{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AUH5WDEC6Y32WM4HVYKIS74IEP","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":"0d8346f973e31091e0d130cd65d30cac5ac67c479b579fa5420d0fcd7769dd5e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-03T15:41:38Z","title_canon_sha256":"b83b9a739c57191378151b98782810d659124597ebcb9c31fe05f47e0a301563"},"schema_version":"1.0","source":{"id":"2507.02726","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02726","created_at":"2026-07-05T11:31:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02726v1","created_at":"2026-07-05T11:31:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02726","created_at":"2026-07-05T11:31:33Z"},{"alias_kind":"pith_short_12","alias_value":"AUH5WDEC6Y32","created_at":"2026-07-05T11:31:33Z"},{"alias_kind":"pith_short_16","alias_value":"AUH5WDEC6Y32WM4H","created_at":"2026-07-05T11:31:33Z"},{"alias_kind":"pith_short_8","alias_value":"AUH5WDEC","created_at":"2026-07-05T11:31:33Z"}],"graph_snapshots":[{"event_id":"sha256:fba45d5a525a8ff2bdb87695a6f30b72b0ce14cae1865170796e00bc0ed4cda7","target":"graph","created_at":"2026-07-05T11:31:33Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.02726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning remains a challenging task for large language models (LLMs), especially within the logically constrained environment of automated theorem proving (ATP), due to sparse rewards and the vast scale of proofs. These challenges are amplified in benchmarks like PutnamBench, which contains university-level problems requiring complex, multi-step reasoning. To address this, we introduce self-generated goal-conditioned MDPs (sG-MDPs), a new framework in which agents generate and pursue their subgoals based on the evolving proof state. Given this more structured generation of goals, the resultin","authors_text":"Anthony Bordg, Haitham Bou Ammar, Jun Wang, Matthieu Zimmer, Rasul Tutunov, Xiaotong Ji","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-03T15:41:38Z","title":"Bourbaki: Self-Generated and Goal-Conditioned MDPs for Theorem Proving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02726","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cc97ab1edaaa8e4a9d22d08e140f26496a878f61b429223c5ef4c2f5d5da75c4","target":"record","created_at":"2026-07-05T11:31:33Z","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":"0d8346f973e31091e0d130cd65d30cac5ac67c479b579fa5420d0fcd7769dd5e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-03T15:41:38Z","title_canon_sha256":"b83b9a739c57191378151b98782810d659124597ebcb9c31fe05f47e0a301563"},"schema_version":"1.0","source":{"id":"2507.02726","kind":"arxiv","version":1}},"canonical_sha256":"050fdb0c82f637ab3387ae14897f8823f7ae3442cb9c0d68d8f393eb962fc6a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"050fdb0c82f637ab3387ae14897f8823f7ae3442cb9c0d68d8f393eb962fc6a9","first_computed_at":"2026-07-05T11:31:33.757627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:33.757627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"moK+t+UJi+Sg17Au7HHKEaGuyGGu5L+VP0Z46FNizTn51+BkujQD7DFxr2Uh55i+eOiwxI2ooKEKp/Pos35JAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:33.758123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02726","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc97ab1edaaa8e4a9d22d08e140f26496a878f61b429223c5ef4c2f5d5da75c4","sha256:fba45d5a525a8ff2bdb87695a6f30b72b0ce14cae1865170796e00bc0ed4cda7"],"state_sha256":"8a0c3b75c4a9e81fb0d7891273173ee004d9cabe1555585549bc14f6253449fa"}