{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:72EFKVXW5C6ICUKWCFFKEYS37N","short_pith_number":"pith:72EFKVXW","canonical_record":{"source":{"id":"2505.12031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T14:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"e09cbf602ebd29257553f39f2fb2e1fdb0b5bd50f419dcb58c93cc60a3ed58b8","abstract_canon_sha256":"cb42032ea85273fc39737d17e140dfad283a7d4b4775c96d3c322a74e3494be8"},"schema_version":"1.0"},"canonical_sha256":"fe885556f6e8bc815156114aa2625bfb636ba5c71274f6113826fc8827f7ff32","source":{"kind":"arxiv","id":"2505.12031","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12031","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12031v1","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12031","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"72EFKVXW5C6I","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"72EFKVXW5C6ICUKW","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"72EFKVXW","created_at":"2026-07-05T11:04:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:72EFKVXW5C6ICUKWCFFKEYS37N","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T14:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"e09cbf602ebd29257553f39f2fb2e1fdb0b5bd50f419dcb58c93cc60a3ed58b8","abstract_canon_sha256":"cb42032ea85273fc39737d17e140dfad283a7d4b4775c96d3c322a74e3494be8"},"schema_version":"1.0"},"canonical_sha256":"fe885556f6e8bc815156114aa2625bfb636ba5c71274f6113826fc8827f7ff32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:57.180938Z","signature_b64":"WV9HGF8J1xHTUT/77oM07AjD/Xh8ihbWTR34p1er4qWSP23gZotXg0EaaHkCzVjen/yl7Ofw3oux1teVQDafBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe885556f6e8bc815156114aa2625bfb636ba5c71274f6113826fc8827f7ff32","last_reissued_at":"2026-07-05T11:04:57.180421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:57.180421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12031","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uor9+7RKWsfCUmkRGZbER2cSzu7Yv0FcJwwaJTyOSHMVdKqfk5uUI6yYy7lVO1ALZKSY9+GZ/R9n7Nfm8ufYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:36:11.791711Z"},"content_sha256":"09e7a25c92383cd35408c6fc6c19b2fc3c014ae325a5b399c56ab157e534b5df","schema_version":"1.0","event_id":"sha256:09e7a25c92383cd35408c6fc6c19b2fc3c014ae325a5b399c56ab157e534b5df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:72EFKVXW5C6ICUKWCFFKEYS37N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chun Cao, Jiakun Zhang, Jiarui Zhang, Jingwei Xu, Junyu Lai, Shuo Xu, Taolue Chen, Yao Yang, Zihang Wang","submitted_at":"2025-05-17T14:47:36Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have sparked considerable interest in automated theorem proving and a prominent line of research integrates stepwise LLM-based provers into tree search. In this paper, we introduce a novel proof-state exploration approach for training data synthesis, designed to produce diverse tactics across a wide range of intermediate proof states, thereby facilitating effective one-shot fine-tuning of LLM as the policy model. We also propose an adaptive beam size strategy, which effectively takes advantage of our data synthesis method and achieves a trade"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12031","kind":"arxiv","version":1},"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/2505.12031/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LPQSaoUuQwPUHqelYLOpmptW2nsuGvGPPHNdsTeGm96oC7fQzAYgBRjXmcecjp1GkNKQHOGO7KVSYZ88u2wyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:36:11.792203Z"},"content_sha256":"9f215a6e07e14831ae3629e9b1c20de9a28579ce9d5472601ec241a49f9f8b93","schema_version":"1.0","event_id":"sha256:9f215a6e07e14831ae3629e9b1c20de9a28579ce9d5472601ec241a49f9f8b93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N/bundle.json","state_url":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/72EFKVXW5C6ICUKWCFFKEYS37N/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T23:36:11Z","links":{"resolver":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N","bundle":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N/bundle.json","state":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/72EFKVXW5C6ICUKWCFFKEYS37N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:72EFKVXW5C6ICUKWCFFKEYS37N","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":"cb42032ea85273fc39737d17e140dfad283a7d4b4775c96d3c322a74e3494be8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T14:47:36Z","title_canon_sha256":"e09cbf602ebd29257553f39f2fb2e1fdb0b5bd50f419dcb58c93cc60a3ed58b8"},"schema_version":"1.0","source":{"id":"2505.12031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12031","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12031v1","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12031","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"72EFKVXW5C6I","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"72EFKVXW5C6ICUKW","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"72EFKVXW","created_at":"2026-07-05T11:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:9f215a6e07e14831ae3629e9b1c20de9a28579ce9d5472601ec241a49f9f8b93","target":"graph","created_at":"2026-07-05T11:04:57Z","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/2505.12031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have sparked considerable interest in automated theorem proving and a prominent line of research integrates stepwise LLM-based provers into tree search. In this paper, we introduce a novel proof-state exploration approach for training data synthesis, designed to produce diverse tactics across a wide range of intermediate proof states, thereby facilitating effective one-shot fine-tuning of LLM as the policy model. We also propose an adaptive beam size strategy, which effectively takes advantage of our data synthesis method and achieves a trade","authors_text":"Chun Cao, Jiakun Zhang, Jiarui Zhang, Jingwei Xu, Junyu Lai, Shuo Xu, Taolue Chen, Yao Yang, Zihang Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T14:47:36Z","title":"LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12031","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":"sha256:09e7a25c92383cd35408c6fc6c19b2fc3c014ae325a5b399c56ab157e534b5df","target":"record","created_at":"2026-07-05T11:04:57Z","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":"cb42032ea85273fc39737d17e140dfad283a7d4b4775c96d3c322a74e3494be8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T14:47:36Z","title_canon_sha256":"e09cbf602ebd29257553f39f2fb2e1fdb0b5bd50f419dcb58c93cc60a3ed58b8"},"schema_version":"1.0","source":{"id":"2505.12031","kind":"arxiv","version":1}},"canonical_sha256":"fe885556f6e8bc815156114aa2625bfb636ba5c71274f6113826fc8827f7ff32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe885556f6e8bc815156114aa2625bfb636ba5c71274f6113826fc8827f7ff32","first_computed_at":"2026-07-05T11:04:57.180421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:57.180421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WV9HGF8J1xHTUT/77oM07AjD/Xh8ihbWTR34p1er4qWSP23gZotXg0EaaHkCzVjen/yl7Ofw3oux1teVQDafBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:57.180938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09e7a25c92383cd35408c6fc6c19b2fc3c014ae325a5b399c56ab157e534b5df","sha256:9f215a6e07e14831ae3629e9b1c20de9a28579ce9d5472601ec241a49f9f8b93"],"state_sha256":"7e8efcc1fc3dbe624256fe4dc3a188e892d603317b1b1d0f1c41974534ca93ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bCCf96JSlaFvCecl6VSta6QrWVgGrweoCOezHBTpgHzMjqxTnnN9j/4hiT2h6sDCy6ybUVNbxdP1DuY2oLfHBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:36:11.795893Z","bundle_sha256":"d7dda27bacfa174e03b7042c9087356600e079cb7c64fe32999ccb937f3d2788"}}