{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BK7ZOPKFZPWUSNA3I6GSHUT6Y7","short_pith_number":"pith:BK7ZOPKF","canonical_record":{"source":{"id":"2410.12881","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-15T18:25:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6cf660cfa7d2e0dcd570b421552a389f8c048fdb04a98fb41a39c7c743049ee4","abstract_canon_sha256":"0f27790267c8996e988ea1a1f8b490a3241ee60f7449536e23fe454772083df5"},"schema_version":"1.0"},"canonical_sha256":"0abf973d45cbed49341b478d23d27ec7d357fbca894a1f18849245ea6e8c6874","source":{"kind":"arxiv","id":"2410.12881","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12881","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12881v2","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12881","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"pith_short_12","alias_value":"BK7ZOPKFZPWU","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"pith_short_16","alias_value":"BK7ZOPKFZPWUSNA3","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"pith_short_8","alias_value":"BK7ZOPKF","created_at":"2026-07-05T10:53:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BK7ZOPKFZPWUSNA3I6GSHUT6Y7","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12881","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-15T18:25:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6cf660cfa7d2e0dcd570b421552a389f8c048fdb04a98fb41a39c7c743049ee4","abstract_canon_sha256":"0f27790267c8996e988ea1a1f8b490a3241ee60f7449536e23fe454772083df5"},"schema_version":"1.0"},"canonical_sha256":"0abf973d45cbed49341b478d23d27ec7d357fbca894a1f18849245ea6e8c6874","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:48.393065Z","signature_b64":"JcpQGK7ohkxC2frjdzTzYq8y6xTo/FmGKaa2XAdLvGCQC+4hUpuKavanpsfF+rxVW8tlw9Kfn+wIw8TyORzwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0abf973d45cbed49341b478d23d27ec7d357fbca894a1f18849245ea6e8c6874","last_reissued_at":"2026-07-05T10:53:48.392535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:48.392535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12881","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:53:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gDw9kertixiQKqHvcn4rzSBQJXyen9MzfAvtnUKt4VHqoUQtPM4KGaARfkyWaaJPKuzDJhX6nkbqggJeq57DDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:18:46.789671Z"},"content_sha256":"1af982beda796043199d21bf33fcfb353004ade905eaccebb7db632f1ef98e52","schema_version":"1.0","event_id":"sha256:1af982beda796043199d21bf33fcfb353004ade905eaccebb7db632f1ef98e52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BK7ZOPKFZPWUSNA3I6GSHUT6Y7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MIND: Math Informed syNthetic Dialogues for Pretraining LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bryan Catanzaro, Eric Nyberg, John Kamalu, Mohammad Shoeybi, Mostofa Patwary, Sanjeev Satheesh, Shrimai Prabhumoye, Syeda Nahida Akter","submitted_at":"2024-10-15T18:25:53Z","abstract_excerpt":"The utility of synthetic data to enhance pretraining data quality and hence to improve downstream task accuracy has been widely explored in recent large language models (LLMs). Yet, these approaches fall inadequate in complex, multi-hop and mathematical reasoning tasks as the synthetic data typically fails to add complementary knowledge to the existing raw corpus. In this work, we propose a novel large-scale and diverse Math Informed syNthetic Dialogue (MIND) generation method that improves the mathematical reasoning ability of LLMs. Specifically, using MIND, we generate synthetic conversation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12881","kind":"arxiv","version":2},"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/2410.12881/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":"2026-07-05T10:53:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uYV3GpCIzbDWdO5Kb2dpAyWw4FfBlAKR9PQhNmDeZqUM07J8W1X0kkfNYXkXVGLOyAP04NTLYuexqo7bDNlcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:18:46.790211Z"},"content_sha256":"0d9d02ab0bd0b1e6e841e299788488253906459bf9b1de0e218b29aa906bc336","schema_version":"1.0","event_id":"sha256:0d9d02ab0bd0b1e6e841e299788488253906459bf9b1de0e218b29aa906bc336"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BK7ZOPKFZPWUSNA3I6GSHUT6Y7/bundle.json","state_url":"https://pith.science/pith/BK7ZOPKFZPWUSNA3I6GSHUT6Y7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BK7ZOPKFZPWUSNA3I6GSHUT6Y7/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":"2026-08-04T14:18:46Z","links":{"resolver":"https://pith.science/pith/BK7ZOPKFZPWUSNA3I6GSHUT6Y7","bundle":"https://pith.science/pith/BK7ZOPKFZPWUSNA3I6GSHUT6Y7/bundle.json","state":"https://pith.science/pith/BK7ZOPKFZPWUSNA3I6GSHUT6Y7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BK7ZOPKFZPWUSNA3I6GSHUT6Y7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BK7ZOPKFZPWUSNA3I6GSHUT6Y7","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":"0f27790267c8996e988ea1a1f8b490a3241ee60f7449536e23fe454772083df5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-15T18:25:53Z","title_canon_sha256":"6cf660cfa7d2e0dcd570b421552a389f8c048fdb04a98fb41a39c7c743049ee4"},"schema_version":"1.0","source":{"id":"2410.12881","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12881","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12881v2","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12881","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"pith_short_12","alias_value":"BK7ZOPKFZPWU","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"pith_short_16","alias_value":"BK7ZOPKFZPWUSNA3","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"pith_short_8","alias_value":"BK7ZOPKF","created_at":"2026-07-05T10:53:48Z"}],"graph_snapshots":[{"event_id":"sha256:0d9d02ab0bd0b1e6e841e299788488253906459bf9b1de0e218b29aa906bc336","target":"graph","created_at":"2026-07-05T10:53:48Z","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/2410.12881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The utility of synthetic data to enhance pretraining data quality and hence to improve downstream task accuracy has been widely explored in recent large language models (LLMs). Yet, these approaches fall inadequate in complex, multi-hop and mathematical reasoning tasks as the synthetic data typically fails to add complementary knowledge to the existing raw corpus. In this work, we propose a novel large-scale and diverse Math Informed syNthetic Dialogue (MIND) generation method that improves the mathematical reasoning ability of LLMs. Specifically, using MIND, we generate synthetic conversation","authors_text":"Bryan Catanzaro, Eric Nyberg, John Kamalu, Mohammad Shoeybi, Mostofa Patwary, Sanjeev Satheesh, Shrimai Prabhumoye, Syeda Nahida Akter","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-15T18:25:53Z","title":"MIND: Math Informed syNthetic Dialogues for Pretraining LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12881","kind":"arxiv","version":2},"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":"sha256:1af982beda796043199d21bf33fcfb353004ade905eaccebb7db632f1ef98e52","target":"record","created_at":"2026-07-05T10:53:48Z","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":"0f27790267c8996e988ea1a1f8b490a3241ee60f7449536e23fe454772083df5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-15T18:25:53Z","title_canon_sha256":"6cf660cfa7d2e0dcd570b421552a389f8c048fdb04a98fb41a39c7c743049ee4"},"schema_version":"1.0","source":{"id":"2410.12881","kind":"arxiv","version":2}},"canonical_sha256":"0abf973d45cbed49341b478d23d27ec7d357fbca894a1f18849245ea6e8c6874","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0abf973d45cbed49341b478d23d27ec7d357fbca894a1f18849245ea6e8c6874","first_computed_at":"2026-07-05T10:53:48.392535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:48.392535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JcpQGK7ohkxC2frjdzTzYq8y6xTo/FmGKaa2XAdLvGCQC+4hUpuKavanpsfF+rxVW8tlw9Kfn+wIw8TyORzwDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:48.393065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12881","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1af982beda796043199d21bf33fcfb353004ade905eaccebb7db632f1ef98e52","sha256:0d9d02ab0bd0b1e6e841e299788488253906459bf9b1de0e218b29aa906bc336"],"state_sha256":"9139c483e99ba2cb3e457c18547d4548807fb728d0a33f644ae7d803d4bdfa93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YzJTNJC3TqLUE/5AdUZnEOP5wpDkImUS22i/r+sXSng73qoSfcBAuP+9x+0Xr+m5zWcFydTOIxnuXD1858zyCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:18:46.829018Z","bundle_sha256":"263e2d77185448cda4927e389ae6c9a432c856e9c7c3850e4aafad1ef6d2f0cc"}}