citation":"https://pith.science/pith/SIPCHM5TF4HQWRTGGUZDKBLJVB/action/citation_signature","submit_replication":"https://pith.science/pith/SIPCHM5TF4HQWRTGGUZDKBLJVB/action/replication_record"}},"created_at":"2026-08-04T00:39:28.729844+00:00","updated_at":"2026-08-04T00:39:28.729844+00:00"}