{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QJ5TON3Q4KJ5ZG433PZB247RWE","short_pith_number":"pith:QJ5TON3Q","schema_version":"1.0","canonical_sha256":"827b373770e293dc9b9bdbf21d73f1b101d7e7fd0fa2055d578cce0346d81588","source":{"kind":"arxiv","id":"2508.06811","version":1},"attestation_state":"computed","paper":{"title":"Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Face","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.SI","authors_text":"Benjamin Laufer, Hamidah Oderinwale, Jon Kleinberg","submitted_at":"2025-08-09T04:08:49Z","abstract_excerpt":"Many have observed that the development and deployment of generative machine learning (ML) and artificial intelligence (AI) models follow a distinctive pattern in which pre-trained models are adapted and fine-tuned for specific downstream tasks. However, there is limited empirical work that examines the structure of these interactions. This paper analyzes 1.86 million models on Hugging Face, a leading peer production platform for model development. Our study of model family trees -- networks that connect fine-tuned models to their base or parent -- reveals sprawling fine-tuning lineages that v"},"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":"2508.06811","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2025-08-09T04:08:49Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"36a050ec75af201ce7079502a599aebc74eb93cd12a026a114ffbd21a0c27eec","abstract_canon_sha256":"865ad12283d6eccc6382e7b7c77f6c9c490874448fc8d58a61b5044887a370e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:35.849977Z","signature_b64":"GZjFnu9EwAxV5aZ4RJ0AMR338eZewzqIEbQDRdl5+EJeqxg+VrzoKRHNQH7d106abObVU3pWkWJ/I2dG2scDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"827b373770e293dc9b9bdbf21d73f1b101d7e7fd0fa2055d578cce0346d81588","last_reissued_at":"2026-07-05T11:51:35.849495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:35.849495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Face","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.SI","authors_text":"Benjamin Laufer, Hamidah Oderinwale, Jon Kleinberg","submitted_at":"2025-08-09T04:08:49Z","abstract_excerpt":"Many have observed that the development and deployment of generative machine learning (ML) and artificial intelligence (AI) models follow a distinctive pattern in which pre-trained models are adapted and fine-tuned for specific downstream tasks. However, there is limited empirical work that examines the structure of these interactions. This paper analyzes 1.86 million models on Hugging Face, a leading peer production platform for model development. Our study of model family trees -- networks that connect fine-tuned models to their base or parent -- reveals sprawling fine-tuning lineages that v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06811","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/2508.06811/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":"2508.06811","created_at":"2026-07-05T11:51:35.849555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06811v1","created_at":"2026-07-05T11:51:35.849555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06811","created_at":"2026-07-05T11:51:35.849555+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJ5TON3Q4KJ5","created_at":"2026-07-05T11:51:35.849555+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJ5TON3Q4KJ5ZG43","created_at":"2026-07-05T11:51:35.849555+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJ5TON3Q","created_at":"2026-07-05T11:51:35.849555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21787","citing_title":"Towards Imputation of Pre-Trained Language Model Metadata using Semantic Fingerprinting","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16902","citing_title":"ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2510.06989","citing_title":"Human-aligned AI Model Cards with Weighted Hierarchy Architecture","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20251","citing_title":"Efficient Evaluation of LLM Performance with Statistical Guarantees","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09617","citing_title":"AdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24902","citing_title":"Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05782","citing_title":"When Models Meet Users: An Empirical Study of Perceptions of General LLMs and Multimodal LLMs on Hugging Face","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QJ5TON3Q4KJ5ZG433PZB247RWE","json":"https://pith.science/pith/QJ5TON3Q4KJ5ZG433PZB247RWE.json","graph_json":"https://pith.science/api/pith-number/QJ5TON3Q4KJ5ZG433PZB247RWE/graph.json","events_json":"https://pith.science/api/pith-number/QJ5TON3Q4KJ5ZG433PZB247RWE/events.json","paper":"https://pith.science/paper/QJ5TON3Q"},"agent_actions":{"view_html":"https://pith.science/pith/QJ5TON3Q4KJ5ZG433PZB247RWE","download_json":"https://pith.science/pith/QJ5TON3Q4KJ5ZG433PZB247RWE.json","view_paper":"https://pith.science/paper/QJ5TON3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06811&json=true","fetch_graph":"https://pith.science/api/pith-number/QJ5TON3Q4KJ5ZG433PZB247RWE/graph.json","fetch_events":"https://pith.science/api/pith-number/QJ5TON3Q4KJ5ZG433PZB247RWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJ5TON3Q4KJ5ZG433PZB247RWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJ5TON3Q4KJ5ZG433PZB247RWE/action/storage_attestation","attest_author":"https://pith.science/pith/QJ5TON3Q4KJ5ZG433PZB247RWE/action/author_attestation","sign_citation":"https://pith.science/pith/QJ5TON3Q4KJ5ZG433PZB247RWE/action/citation_signature","submit_replication":"https://pith.science/pith/QJ5TON3Q4KJ5ZG433PZB247RWE/action/replication_record"}},"created_at":"2026-07-05T11:51:35.849555+00:00","updated_at":"2026-07-05T11:51:35.849555+00:00"}