{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MJF7K2VGV6HSC2MYIB7G34FJ7A","short_pith_number":"pith:MJF7K2VG","schema_version":"1.0","canonical_sha256":"624bf56aa6af8f216998407e6df0a9f82fae250dd4ea31e88304c342d4ebe172","source":{"kind":"arxiv","id":"2502.16069","version":2},"attestation_state":"computed","paper":{"title":"Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ang Chen, Jayanth Srinivasa, Jiachen Liu, Mosharaf Chowdhury, Myungjin Lee, Patrick Tser Jern Kon, Qiuyi Ding, Yibo Huang, Yiming Qiu, Zhenning Yang","submitted_at":"2025-02-22T03:58:19Z","abstract_excerpt":"Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing capabilities of large language models (LLMs) in automating different aspects of the scientific process, automating rigorous experimentation remains a significant challenge. To address this gap, we propose Curie, an AI agent framework designed to embed rigor into the experimentation process through three key components: an intra-agent rigor module to enhance reliability, an inter-agent rigor module to maintain method"},"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":"2502.16069","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-22T03:58:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d19752cdaa341625218059ffca4139f541ccbb927a1a0b50a1ac06c03e27db0c","abstract_canon_sha256":"edaf0e65c16f09450d1982cfbb9e8836431a37c87c4eecac9a9ca455c4510ac4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:57.952911Z","signature_b64":"M1f7Y1EU57tD1h1rwc40hxUFdUtiP3HX/YmLak3wuvJB6te7ytNZkK4wOeHhR2lFC3UJkTIdM7Pd2p9v//4jAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"624bf56aa6af8f216998407e6df0a9f82fae250dd4ea31e88304c342d4ebe172","last_reissued_at":"2026-07-05T10:19:57.952434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:57.952434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ang Chen, Jayanth Srinivasa, Jiachen Liu, Mosharaf Chowdhury, Myungjin Lee, Patrick Tser Jern Kon, Qiuyi Ding, Yibo Huang, Yiming Qiu, Zhenning Yang","submitted_at":"2025-02-22T03:58:19Z","abstract_excerpt":"Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing capabilities of large language models (LLMs) in automating different aspects of the scientific process, automating rigorous experimentation remains a significant challenge. To address this gap, we propose Curie, an AI agent framework designed to embed rigor into the experimentation process through three key components: an intra-agent rigor module to enhance reliability, an inter-agent rigor module to maintain method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16069","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/2502.16069/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":"2502.16069","created_at":"2026-07-05T10:19:57.952489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16069v2","created_at":"2026-07-05T10:19:57.952489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16069","created_at":"2026-07-05T10:19:57.952489+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJF7K2VGV6HS","created_at":"2026-07-05T10:19:57.952489+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJF7K2VGV6HSC2MY","created_at":"2026-07-05T10:19:57.952489+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJF7K2VG","created_at":"2026-07-05T10:19:57.952489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20394","citing_title":"Agentic AutoResearch forSpace Autonomy: An Auditable, LLM-Driven Research Agent for Aerospace Control Problems","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04505","citing_title":"Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision Making","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26340","citing_title":"ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23204","citing_title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":267,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04375","citing_title":"Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16616","citing_title":"MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2506.22598","citing_title":"RExBench: Can coding agents autonomously implement AI research extensions?","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10224","citing_title":"Hypothesis-Driven Deep Research with Large Language Models: A Structured Methodology for Automated Knowledge Discovery","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04375","citing_title":"Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery","ref_index":87,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MJF7K2VGV6HSC2MYIB7G34FJ7A","json":"https://pith.science/pith/MJF7K2VGV6HSC2MYIB7G34FJ7A.json","graph_json":"https://pith.science/api/pith-number/MJF7K2VGV6HSC2MYIB7G34FJ7A/graph.json","events_json":"https://pith.science/api/pith-number/MJF7K2VGV6HSC2MYIB7G34FJ7A/events.json","paper":"https://pith.science/paper/MJF7K2VG"},"agent_actions":{"view_html":"https://pith.science/pith/MJF7K2VGV6HSC2MYIB7G34FJ7A","download_json":"https://pith.science/pith/MJF7K2VGV6HSC2MYIB7G34FJ7A.json","view_paper":"https://pith.science/paper/MJF7K2VG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16069&json=true","fetch_graph":"https://pith.science/api/pith-number/MJF7K2VGV6HSC2MYIB7G34FJ7A/graph.json","fetch_events":"https://pith.science/api/pith-number/MJF7K2VGV6HSC2MYIB7G34FJ7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJF7K2VGV6HSC2MYIB7G34FJ7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJF7K2VGV6HSC2MYIB7G34FJ7A/action/storage_attestation","attest_author":"https://pith.science/pith/MJF7K2VGV6HSC2MYIB7G34FJ7A/action/author_attestation","sign_citation":"https://pith.science/pith/MJF7K2VGV6HSC2MYIB7G34FJ7A/action/citation_signature","submit_replication":"https://pith.science/pith/MJF7K2VGV6HSC2MYIB7G34FJ7A/action/replication_record"}},"created_at":"2026-07-05T10:19:57.952489+00:00","updated_at":"2026-07-05T10:19:57.952489+00:00"}