{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UHRP43IOT5XKOG3G74FYVZBV23","short_pith_number":"pith:UHRP43IO","schema_version":"1.0","canonical_sha256":"a1e2fe6d0e9f6ea71b66ff0b8ae435d6d8ae0867a394dbe9ef249e5b8915eced","source":{"kind":"arxiv","id":"2607.01595","version":1},"attestation_state":"computed","paper":{"title":"Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Haoran Lin, Junyan Tan, Siyuan Guo, Tianyu Shen, Xinyue Luo, Yichen Fang, Zeyu Qiao","submitted_at":"2026-07-02T01:45:30Z","abstract_excerpt":"As the scale and complexity of cloud-based AI systems continue to escalate, ensuring service reliability through rapid fault detection and adaptive recovery has become a critical challenge. While existing approaches integrate Large Language Models (LLMs) for semantic understanding and Deep Reinforcement Learning (DRL) for policy optimization, they often rely on sequential, loosely coupled architectures that underutilize the generative and reasoning capabilities of LLMs. In this paper, we propose a paradigm shift with PASE, a Planning-Aware Semantic self-healing engine, a novel fault self-heali"},"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":"2607.01595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T01:45:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4adb3790e9ecf4db3991114c6ec1bcd0867852fccfad0c025fd40d6a95cb12c9","abstract_canon_sha256":"417e74261092e714b8de320916c6304fabe0dfbf9ce419d3dca15de6c87d3da7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:02.878202Z","signature_b64":"9bvd1zA9x8ggLzwRCAx+cmJCg1mXT0AtqAaAx/oRVVr561H86G/ONnuGNn6LJ2mEo3w9HY5/ZkE5dDOgdLr6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1e2fe6d0e9f6ea71b66ff0b8ae435d6d8ae0867a394dbe9ef249e5b8915eced","last_reissued_at":"2026-07-03T01:17:02.877842Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:02.877842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Haoran Lin, Junyan Tan, Siyuan Guo, Tianyu Shen, Xinyue Luo, Yichen Fang, Zeyu Qiao","submitted_at":"2026-07-02T01:45:30Z","abstract_excerpt":"As the scale and complexity of cloud-based AI systems continue to escalate, ensuring service reliability through rapid fault detection and adaptive recovery has become a critical challenge. While existing approaches integrate Large Language Models (LLMs) for semantic understanding and Deep Reinforcement Learning (DRL) for policy optimization, they often rely on sequential, loosely coupled architectures that underutilize the generative and reasoning capabilities of LLMs. In this paper, we propose a paradigm shift with PASE, a Planning-Aware Semantic self-healing engine, a novel fault self-heali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01595","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/2607.01595/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":"2607.01595","created_at":"2026-07-03T01:17:02.877899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01595v1","created_at":"2026-07-03T01:17:02.877899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01595","created_at":"2026-07-03T01:17:02.877899+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHRP43IOT5XK","created_at":"2026-07-03T01:17:02.877899+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHRP43IOT5XKOG3G","created_at":"2026-07-03T01:17:02.877899+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHRP43IO","created_at":"2026-07-03T01:17:02.877899+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/UHRP43IOT5XKOG3G74FYVZBV23","json":"https://pith.science/pith/UHRP43IOT5XKOG3G74FYVZBV23.json","graph_json":"https://pith.science/api/pith-number/UHRP43IOT5XKOG3G74FYVZBV23/graph.json","events_json":"https://pith.science/api/pith-number/UHRP43IOT5XKOG3G74FYVZBV23/events.json","paper":"https://pith.science/paper/UHRP43IO"},"agent_actions":{"view_html":"https://pith.science/pith/UHRP43IOT5XKOG3G74FYVZBV23","download_json":"https://pith.science/pith/UHRP43IOT5XKOG3G74FYVZBV23.json","view_paper":"https://pith.science/paper/UHRP43IO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01595&json=true","fetch_graph":"https://pith.science/api/pith-number/UHRP43IOT5XKOG3G74FYVZBV23/graph.json","fetch_events":"https://pith.science/api/pith-number/UHRP43IOT5XKOG3G74FYVZBV23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHRP43IOT5XKOG3G74FYVZBV23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHRP43IOT5XKOG3G74FYVZBV23/action/storage_attestation","attest_author":"https://pith.science/pith/UHRP43IOT5XKOG3G74FYVZBV23/action/author_attestation","sign_citation":"https://pith.science/pith/UHRP43IOT5XKOG3G74FYVZBV23/action/citation_signature","submit_replication":"https://pith.science/pith/UHRP43IOT5XKOG3G74FYVZBV23/action/replication_record"}},"created_at":"2026-07-03T01:17:02.877899+00:00","updated_at":"2026-07-03T01:17:02.877899+00:00"}