{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GSJFHZ2K5VRFUFPVTEMPJVT6KB","short_pith_number":"pith:GSJFHZ2K","schema_version":"1.0","canonical_sha256":"349253e74aed625a15f59918f4d67e506fc5c07a5cd45dae0f8d4e5da72254cd","source":{"kind":"arxiv","id":"2607.18068","version":1},"attestation_state":"computed","paper":{"title":"Human Grounded Evaluation of Large Language Models for Optical Network Automation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NI","authors_text":"Carlos Natalino, Kiarash Rezaei, Omran Ayoub, Paolo Monti","submitted_at":"2026-07-20T15:36:00Z","abstract_excerpt":"Large language models (LLMs) are increasingly adopted for network automation, yet their output quality and inference cost can vary substantially across LLM families. We present HuGLEN, a stepwise evaluation pipeline that uses an LLM-as-a-judge together with a small set of expert ratings to enable scalable and reproducible comparison of candidate LLMs, and to rank them using a quality efficiency score (QES). We demonstrate HuGLEN for translating outputs from an explainable artificial intelligence (XAI) model for the optical network quality of transmission (QoT) estimation task into operator-fri"},"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":"2607.18068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2026-07-20T15:36:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4899775fe0931c002188d55fae67b8038bc4f1dd81c43c98fe6666f951944279","abstract_canon_sha256":"b6231c209142f82b3c473f671b31a23da279dd02595e78f4f4101eb1221b75d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:22:14.624975Z","signature_b64":"Gr63xoDGTSXMAM72+GR1ivrwZsOVDGKqJc46bxz7sPjhpilIOBIbmzgSTU4IHkv6hemrWh7IRP7/hIlGB7QUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"349253e74aed625a15f59918f4d67e506fc5c07a5cd45dae0f8d4e5da72254cd","last_reissued_at":"2026-07-21T02:22:14.624167Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:22:14.624167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human Grounded Evaluation of Large Language Models for Optical Network Automation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NI","authors_text":"Carlos Natalino, Kiarash Rezaei, Omran Ayoub, Paolo Monti","submitted_at":"2026-07-20T15:36:00Z","abstract_excerpt":"Large language models (LLMs) are increasingly adopted for network automation, yet their output quality and inference cost can vary substantially across LLM families. We present HuGLEN, a stepwise evaluation pipeline that uses an LLM-as-a-judge together with a small set of expert ratings to enable scalable and reproducible comparison of candidate LLMs, and to rank them using a quality efficiency score (QES). We demonstrate HuGLEN for translating outputs from an explainable artificial intelligence (XAI) model for the optical network quality of transmission (QoT) estimation task into operator-fri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18068","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/2607.18068/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":"2607.18068","created_at":"2026-07-21T02:22:14.624591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18068v1","created_at":"2026-07-21T02:22:14.624591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18068","created_at":"2026-07-21T02:22:14.624591+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSJFHZ2K5VRF","created_at":"2026-07-21T02:22:14.624591+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSJFHZ2K5VRFUFPV","created_at":"2026-07-21T02:22:14.624591+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSJFHZ2K","created_at":"2026-07-21T02:22:14.624591+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/GSJFHZ2K5VRFUFPVTEMPJVT6KB","json":"https://pith.science/pith/GSJFHZ2K5VRFUFPVTEMPJVT6KB.json","graph_json":"https://pith.science/api/pith-number/GSJFHZ2K5VRFUFPVTEMPJVT6KB/graph.json","events_json":"https://pith.science/api/pith-number/GSJFHZ2K5VRFUFPVTEMPJVT6KB/events.json","paper":"https://pith.science/paper/GSJFHZ2K"},"agent_actions":{"view_html":"https://pith.science/pith/GSJFHZ2K5VRFUFPVTEMPJVT6KB","download_json":"https://pith.science/pith/GSJFHZ2K5VRFUFPVTEMPJVT6KB.json","view_paper":"https://pith.science/paper/GSJFHZ2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18068&json=true","fetch_graph":"https://pith.science/api/pith-number/GSJFHZ2K5VRFUFPVTEMPJVT6KB/graph.json","fetch_events":"https://pith.science/api/pith-number/GSJFHZ2K5VRFUFPVTEMPJVT6KB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSJFHZ2K5VRFUFPVTEMPJVT6KB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSJFHZ2K5VRFUFPVTEMPJVT6KB/action/storage_attestation","attest_author":"https://pith.science/pith/GSJFHZ2K5VRFUFPVTEMPJVT6KB/action/author_attestation","sign_citation":"https://pith.science/pith/GSJFHZ2K5VRFUFPVTEMPJVT6KB/action/citation_signature","submit_replication":"https://pith.science/pith/GSJFHZ2K5VRFUFPVTEMPJVT6KB/action/replication_record"}},"created_at":"2026-07-21T02:22:14.624591+00:00","updated_at":"2026-07-21T02:22:14.624591+00:00"}