{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5AR7YT6WV7AZ5OMESRE2MZ4UDZ","short_pith_number":"pith:5AR7YT6W","schema_version":"1.0","canonical_sha256":"e823fc4fd6afc19eb9849449a667941e77b18cc871372f1ee92c8d354cf0f023","source":{"kind":"arxiv","id":"2606.06212","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Agentic Configuration Repair for Computer Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Benjamin Hoffman, Ioannis Protogeros, Laurent Vanbever, Rufat Asadli","submitted_at":"2026-06-04T14:20:25Z","abstract_excerpt":"Misconfigurations in computer networks remain a major source of critical Internet outages. Research is turning to Large Language Models (LLMs) to automate the complex, error-prone task of network configuration. However, even state-of-the-art models fail to resolve misconfigurations in large-scale, complex scenarios and often introduce new errors. In this work, we benchmark open- and closed-source LLMs augmented with formal network verification and context retrieval tools. We demonstrate that agentic architectures outperform base LLMs in repair efficacy (by 12% on average) and safety (by 17% on"},"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":"2606.06212","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T14:20:25Z","cross_cats_sorted":[],"title_canon_sha256":"2ee221a93ca184608a9c9a1bc0ea0e1679e5f7aca4adecb93abd176f5ad21e0a","abstract_canon_sha256":"94296180d77808cab04c0066befeee4d296481c0ae4cd77184fdeaa6a1bcb614"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:37.587094Z","signature_b64":"1tpao0vtvjn65RbRaHrRw+CKPoJyxFRwPy9VouZufH/DmqDNd39xoV6SfNI1a0H/AgQmXDkttQbQC/en2vPWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e823fc4fd6afc19eb9849449a667941e77b18cc871372f1ee92c8d354cf0f023","last_reissued_at":"2026-06-05T01:15:37.586582Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:37.586582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Agentic Configuration Repair for Computer Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Benjamin Hoffman, Ioannis Protogeros, Laurent Vanbever, Rufat Asadli","submitted_at":"2026-06-04T14:20:25Z","abstract_excerpt":"Misconfigurations in computer networks remain a major source of critical Internet outages. Research is turning to Large Language Models (LLMs) to automate the complex, error-prone task of network configuration. However, even state-of-the-art models fail to resolve misconfigurations in large-scale, complex scenarios and often introduce new errors. In this work, we benchmark open- and closed-source LLMs augmented with formal network verification and context retrieval tools. We demonstrate that agentic architectures outperform base LLMs in repair efficacy (by 12% on average) and safety (by 17% on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06212","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/2606.06212/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":"2606.06212","created_at":"2026-06-05T01:15:37.586662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06212v1","created_at":"2026-06-05T01:15:37.586662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06212","created_at":"2026-06-05T01:15:37.586662+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AR7YT6WV7AZ","created_at":"2026-06-05T01:15:37.586662+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AR7YT6WV7AZ5OME","created_at":"2026-06-05T01:15:37.586662+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AR7YT6W","created_at":"2026-06-05T01:15:37.586662+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/5AR7YT6WV7AZ5OMESRE2MZ4UDZ","json":"https://pith.science/pith/5AR7YT6WV7AZ5OMESRE2MZ4UDZ.json","graph_json":"https://pith.science/api/pith-number/5AR7YT6WV7AZ5OMESRE2MZ4UDZ/graph.json","events_json":"https://pith.science/api/pith-number/5AR7YT6WV7AZ5OMESRE2MZ4UDZ/events.json","paper":"https://pith.science/paper/5AR7YT6W"},"agent_actions":{"view_html":"https://pith.science/pith/5AR7YT6WV7AZ5OMESRE2MZ4UDZ","download_json":"https://pith.science/pith/5AR7YT6WV7AZ5OMESRE2MZ4UDZ.json","view_paper":"https://pith.science/paper/5AR7YT6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06212&json=true","fetch_graph":"https://pith.science/api/pith-number/5AR7YT6WV7AZ5OMESRE2MZ4UDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5AR7YT6WV7AZ5OMESRE2MZ4UDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AR7YT6WV7AZ5OMESRE2MZ4UDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AR7YT6WV7AZ5OMESRE2MZ4UDZ/action/storage_attestation","attest_author":"https://pith.science/pith/5AR7YT6WV7AZ5OMESRE2MZ4UDZ/action/author_attestation","sign_citation":"https://pith.science/pith/5AR7YT6WV7AZ5OMESRE2MZ4UDZ/action/citation_signature","submit_replication":"https://pith.science/pith/5AR7YT6WV7AZ5OMESRE2MZ4UDZ/action/replication_record"}},"created_at":"2026-06-05T01:15:37.586662+00:00","updated_at":"2026-06-05T01:15:37.586662+00:00"}