{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P4T6F56TZ6O56XCHBPRDVYNB6F","short_pith_number":"pith:P4T6F56T","schema_version":"1.0","canonical_sha256":"7f27e2f7d3cf9ddf5c470be23ae1a1f172cefe798f89aabf98ca5f7d43f96ca8","source":{"kind":"arxiv","id":"2402.17879","version":2},"attestation_state":"computed","paper":{"title":"Automated Statistical Model Discovery with Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Emily B. Fox, Michael Y. Li, Noah D. Goodman","submitted_at":"2024-02-27T20:33:22Z","abstract_excerpt":"Statistical model discovery is a challenging search over a vast space of models subject to domain-specific constraints. Efficiently searching over this space requires expertise in modeling and the problem domain. Motivated by the domain knowledge and programming capabilities of large language models (LMs), we introduce a method for language model driven automated statistical model discovery. We cast our automated procedure within the principled framework of Box's Loop: the LM iterates between proposing statistical models represented as probabilistic programs, acting as a modeler, and critiquin"},"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":"2402.17879","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T20:33:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"23d0e26c295e8cdd03b05458351998f894ff4d563d4d2c5b5361172d1b28538f","abstract_canon_sha256":"b025c169096450bb7037649dba7d9fc78320f43f1cee0f21fdad94972eeed744"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:19.432024Z","signature_b64":"2Jtccjv0go3N2nP41q0ueMCql2U6AniWU6tpVNGzriBt5LA6Y+ESuSa//rLlEt7+YnkPk6+uUXlPLZcfkgR3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f27e2f7d3cf9ddf5c470be23ae1a1f172cefe798f89aabf98ca5f7d43f96ca8","last_reissued_at":"2026-07-05T08:35:19.431610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:19.431610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Statistical Model Discovery with Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Emily B. Fox, Michael Y. Li, Noah D. Goodman","submitted_at":"2024-02-27T20:33:22Z","abstract_excerpt":"Statistical model discovery is a challenging search over a vast space of models subject to domain-specific constraints. Efficiently searching over this space requires expertise in modeling and the problem domain. Motivated by the domain knowledge and programming capabilities of large language models (LMs), we introduce a method for language model driven automated statistical model discovery. We cast our automated procedure within the principled framework of Box's Loop: the LM iterates between proposing statistical models represented as probabilistic programs, acting as a modeler, and critiquin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17879","kind":"arxiv","version":2},"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/2402.17879/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":"2402.17879","created_at":"2026-07-05T08:35:19.431665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17879v2","created_at":"2026-07-05T08:35:19.431665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17879","created_at":"2026-07-05T08:35:19.431665+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4T6F56TZ6O5","created_at":"2026-07-05T08:35:19.431665+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4T6F56TZ6O56XCH","created_at":"2026-07-05T08:35:19.431665+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4T6F56T","created_at":"2026-07-05T08:35:19.431665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25923","citing_title":"$\\text{DT}^2$: Decision-Targeted Digital Twins","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00384","citing_title":"VESTA: Visual Exploration with Statistical Tool Agents","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27386","citing_title":"Agentic Publication Protocol: An Attempt to Modernize Scientific Publication","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17790","citing_title":"STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2509.01082","citing_title":"RefineStat: Efficient Exploration for Probabilistic Program Synthesis","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14718","citing_title":"The Agentification of Scientific Research: A Physicist's Perspective","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4T6F56TZ6O56XCHBPRDVYNB6F","json":"https://pith.science/pith/P4T6F56TZ6O56XCHBPRDVYNB6F.json","graph_json":"https://pith.science/api/pith-number/P4T6F56TZ6O56XCHBPRDVYNB6F/graph.json","events_json":"https://pith.science/api/pith-number/P4T6F56TZ6O56XCHBPRDVYNB6F/events.json","paper":"https://pith.science/paper/P4T6F56T"},"agent_actions":{"view_html":"https://pith.science/pith/P4T6F56TZ6O56XCHBPRDVYNB6F","download_json":"https://pith.science/pith/P4T6F56TZ6O56XCHBPRDVYNB6F.json","view_paper":"https://pith.science/paper/P4T6F56T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17879&json=true","fetch_graph":"https://pith.science/api/pith-number/P4T6F56TZ6O56XCHBPRDVYNB6F/graph.json","fetch_events":"https://pith.science/api/pith-number/P4T6F56TZ6O56XCHBPRDVYNB6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4T6F56TZ6O56XCHBPRDVYNB6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4T6F56TZ6O56XCHBPRDVYNB6F/action/storage_attestation","attest_author":"https://pith.science/pith/P4T6F56TZ6O56XCHBPRDVYNB6F/action/author_attestation","sign_citation":"https://pith.science/pith/P4T6F56TZ6O56XCHBPRDVYNB6F/action/citation_signature","submit_replication":"https://pith.science/pith/P4T6F56TZ6O56XCHBPRDVYNB6F/action/replication_record"}},"created_at":"2026-07-05T08:35:19.431665+00:00","updated_at":"2026-07-05T08:35:19.431665+00:00"}