{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MNCYARR5KCJYSZHPE5KERYACJT","short_pith_number":"pith:MNCYARR5","schema_version":"1.0","canonical_sha256":"634580463d50938964ef275448e0024cd88100a3b6ac5b085f548828f5f7408b","source":{"kind":"arxiv","id":"2511.20333","version":1},"attestation_state":"computed","paper":{"title":"NNGPT: Rethinking AutoML with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Avi Goyal, Chandini Vysyaraju, Dmitry Ignatov, Furui Qin, Radu Timofte, Raghuvir Duvvuri, Roman Kochnev, Tolgay Atinc Uzun, Waleed Khalid, Xi Zhang, Yashkumar Sanjaybhai Dhameliya","submitted_at":"2025-11-25T14:10:44Z","abstract_excerpt":"Building self-improving AI systems remains a fundamental challenge in the AI domain. We present NNGPT, an open-source framework that turns a large language model (LLM) into a self-improving AutoML engine for neural network development, primarily for computer vision. Unlike previous frameworks, NNGPT extends the dataset of neural networks by generating new models, enabling continuous fine-tuning of LLMs based on closed-loop system of generation, assessment, and self-improvement. It integrates within one unified workflow five synergistic LLM-based pipelines: zero-shot architecture synthesis, hyp"},"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":"2511.20333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-11-25T14:10:44Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"4f0e2169cd488003bf8822026b9da505ec5f8a5908e856920708eba3c8557ca0","abstract_canon_sha256":"f1c57973e12454982eed1fd3af72a65cfa3afd47d722d80d17d77b7db55e3a41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:11.422180Z","signature_b64":"CXNb3+Rqb5F04tIwaOUwXypRX7VYDmbAE2vktksYrdeXP9GzVXSRMyafm3A3ba2rNJmOQXai70kuXDvaM/XMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"634580463d50938964ef275448e0024cd88100a3b6ac5b085f548828f5f7408b","last_reissued_at":"2026-06-02T02:04:11.421681Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:11.421681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NNGPT: Rethinking AutoML with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Avi Goyal, Chandini Vysyaraju, Dmitry Ignatov, Furui Qin, Radu Timofte, Raghuvir Duvvuri, Roman Kochnev, Tolgay Atinc Uzun, Waleed Khalid, Xi Zhang, Yashkumar Sanjaybhai Dhameliya","submitted_at":"2025-11-25T14:10:44Z","abstract_excerpt":"Building self-improving AI systems remains a fundamental challenge in the AI domain. We present NNGPT, an open-source framework that turns a large language model (LLM) into a self-improving AutoML engine for neural network development, primarily for computer vision. Unlike previous frameworks, NNGPT extends the dataset of neural networks by generating new models, enabling continuous fine-tuning of LLMs based on closed-loop system of generation, assessment, and self-improvement. It integrates within one unified workflow five synergistic LLM-based pipelines: zero-shot architecture synthesis, hyp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.20333","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/2511.20333/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":"2511.20333","created_at":"2026-06-02T02:04:11.421733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.20333v1","created_at":"2026-06-02T02:04:11.421733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.20333","created_at":"2026-06-02T02:04:11.421733+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNCYARR5KCJY","created_at":"2026-06-02T02:04:11.421733+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNCYARR5KCJYSZHP","created_at":"2026-06-02T02:04:11.421733+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNCYARR5","created_at":"2026-06-02T02:04:11.421733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2511.07329","citing_title":"Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2511.07329","citing_title":"Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2512.24120","citing_title":"Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNCYARR5KCJYSZHPE5KERYACJT","json":"https://pith.science/pith/MNCYARR5KCJYSZHPE5KERYACJT.json","graph_json":"https://pith.science/api/pith-number/MNCYARR5KCJYSZHPE5KERYACJT/graph.json","events_json":"https://pith.science/api/pith-number/MNCYARR5KCJYSZHPE5KERYACJT/events.json","paper":"https://pith.science/paper/MNCYARR5"},"agent_actions":{"view_html":"https://pith.science/pith/MNCYARR5KCJYSZHPE5KERYACJT","download_json":"https://pith.science/pith/MNCYARR5KCJYSZHPE5KERYACJT.json","view_paper":"https://pith.science/paper/MNCYARR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.20333&json=true","fetch_graph":"https://pith.science/api/pith-number/MNCYARR5KCJYSZHPE5KERYACJT/graph.json","fetch_events":"https://pith.science/api/pith-number/MNCYARR5KCJYSZHPE5KERYACJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNCYARR5KCJYSZHPE5KERYACJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNCYARR5KCJYSZHPE5KERYACJT/action/storage_attestation","attest_author":"https://pith.science/pith/MNCYARR5KCJYSZHPE5KERYACJT/action/author_attestation","sign_citation":"https://pith.science/pith/MNCYARR5KCJYSZHPE5KERYACJT/action/citation_signature","submit_replication":"https://pith.science/pith/MNCYARR5KCJYSZHPE5KERYACJT/action/replication_record"}},"created_at":"2026-06-02T02:04:11.421733+00:00","updated_at":"2026-06-02T02:04:11.421733+00:00"}