{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7MT2AMLNDX2ABAWTD6IN2O4QHE","short_pith_number":"pith:7MT2AMLN","canonical_record":{"source":{"id":"2403.18120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-26T22:01:13Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"787fca54ac40ed26f57b731e0754e86f34ec52ec8b750a682ac49512abbfc2ca","abstract_canon_sha256":"232fe52b3c8c754bbc8581204b5971e0b63385d7d6847a59288184694907cd81"},"schema_version":"1.0"},"canonical_sha256":"fb27a0316d1df40082d31f90dd3b9039301d85c51fe5b8792c532c3cbf31a36d","source":{"kind":"arxiv","id":"2403.18120","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18120","created_at":"2026-07-05T08:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18120v1","created_at":"2026-07-05T08:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18120","created_at":"2026-07-05T08:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"7MT2AMLNDX2A","created_at":"2026-07-05T08:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"7MT2AMLNDX2ABAWT","created_at":"2026-07-05T08:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"7MT2AMLN","created_at":"2026-07-05T08:01:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7MT2AMLNDX2ABAWTD6IN2O4QHE","target":"record","payload":{"canonical_record":{"source":{"id":"2403.18120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-26T22:01:13Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"787fca54ac40ed26f57b731e0754e86f34ec52ec8b750a682ac49512abbfc2ca","abstract_canon_sha256":"232fe52b3c8c754bbc8581204b5971e0b63385d7d6847a59288184694907cd81"},"schema_version":"1.0"},"canonical_sha256":"fb27a0316d1df40082d31f90dd3b9039301d85c51fe5b8792c532c3cbf31a36d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:20.561812Z","signature_b64":"4pHxr7O8XUR+8x8hqkJgAKR2xigdtKTfY3RynJ5Nro8O/fxkMyTlMRrpkmMkIzgn3Nd4iXXpkrUdu8ATrEIkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb27a0316d1df40082d31f90dd3b9039301d85c51fe5b8792c532c3cbf31a36d","last_reissued_at":"2026-07-05T08:01:20.561305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:20.561305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.18120","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":"2026-07-05T08:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BrBsXmkBXAT0KmxA5Cow4AIEe66t505LzkCzzvjgQa8OAwcY+r/KTyToAm5WASVtjoQ6Tj8pESC65b8zd+eLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:25:55.551491Z"},"content_sha256":"16a3a586f7aefdfd9176c23f25ac26afcb5949f2a807d375d3fb9b0cd8cdbe72","schema_version":"1.0","event_id":"sha256:16a3a586f7aefdfd9176c23f25ac26afcb5949f2a807d375d3fb9b0cd8cdbe72"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7MT2AMLNDX2ABAWTD6IN2O4QHE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Charles Staats, Christian Szegedy, Jin Peng Zhou, Kilian Q. Weinberger, Wenda Li, Yuhuai Wu","submitted_at":"2024-03-26T22:01:13Z","abstract_excerpt":"Large language models (LLM), such as Google's Minerva and OpenAI's GPT families, are becoming increasingly capable of solving mathematical quantitative reasoning problems. However, they still make unjustified logical and computational errors in their reasoning steps and answers. In this paper, we leverage the fact that if the training corpus of LLMs contained sufficiently many examples of formal mathematics (e.g. in Isabelle, a formal theorem proving environment), they can be prompted to translate i.e. autoformalize informal mathematical statements into formal Isabelle code -- which can be ver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18120","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/2403.18120/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":"2026-07-05T08:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y4hJjInwLt7YY2xLfY/iQLa7xMmAhN/kODP4VFl+yh/7SgiKEJ/nVVtL1+uLLjOi2Y4f7raFYVZXTojHor8jBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:25:55.552049Z"},"content_sha256":"83042c8b8181c484c925099462a4d54b6f9e81bf277a01c0539dba6cbde66c89","schema_version":"1.0","event_id":"sha256:83042c8b8181c484c925099462a4d54b6f9e81bf277a01c0539dba6cbde66c89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7MT2AMLNDX2ABAWTD6IN2O4QHE/bundle.json","state_url":"https://pith.science/pith/7MT2AMLNDX2ABAWTD6IN2O4QHE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7MT2AMLNDX2ABAWTD6IN2O4QHE/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":"2026-07-31T16:25:55Z","links":{"resolver":"https://pith.science/pith/7MT2AMLNDX2ABAWTD6IN2O4QHE","bundle":"https://pith.science/pith/7MT2AMLNDX2ABAWTD6IN2O4QHE/bundle.json","state":"https://pith.science/pith/7MT2AMLNDX2ABAWTD6IN2O4QHE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7MT2AMLNDX2ABAWTD6IN2O4QHE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7MT2AMLNDX2ABAWTD6IN2O4QHE","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":"232fe52b3c8c754bbc8581204b5971e0b63385d7d6847a59288184694907cd81","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-26T22:01:13Z","title_canon_sha256":"787fca54ac40ed26f57b731e0754e86f34ec52ec8b750a682ac49512abbfc2ca"},"schema_version":"1.0","source":{"id":"2403.18120","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18120","created_at":"2026-07-05T08:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18120v1","created_at":"2026-07-05T08:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18120","created_at":"2026-07-05T08:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"7MT2AMLNDX2A","created_at":"2026-07-05T08:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"7MT2AMLNDX2ABAWT","created_at":"2026-07-05T08:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"7MT2AMLN","created_at":"2026-07-05T08:01:20Z"}],"graph_snapshots":[{"event_id":"sha256:83042c8b8181c484c925099462a4d54b6f9e81bf277a01c0539dba6cbde66c89","target":"graph","created_at":"2026-07-05T08:01:20Z","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/2403.18120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLM), such as Google's Minerva and OpenAI's GPT families, are becoming increasingly capable of solving mathematical quantitative reasoning problems. However, they still make unjustified logical and computational errors in their reasoning steps and answers. In this paper, we leverage the fact that if the training corpus of LLMs contained sufficiently many examples of formal mathematics (e.g. in Isabelle, a formal theorem proving environment), they can be prompted to translate i.e. autoformalize informal mathematical statements into formal Isabelle code -- which can be ver","authors_text":"Charles Staats, Christian Szegedy, Jin Peng Zhou, Kilian Q. Weinberger, Wenda Li, Yuhuai Wu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-26T22:01:13Z","title":"Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18120","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":"sha256:16a3a586f7aefdfd9176c23f25ac26afcb5949f2a807d375d3fb9b0cd8cdbe72","target":"record","created_at":"2026-07-05T08:01:20Z","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":"232fe52b3c8c754bbc8581204b5971e0b63385d7d6847a59288184694907cd81","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-26T22:01:13Z","title_canon_sha256":"787fca54ac40ed26f57b731e0754e86f34ec52ec8b750a682ac49512abbfc2ca"},"schema_version":"1.0","source":{"id":"2403.18120","kind":"arxiv","version":1}},"canonical_sha256":"fb27a0316d1df40082d31f90dd3b9039301d85c51fe5b8792c532c3cbf31a36d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb27a0316d1df40082d31f90dd3b9039301d85c51fe5b8792c532c3cbf31a36d","first_computed_at":"2026-07-05T08:01:20.561305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:20.561305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4pHxr7O8XUR+8x8hqkJgAKR2xigdtKTfY3RynJ5Nro8O/fxkMyTlMRrpkmMkIzgn3Nd4iXXpkrUdu8ATrEIkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:20.561812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.18120","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16a3a586f7aefdfd9176c23f25ac26afcb5949f2a807d375d3fb9b0cd8cdbe72","sha256:83042c8b8181c484c925099462a4d54b6f9e81bf277a01c0539dba6cbde66c89"],"state_sha256":"23e1690b3a3c85410715b510d7c15dbc211ffd27c0b5324b063df6b6e602e1e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4qevmFR1JN5Kc66RWNr6asw+UHdArbhXPj3n965+ccsBoxcXFeg9E/xq0FPcW6JWtAJBaQxNsHuZ/mW9Fr7VBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T16:25:55.560740Z","bundle_sha256":"370a72152a7070cb5f272cfb955e141f530c2720cbe13ff1c5cd293e62adb9cf"}}