{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MF5KXMPKTVYIA5WOVOT7HEYIFD","short_pith_number":"pith:MF5KXMPK","canonical_record":{"source":{"id":"2407.10040","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-14T01:43:07Z","cross_cats_sorted":[],"title_canon_sha256":"e527d1446a819d931cd7af314b1baff0ae53e2c5c89211c019ab89587bcb7ab6","abstract_canon_sha256":"dfb92c9e747be98c8a7095a3b9215e8956fe8eeca7b78538fc0bf28f209917e8"},"schema_version":"1.0"},"canonical_sha256":"617aabb1ea9d708076ceaba7f3930828e590b6aadceed8619818ad443f9aafb3","source":{"kind":"arxiv","id":"2407.10040","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10040","created_at":"2026-07-05T10:31:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10040v5","created_at":"2026-07-05T10:31:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10040","created_at":"2026-07-05T10:31:45Z"},{"alias_kind":"pith_short_12","alias_value":"MF5KXMPKTVYI","created_at":"2026-07-05T10:31:45Z"},{"alias_kind":"pith_short_16","alias_value":"MF5KXMPKTVYIA5WO","created_at":"2026-07-05T10:31:45Z"},{"alias_kind":"pith_short_8","alias_value":"MF5KXMPK","created_at":"2026-07-05T10:31:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MF5KXMPKTVYIA5WOVOT7HEYIFD","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10040","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-14T01:43:07Z","cross_cats_sorted":[],"title_canon_sha256":"e527d1446a819d931cd7af314b1baff0ae53e2c5c89211c019ab89587bcb7ab6","abstract_canon_sha256":"dfb92c9e747be98c8a7095a3b9215e8956fe8eeca7b78538fc0bf28f209917e8"},"schema_version":"1.0"},"canonical_sha256":"617aabb1ea9d708076ceaba7f3930828e590b6aadceed8619818ad443f9aafb3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:45.174924Z","signature_b64":"WvcszJpZCTmz3k/lBeMrQLuINwjpWR9dJuUcCaC9n6VOdNqUbhAi0bReVF0htD/qY/0zWzcdOPneeqz4moP7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"617aabb1ea9d708076ceaba7f3930828e590b6aadceed8619818ad443f9aafb3","last_reissued_at":"2026-07-05T10:31:45.174024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:45.174024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10040","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:31:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xAmBWvfU/5TUNluSQBx+YozebIcmCI66RreT0YQLMsg47amMpvsbfQFJi2igtdailhcpCcXlliOsF3nGToNUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T11:37:21.982580Z"},"content_sha256":"d099db7c76f9ecabfa65887d4f34f76503f484c6ff28ea2d3a6e4ca82f9444cf","schema_version":"1.0","event_id":"sha256:d099db7c76f9ecabfa65887d4f34f76503f484c6ff28ea2d3a6e4ca82f9444cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MF5KXMPKTVYIA5WOVOT7HEYIFD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lean-STaR: Learning to Interleave Thinking and Proving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haohan Lin, Sean Welleck, Yiming Yang, Zhiqing Sun","submitted_at":"2024-07-14T01:43:07Z","abstract_excerpt":"Traditional language model-based theorem proving assumes that by training on a sufficient amount of formal proof data, a model will learn to prove theorems. Our key observation is that a wealth of informal information that is not present in formal proofs can be useful for learning to prove theorems. For instance, humans think through steps of a proof, but this thought process is not visible in the resulting code. We present Lean-STaR, a framework for training language models to produce informal thoughts prior to each step of a proof, thereby boosting the model's theorem-proving capabilities. L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10040","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/2407.10040/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":"2026-07-05T10:31:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9eX5ql9kJ9YLzU5IigJP+HsdHksP6d4EXSPhFxLgcOdwhyfS5plGoSjMA79wG73QhUWwlknR2pFznPkCc7zVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T11:37:21.983077Z"},"content_sha256":"9ff2f52262be2768c73d2d140340cab3bc4b8413bd3c569193a9f175e12c7e21","schema_version":"1.0","event_id":"sha256:9ff2f52262be2768c73d2d140340cab3bc4b8413bd3c569193a9f175e12c7e21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MF5KXMPKTVYIA5WOVOT7HEYIFD/bundle.json","state_url":"https://pith.science/pith/MF5KXMPKTVYIA5WOVOT7HEYIFD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MF5KXMPKTVYIA5WOVOT7HEYIFD/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":"2026-08-02T11:37:21Z","links":{"resolver":"https://pith.science/pith/MF5KXMPKTVYIA5WOVOT7HEYIFD","bundle":"https://pith.science/pith/MF5KXMPKTVYIA5WOVOT7HEYIFD/bundle.json","state":"https://pith.science/pith/MF5KXMPKTVYIA5WOVOT7HEYIFD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MF5KXMPKTVYIA5WOVOT7HEYIFD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MF5KXMPKTVYIA5WOVOT7HEYIFD","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":"dfb92c9e747be98c8a7095a3b9215e8956fe8eeca7b78538fc0bf28f209917e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-14T01:43:07Z","title_canon_sha256":"e527d1446a819d931cd7af314b1baff0ae53e2c5c89211c019ab89587bcb7ab6"},"schema_version":"1.0","source":{"id":"2407.10040","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10040","created_at":"2026-07-05T10:31:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10040v5","created_at":"2026-07-05T10:31:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10040","created_at":"2026-07-05T10:31:45Z"},{"alias_kind":"pith_short_12","alias_value":"MF5KXMPKTVYI","created_at":"2026-07-05T10:31:45Z"},{"alias_kind":"pith_short_16","alias_value":"MF5KXMPKTVYIA5WO","created_at":"2026-07-05T10:31:45Z"},{"alias_kind":"pith_short_8","alias_value":"MF5KXMPK","created_at":"2026-07-05T10:31:45Z"}],"graph_snapshots":[{"event_id":"sha256:9ff2f52262be2768c73d2d140340cab3bc4b8413bd3c569193a9f175e12c7e21","target":"graph","created_at":"2026-07-05T10:31:45Z","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/2407.10040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional language model-based theorem proving assumes that by training on a sufficient amount of formal proof data, a model will learn to prove theorems. Our key observation is that a wealth of informal information that is not present in formal proofs can be useful for learning to prove theorems. For instance, humans think through steps of a proof, but this thought process is not visible in the resulting code. We present Lean-STaR, a framework for training language models to produce informal thoughts prior to each step of a proof, thereby boosting the model's theorem-proving capabilities. L","authors_text":"Haohan Lin, Sean Welleck, Yiming Yang, Zhiqing Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-14T01:43:07Z","title":"Lean-STaR: Learning to Interleave Thinking and Proving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10040","kind":"arxiv","version":5},"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:d099db7c76f9ecabfa65887d4f34f76503f484c6ff28ea2d3a6e4ca82f9444cf","target":"record","created_at":"2026-07-05T10:31:45Z","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":"dfb92c9e747be98c8a7095a3b9215e8956fe8eeca7b78538fc0bf28f209917e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-14T01:43:07Z","title_canon_sha256":"e527d1446a819d931cd7af314b1baff0ae53e2c5c89211c019ab89587bcb7ab6"},"schema_version":"1.0","source":{"id":"2407.10040","kind":"arxiv","version":5}},"canonical_sha256":"617aabb1ea9d708076ceaba7f3930828e590b6aadceed8619818ad443f9aafb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"617aabb1ea9d708076ceaba7f3930828e590b6aadceed8619818ad443f9aafb3","first_computed_at":"2026-07-05T10:31:45.174024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:45.174024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WvcszJpZCTmz3k/lBeMrQLuINwjpWR9dJuUcCaC9n6VOdNqUbhAi0bReVF0htD/qY/0zWzcdOPneeqz4moP7Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:45.174924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10040","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d099db7c76f9ecabfa65887d4f34f76503f484c6ff28ea2d3a6e4ca82f9444cf","sha256:9ff2f52262be2768c73d2d140340cab3bc4b8413bd3c569193a9f175e12c7e21"],"state_sha256":"995c4b118c0c65214583bbf34c7e165f5928d10e649a63943afde9e5e3ec2c01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yZjMSO0QgokrqPl0zJMeeOSbENlH8a/CarNgnZKpV8gzbmxldr0II4fm7WV3Pk6/vBxHNKSKwQSPRDVHYE7HDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T11:37:21.986403Z","bundle_sha256":"1a43f32dea7dda051f5e11c2a9865d7c5913cf1789d1f8c4c4fac356b5a05587"}}