{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S6LTEQWPZ3A2UF7IRCIBPQJZM7","short_pith_number":"pith:S6LTEQWP","schema_version":"1.0","canonical_sha256":"97973242cfcec1aa17e8889017c13967ee683fdb9e4e4095b33f388a53bdcd62","source":{"kind":"arxiv","id":"2310.04353","version":5},"attestation_state":"computed","paper":{"title":"An In-Context Learning Agent for Formal Theorem-Proving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LO","cs.PL"],"primary_cat":"cs.LG","authors_text":"Amitayush Thakur, George Tsoukalas, Jimmy Xin, Swarat Chaudhuri, Yeming Wen","submitted_at":"2023-10-06T16:21:22Z","abstract_excerpt":"We present an in-context learning agent for formal theorem-proving in environments like Lean and Coq. Current state-of-the-art models for the problem are finetuned on environment-specific proof data. By contrast, our approach, called COPRA, repeatedly asks a high-capacity, general-purpose large language model (GPT-4) to propose tactic applications from within a stateful backtracking search. Proposed tactics are executed in the underlying proof environment. Feedback from the execution is used to build the prompt for the next model query, along with selected information from the search history a"},"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":"2310.04353","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T16:21:22Z","cross_cats_sorted":["cs.AI","cs.LO","cs.PL"],"title_canon_sha256":"7217c615a8969fa725a2b230a1df438f912ffbe4b8066b9269468ead1aead6ca","abstract_canon_sha256":"3be3b8fe34c98a5d03e71f2dc00ca7d5b4d84831efd81b48bff5e25e9fce5e95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:17.481640Z","signature_b64":"oAFvEFJNT/9jCXn0B6l79KZcWYSmwGcY5eGiQuhIJ3dTCgF+rJKS0nagQxUiw+UtP8j+ooPU5VcSUatJ5/BfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97973242cfcec1aa17e8889017c13967ee683fdb9e4e4095b33f388a53bdcd62","last_reissued_at":"2026-07-05T08:53:17.481115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:17.481115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An In-Context Learning Agent for Formal Theorem-Proving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LO","cs.PL"],"primary_cat":"cs.LG","authors_text":"Amitayush Thakur, George Tsoukalas, Jimmy Xin, Swarat Chaudhuri, Yeming Wen","submitted_at":"2023-10-06T16:21:22Z","abstract_excerpt":"We present an in-context learning agent for formal theorem-proving in environments like Lean and Coq. Current state-of-the-art models for the problem are finetuned on environment-specific proof data. By contrast, our approach, called COPRA, repeatedly asks a high-capacity, general-purpose large language model (GPT-4) to propose tactic applications from within a stateful backtracking search. Proposed tactics are executed in the underlying proof environment. Feedback from the execution is used to build the prompt for the next model query, along with selected information from the search history a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04353","kind":"arxiv","version":5},"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/2310.04353/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":"2310.04353","created_at":"2026-07-05T08:53:17.481179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04353v5","created_at":"2026-07-05T08:53:17.481179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04353","created_at":"2026-07-05T08:53:17.481179+00:00"},{"alias_kind":"pith_short_12","alias_value":"S6LTEQWPZ3A2","created_at":"2026-07-05T08:53:17.481179+00:00"},{"alias_kind":"pith_short_16","alias_value":"S6LTEQWPZ3A2UF7I","created_at":"2026-07-05T08:53:17.481179+00:00"},{"alias_kind":"pith_short_8","alias_value":"S6LTEQWP","created_at":"2026-07-05T08:53:17.481179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26442","citing_title":"AXLE: A Cloud Infrastructure for Lean 4 Theorem Proving Utilities","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09450","citing_title":"TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27485","citing_title":"Automating Formal Verification with Agent-Guided Tree Search","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30914","citing_title":"Automating Formal Verification with Reinforcement Learning and Recursive Inference","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23109","citing_title":"Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23772","citing_title":"Agentic Proving for Program Verification","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2403.17134","citing_title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14274","citing_title":"Discovering New Theorems via LLMs with In-Context Proof Learning in Lean","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2602.24273","citing_title":"A Minimal Agent for Automated Theorem Proving","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05820","citing_title":"SpecRL: Reinforcement Learning with Test-Based Completeness Rewards for Formal Specification Synthesis","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S6LTEQWPZ3A2UF7IRCIBPQJZM7","json":"https://pith.science/pith/S6LTEQWPZ3A2UF7IRCIBPQJZM7.json","graph_json":"https://pith.science/api/pith-number/S6LTEQWPZ3A2UF7IRCIBPQJZM7/graph.json","events_json":"https://pith.science/api/pith-number/S6LTEQWPZ3A2UF7IRCIBPQJZM7/events.json","paper":"https://pith.science/paper/S6LTEQWP"},"agent_actions":{"view_html":"https://pith.science/pith/S6LTEQWPZ3A2UF7IRCIBPQJZM7","download_json":"https://pith.science/pith/S6LTEQWPZ3A2UF7IRCIBPQJZM7.json","view_paper":"https://pith.science/paper/S6LTEQWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04353&json=true","fetch_graph":"https://pith.science/api/pith-number/S6LTEQWPZ3A2UF7IRCIBPQJZM7/graph.json","fetch_events":"https://pith.science/api/pith-number/S6LTEQWPZ3A2UF7IRCIBPQJZM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S6LTEQWPZ3A2UF7IRCIBPQJZM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S6LTEQWPZ3A2UF7IRCIBPQJZM7/action/storage_attestation","attest_author":"https://pith.science/pith/S6LTEQWPZ3A2UF7IRCIBPQJZM7/action/author_attestation","sign_citation":"https://pith.science/pith/S6LTEQWPZ3A2UF7IRCIBPQJZM7/action/citation_signature","submit_replication":"https://pith.science/pith/S6LTEQWPZ3A2UF7IRCIBPQJZM7/action/replication_record"}},"created_at":"2026-07-05T08:53:17.481179+00:00","updated_at":"2026-07-05T08:53:17.481179+00:00"}