{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CK77J6CVPFWHZU4WIC6Z6NTXIZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7876b58733134eda9a645d6306e3207c9a5b992acd3012f746c1bfa68f6d9dbe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-27T18:43:47Z","title_canon_sha256":"4138a86950985f0b6156a71c8745ff86b466186134f13555f49ea92369a7906b"},"schema_version":"1.0","source":{"id":"2602.24273","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.24273","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2602.24273v3","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.24273","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"CK77J6CVPFWH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CK77J6CVPFWHZU4W","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CK77J6CV","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:1569320e1007a40db997ddba81d3812edc06207c0ef03c67f9ce3e5be6e33935","target":"graph","created_at":"2026-05-17T23:38:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our results show competitive performance compared to state-of-the-art approaches, while using a significantly simpler architecture and a fraction of their cost."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the implemented core features (iterative refinement, library search, context management) are sufficient to achieve competitive results across qualitatively different benchmarks without additional specialized components."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A minimal agentic system achieves competitive performance in automated theorem proving with a simpler design and lower cost than state-of-the-art methods."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A minimal agent achieves competitive theorem proving performance with iterative refinement, library search, and context management at a fraction of state-of-the-art costs."}],"snapshot_sha256":"a070584c0bf235ee5b0450a0a6c8e2e300e881abd9aadeae6e29a29b3667385a"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We propose a minimal agentic baseline that enables systematic comparison across different AI-based theorem prover architectures. This design implements the core features shared among state-of-the-art systems: iterative proof refinement, library search and context management. We evaluate this agentic approach using qualitatively different benchmarks and compare various frontier language models and design choices. Our results show competitive performance compared to state-of-the-art approaches, while using a significantly simpler architecture and a fraction of their cost. Additionally, we demons","authors_text":"Austin Letson, Borja Requena, Izan Beltran-Ferreiro, Krystian Nowakowski, Leopoldo Sarra","cross_cats":[],"headline":"A minimal agent achieves competitive theorem proving performance with iterative refinement, library search, and context management at a fraction of state-of-the-art costs.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-27T18:43:47Z","title":"A Minimal Agent for Automated Theorem Proving"},"references":{"count":87,"internal_anchors":9,"resolved_work":87,"sample":[{"cited_arxiv_id":"","doi":"10.1007/978-3-030-","is_internal_anchor":false,"ref_index":1,"title":"Davis, Guillaume Baudart, and Louis Mandel","work_id":"138a89bd-9857-4e55-a915-ff4f36d70e77","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Lars Becker et al.A blueprint for the formalization of Carleson’s theorem on convergence of Fourier series. 2025. arXiv:2405.06423 [math.CA] .url: https://arxiv.org/abs/ 2405.06423","work_id":"9c02fca6-ca63-4f28-9c34-5e958f6f90ce","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Ben Cottier, Ben Snodin, David Owen, and Tom Adamczewski","work_id":"cf9d574b-6923-4156-bebb-a360e7337507","year":2023},{"cited_arxiv_id":"","doi":"10.1038/s41586-025-09833-y","is_internal_anchor":false,"ref_index":4,"title":"Olympiad-level formal mathematical reasoning with reinforcement learning.Nature","work_id":"7185d70a-ddd1-45ed-bbec-e728c41ebf52","year":2025},{"cited_arxiv_id":"2510.01346","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Aristotle: IMO-level Automated Theorem Proving","work_id":"6c61af2f-a34a-4647-9111-6ba5a60f6bc2","year":2025}],"snapshot_sha256":"a2d47502d30914960a6241c805b9a2a35ef04c160f3132eaf6023fa9d0ae4dec"},"source":{"id":"2602.24273","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T18:42:05.188965Z","id":"77bd93ac-7bcb-4c8a-8232-531d8eec972d","model_set":{"reader":"grok-4.3"},"one_line_summary":"A minimal agentic system achieves competitive performance in automated theorem proving with a simpler design and lower cost than state-of-the-art methods.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A minimal agent achieves competitive theorem proving performance with iterative refinement, library search, and context management at a fraction of state-of-the-art costs.","strongest_claim":"Our results show competitive performance compared to state-of-the-art approaches, while using a significantly simpler architecture and a fraction of their cost.","weakest_assumption":"The assumption that the implemented core features (iterative refinement, library search, context management) are sufficient to achieve competitive results across qualitatively different benchmarks without additional specialized components."}},"verdict_id":"77bd93ac-7bcb-4c8a-8232-531d8eec972d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9713cd69b48fd3afd345f1a1575e69a7a9df14dae062f809ee39216401c0c998","target":"record","created_at":"2026-05-17T23:38:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7876b58733134eda9a645d6306e3207c9a5b992acd3012f746c1bfa68f6d9dbe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-27T18:43:47Z","title_canon_sha256":"4138a86950985f0b6156a71c8745ff86b466186134f13555f49ea92369a7906b"},"schema_version":"1.0","source":{"id":"2602.24273","kind":"arxiv","version":3}},"canonical_sha256":"12bff4f855796c7cd39640bd9f367746740a481eda51a50f6c8e92284971e060","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12bff4f855796c7cd39640bd9f367746740a481eda51a50f6c8e92284971e060","first_computed_at":"2026-05-17T23:38:59.857492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:59.857492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ll+uuqq2/dBZtl+lnCvOy8FOI6lVIif74N/CFUbhzT3bpV8drt9S4WFZHP6jFjPEJd7X4RubpTggXLDtm1lAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:59.858270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.24273","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9713cd69b48fd3afd345f1a1575e69a7a9df14dae062f809ee39216401c0c998","sha256:1569320e1007a40db997ddba81d3812edc06207c0ef03c67f9ce3e5be6e33935"],"state_sha256":"d673d6f79ed16355393899460e4cf61b5f2171a0a73e50e7925acb70d7208ae6"}