{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FEFCKLZGABKRAX2HGJ44YGFBRU","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":"c5909645f5415efa6036b7716f8c17048252c3fd4b6a74a85885aa05b2f1e5e7","cross_cats_sorted":["cs.AI","cs.LO","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-13T01:33:20Z","title_canon_sha256":"ed92ff7aced7b8c2167c2107450b9ab358e55d03810b1e0afed5054742d303a3"},"schema_version":"1.0","source":{"id":"2604.18587","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.18587","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"arxiv_version","alias_value":"2604.18587v2","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18587","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_12","alias_value":"FEFCKLZGABKR","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_16","alias_value":"FEFCKLZGABKRAX2H","created_at":"2026-06-01T01:03:53Z"},{"alias_kind":"pith_short_8","alias_value":"FEFCKLZG","created_at":"2026-06-01T01:03:53Z"}],"graph_snapshots":[{"event_id":"sha256:0911484a46101c44c57d30875b8addf174874a1d2caf7ff502ef91c53d7071bb","target":"graph","created_at":"2026-06-01T01:03:53Z","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 approach achieves state-of-the-art performance on PutnamBench among publicly reported ∼8B and ∼32B parameter models under comparable test-time budgets"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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"},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Compiler outputs compress diverse proof attempts into a compact set of failure modes that support local corrections and stronger theorem proving."}],"snapshot_sha256":"9d8a70447989471a8167eb3fd4526f32fea3ebd23c3453067172bfec1ca0fe9b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3d67ba3a59f67d66b04218410b8324c85731d1a39d5919baadd0d43e80e5c0c2"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.18587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guchan Li, Hongning Wang, Rui Tian","cross_cats":["cs.AI","cs.LO","cs.PL"],"headline":"Compiler outputs compress diverse proof attempts into a compact set of failure modes that support local corrections and stronger theorem proving.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-13T01:33:20Z","title":"Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.18587","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T12:38:53.288785Z","id":"751764c0-9b85-496d-adc3-362d9d142c74","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Compiler outputs compress diverse proof attempts into a compact set of failure modes that support local corrections and stronger theorem proving.","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","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"}},"verdict_id":"751764c0-9b85-496d-adc3-362d9d142c74"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5a46950b5783c3adad28f3de0f81ffd3794b2a25224ce04619cf5936cc19ecb5","target":"record","created_at":"2026-06-01T01:03:53Z","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":"c5909645f5415efa6036b7716f8c17048252c3fd4b6a74a85885aa05b2f1e5e7","cross_cats_sorted":["cs.AI","cs.LO","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-13T01:33:20Z","title_canon_sha256":"ed92ff7aced7b8c2167c2107450b9ab358e55d03810b1e0afed5054742d303a3"},"schema_version":"1.0","source":{"id":"2604.18587","kind":"arxiv","version":2}},"canonical_sha256":"290a252f260055105f473279cc18a18d1d1fd37e4837aba2c7f71af68a4d0fcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"290a252f260055105f473279cc18a18d1d1fd37e4837aba2c7f71af68a4d0fcf","first_computed_at":"2026-06-01T01:03:53.423143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:53.423143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bH+82tqJijbzDmlYVJ+Fas5aJxSlhBTFKq1U5wMDgTMwgQELNNnpavmlW1mYgqHZZ+JfGGmVlgOBfqKeqLsJCQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:53.424192Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.18587","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a46950b5783c3adad28f3de0f81ffd3794b2a25224ce04619cf5936cc19ecb5","sha256:0911484a46101c44c57d30875b8addf174874a1d2caf7ff502ef91c53d7071bb"],"state_sha256":"56a6710a4ce38ffb4938b810cf4b29081a7745b5cfea6008628194fc408f2d32"}