{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FEFCKLZGABKRAX2HGJ44YGFBRU","short_pith_number":"pith:FEFCKLZG","schema_version":"1.0","canonical_sha256":"290a252f260055105f473279cc18a18d1d1fd37e4837aba2c7f71af68a4d0fcf","source":{"kind":"arxiv","id":"2604.18587","version":2},"attestation_state":"computed","paper":{"title":"Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Compiler outputs compress diverse proof attempts into a compact set of failure modes that support local corrections and stronger theorem proving.","cross_cats":["cs.AI","cs.LO","cs.PL"],"primary_cat":"cs.LG","authors_text":"Guchan Li, Hongning Wang, Rui Tian","submitted_at":"2026-03-13T01:33:20Z","abstract_excerpt":"Large language models (LLMs) have demonstrated significant potential in formal theorem proving, yet state-of-the-art performance often necessitates prohibitive test-time compute via massive roll-outs or extended context windows. In this work, we address this scalability bottleneck by exploiting an informative structure in formal verification: the observation that compilers map a vast space of diverse proof attempts to a compact set of structured failure modes. We introduce a learning-to-refine framework that leverages this compression to perform efficient learning and proof exploration. We per"},"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":true},"canonical_record":{"source":{"id":"2604.18587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-13T01:33:20Z","cross_cats_sorted":["cs.AI","cs.LO","cs.PL"],"title_canon_sha256":"ed92ff7aced7b8c2167c2107450b9ab358e55d03810b1e0afed5054742d303a3","abstract_canon_sha256":"c5909645f5415efa6036b7716f8c17048252c3fd4b6a74a85885aa05b2f1e5e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:53.424192Z","signature_b64":"bH+82tqJijbzDmlYVJ+Fas5aJxSlhBTFKq1U5wMDgTMwgQELNNnpavmlW1mYgqHZZ+JfGGmVlgOBfqKeqLsJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"290a252f260055105f473279cc18a18d1d1fd37e4837aba2c7f71af68a4d0fcf","last_reissued_at":"2026-06-01T01:03:53.423143Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:53.423143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Compiler outputs compress diverse proof attempts into a compact set of failure modes that support local corrections and stronger theorem proving.","cross_cats":["cs.AI","cs.LO","cs.PL"],"primary_cat":"cs.LG","authors_text":"Guchan Li, Hongning Wang, Rui Tian","submitted_at":"2026-03-13T01:33:20Z","abstract_excerpt":"Large language models (LLMs) have demonstrated significant potential in formal theorem proving, yet state-of-the-art performance often necessitates prohibitive test-time compute via massive roll-outs or extended context windows. In this work, we address this scalability bottleneck by exploiting an informative structure in formal verification: the observation that compilers map a vast space of diverse proof attempts to a compact set of structured failure modes. We introduce a learning-to-refine framework that leverages this compression to perform efficient learning and proof exploration. We per"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our approach achieves state-of-the-art performance on PutnamBench among publicly reported ∼8B and ∼32B parameter models under comparable test-time budgets","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"that compilers map a vast space of diverse proof attempts to a compact set of structured failure modes that can be leveraged for efficient learning and proof exploration without accumulating long histories of attempts","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Compiler feedback compresses diverse proof attempts into structured failure modes for efficient local refinement, boosting LLM-based theorem provers to SOTA on PutnamBench for 8B and 32B models under fixed test-time budgets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Compiler outputs compress diverse proof attempts into a compact set of failure modes that support local corrections and stronger theorem proving.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9d8a70447989471a8167eb3fd4526f32fea3ebd23c3453067172bfec1ca0fe9b"},"source":{"id":"2604.18587","kind":"arxiv","version":2},"verdict":{"id":"751764c0-9b85-496d-adc3-362d9d142c74","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T12:38:53.288785Z","strongest_claim":"our approach achieves state-of-the-art performance on PutnamBench among publicly reported ∼8B and ∼32B parameter models under comparable test-time budgets","one_line_summary":"Compiler feedback compresses diverse proof attempts into structured failure modes for efficient local refinement, boosting LLM-based theorem provers to SOTA on PutnamBench for 8B and 32B models under fixed test-time budgets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"that compilers map a vast space of diverse proof attempts to a compact set of structured failure modes that can be leveraged for efficient learning and proof exploration without accumulating long histories of attempts","pith_extraction_headline":"Compiler outputs compress diverse proof attempts into a compact set of failure modes that support local corrections and stronger theorem proving."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.18587/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":2,"snapshot_sha256":"3d67ba3a59f67d66b04218410b8324c85731d1a39d5919baadd0d43e80e5c0c2"},"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":"2604.18587","created_at":"2026-06-01T01:03:53.423339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.18587v2","created_at":"2026-06-01T01:03:53.423339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18587","created_at":"2026-06-01T01:03:53.423339+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEFCKLZGABKR","created_at":"2026-06-01T01:03:53.423339+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEFCKLZGABKRAX2H","created_at":"2026-06-01T01:03:53.423339+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEFCKLZG","created_at":"2026-06-01T01:03:53.423339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEFCKLZGABKRAX2HGJ44YGFBRU","json":"https://pith.science/pith/FEFCKLZGABKRAX2HGJ44YGFBRU.json","graph_json":"https://pith.science/api/pith-number/FEFCKLZGABKRAX2HGJ44YGFBRU/graph.json","events_json":"https://pith.science/api/pith-number/FEFCKLZGABKRAX2HGJ44YGFBRU/events.json","paper":"https://pith.science/paper/FEFCKLZG"},"agent_actions":{"view_html":"https://pith.science/pith/FEFCKLZGABKRAX2HGJ44YGFBRU","download_json":"https://pith.science/pith/FEFCKLZGABKRAX2HGJ44YGFBRU.json","view_paper":"https://pith.science/paper/FEFCKLZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.18587&json=true","fetch_graph":"https://pith.science/api/pith-number/FEFCKLZGABKRAX2HGJ44YGFBRU/graph.json","fetch_events":"https://pith.science/api/pith-number/FEFCKLZGABKRAX2HGJ44YGFBRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEFCKLZGABKRAX2HGJ44YGFBRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEFCKLZGABKRAX2HGJ44YGFBRU/action/storage_attestation","attest_author":"https://pith.science/pith/FEFCKLZGABKRAX2HGJ44YGFBRU/action/author_attestation","sign_citation":"https://pith.science/pith/FEFCKLZGABKRAX2HGJ44YGFBRU/action/citation_signature","submit_replication":"https://pith.science/pith/FEFCKLZGABKRAX2HGJ44YGFBRU/action/replication_record"}},"created_at":"2026-06-01T01:03:53.423339+00:00","updated_at":"2026-06-01T01:03:53.423339+00:00"}