{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KB53D5O3QT5ZZEP3VYQMI3L6I6","short_pith_number":"pith:KB53D5O3","schema_version":"1.0","canonical_sha256":"507bb1f5db84fb9c91fbae20c46d7e47b754bfe13b020267208c8dd80fd510e3","source":{"kind":"arxiv","id":"2506.14529","version":1},"attestation_state":"computed","paper":{"title":"Automated Decision-Making on Networks with LLMs through Knowledge-Guided Evolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lanning Wei, Quanming Yao, Xiaohan Zheng, Yong Li","submitted_at":"2025-06-17T13:53:48Z","abstract_excerpt":"Effective decision-making on networks often relies on learning from graph-structured data, where Graph Neural Networks (GNNs) play a central role, but they take efforts to configure and tune. In this demo, we propose LLMNet, showing how to design GNN automated through Large Language Models. Our system develops a set of agents that construct graph-related knowlege bases and then leverages Retrieval-Augmented Generation (RAG) to support automated configuration and refinement of GNN models through a knowledge-guided evolution process. These agents, equipped with specialized knowledge bases, extra"},"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":"2506.14529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T13:53:48Z","cross_cats_sorted":[],"title_canon_sha256":"c4cc70a3ff40411d2dc2916ec1c74d9a1f5a9d60ec5f52ac8801c65758f1a94e","abstract_canon_sha256":"64be4d5c3f3ed88e7f9d2b5686c8a6e5d6099c872f84438b2564ca8b13ba7498"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:58.236192Z","signature_b64":"Gzy/FOKE818mqsRzMSzp6h9dcyMlUKJwlAmMzC1WhNFzzTvFtvDOszoWGomAuri5/544TYdN5wixMV9x5B5bAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"507bb1f5db84fb9c91fbae20c46d7e47b754bfe13b020267208c8dd80fd510e3","last_reissued_at":"2026-07-05T11:22:58.235686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:58.235686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Decision-Making on Networks with LLMs through Knowledge-Guided Evolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lanning Wei, Quanming Yao, Xiaohan Zheng, Yong Li","submitted_at":"2025-06-17T13:53:48Z","abstract_excerpt":"Effective decision-making on networks often relies on learning from graph-structured data, where Graph Neural Networks (GNNs) play a central role, but they take efforts to configure and tune. In this demo, we propose LLMNet, showing how to design GNN automated through Large Language Models. Our system develops a set of agents that construct graph-related knowlege bases and then leverages Retrieval-Augmented Generation (RAG) to support automated configuration and refinement of GNN models through a knowledge-guided evolution process. These agents, equipped with specialized knowledge bases, extra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14529","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/2506.14529/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":"2506.14529","created_at":"2026-07-05T11:22:58.235752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14529v1","created_at":"2026-07-05T11:22:58.235752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14529","created_at":"2026-07-05T11:22:58.235752+00:00"},{"alias_kind":"pith_short_12","alias_value":"KB53D5O3QT5Z","created_at":"2026-07-05T11:22:58.235752+00:00"},{"alias_kind":"pith_short_16","alias_value":"KB53D5O3QT5ZZEP3","created_at":"2026-07-05T11:22:58.235752+00:00"},{"alias_kind":"pith_short_8","alias_value":"KB53D5O3","created_at":"2026-07-05T11:22:58.235752+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/KB53D5O3QT5ZZEP3VYQMI3L6I6","json":"https://pith.science/pith/KB53D5O3QT5ZZEP3VYQMI3L6I6.json","graph_json":"https://pith.science/api/pith-number/KB53D5O3QT5ZZEP3VYQMI3L6I6/graph.json","events_json":"https://pith.science/api/pith-number/KB53D5O3QT5ZZEP3VYQMI3L6I6/events.json","paper":"https://pith.science/paper/KB53D5O3"},"agent_actions":{"view_html":"https://pith.science/pith/KB53D5O3QT5ZZEP3VYQMI3L6I6","download_json":"https://pith.science/pith/KB53D5O3QT5ZZEP3VYQMI3L6I6.json","view_paper":"https://pith.science/paper/KB53D5O3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14529&json=true","fetch_graph":"https://pith.science/api/pith-number/KB53D5O3QT5ZZEP3VYQMI3L6I6/graph.json","fetch_events":"https://pith.science/api/pith-number/KB53D5O3QT5ZZEP3VYQMI3L6I6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KB53D5O3QT5ZZEP3VYQMI3L6I6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KB53D5O3QT5ZZEP3VYQMI3L6I6/action/storage_attestation","attest_author":"https://pith.science/pith/KB53D5O3QT5ZZEP3VYQMI3L6I6/action/author_attestation","sign_citation":"https://pith.science/pith/KB53D5O3QT5ZZEP3VYQMI3L6I6/action/citation_signature","submit_replication":"https://pith.science/pith/KB53D5O3QT5ZZEP3VYQMI3L6I6/action/replication_record"}},"created_at":"2026-07-05T11:22:58.235752+00:00","updated_at":"2026-07-05T11:22:58.235752+00:00"}