{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MBAUTBXOUIEV3GHGEB7VX3OAUW","short_pith_number":"pith:MBAUTBXO","canonical_record":{"source":{"id":"2310.06786","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-10T16:57:28Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"12f9c75d5a58248e376ddc174f914d1b54b6f14a8d81f55a35313e4b3f69737d","abstract_canon_sha256":"b9542b1bf326a7046beaf3fbd275c1f8908e2d8df1cd4e00408c599cf7c1f1ec"},"schema_version":"1.0"},"canonical_sha256":"60414986eea2095d98e6207f5bedc0a5b326125f1fedc7001c9e83454eb0bb50","source":{"kind":"arxiv","id":"2310.06786","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06786","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06786v1","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06786","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_12","alias_value":"MBAUTBXOUIEV","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_16","alias_value":"MBAUTBXOUIEV3GHG","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_8","alias_value":"MBAUTBXO","created_at":"2026-07-05T06:59:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MBAUTBXOUIEV3GHGEB7VX3OAUW","target":"record","payload":{"canonical_record":{"source":{"id":"2310.06786","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-10T16:57:28Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"12f9c75d5a58248e376ddc174f914d1b54b6f14a8d81f55a35313e4b3f69737d","abstract_canon_sha256":"b9542b1bf326a7046beaf3fbd275c1f8908e2d8df1cd4e00408c599cf7c1f1ec"},"schema_version":"1.0"},"canonical_sha256":"60414986eea2095d98e6207f5bedc0a5b326125f1fedc7001c9e83454eb0bb50","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:23.947107Z","signature_b64":"8nRDFwMSYttnNYQelKrD2CrPGMctnRXEdgEtdqGEWNwVGMUzgTLXWtmtpUTtgrz5yTqmzkMTw6GnzuJU4DZpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60414986eea2095d98e6207f5bedc0a5b326125f1fedc7001c9e83454eb0bb50","last_reissued_at":"2026-07-05T06:59:23.946670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:23.946670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.06786","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":"2026-07-05T06:59:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LeKY3hJPdU7FM52BtEGZYpRCIjpHLg0Wn/EBajn0/IfTrJKGcjU287i1XvPbkt+efC5heRKJHhhgERe74lekDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:57:12.050207Z"},"content_sha256":"c5a8d7fcc8701029d82c70e74bab3d4e362c82adc3f7bf5e1a65243d3e881759","schema_version":"1.0","event_id":"sha256:c5a8d7fcc8701029d82c70e74bab3d4e362c82adc3f7bf5e1a65243d3e881759"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MBAUTBXOUIEV3GHGEB7VX3OAUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jimmy Ba, Keiran Paster, Marco Dos Santos, Zhangir Azerbayev","submitted_at":"2023-10-10T16:57:28Z","abstract_excerpt":"There is growing evidence that pretraining on high quality, carefully thought-out tokens such as code or mathematics plays an important role in improving the reasoning abilities of large language models. For example, Minerva, a PaLM model finetuned on billions of tokens of mathematical documents from arXiv and the web, reported dramatically improved performance on problems that require quantitative reasoning. However, because all known open source web datasets employ preprocessing that does not faithfully preserve mathematical notation, the benefits of large scale training on quantitive web do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06786","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/2310.06786/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":"2026-07-05T06:59:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"giLPdvDEyiywI1hIjGcg69YpV3bK84yJzjxZzLCq7bs27vIl+aDnQ0k4WvaIZkVtfONSDQJO76AzZizkIv+tDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:57:12.051183Z"},"content_sha256":"a08c783b5e7b7a6548b6804afbb229a1c257ffb64a95c571f455b3c0d04a3422","schema_version":"1.0","event_id":"sha256:a08c783b5e7b7a6548b6804afbb229a1c257ffb64a95c571f455b3c0d04a3422"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MBAUTBXOUIEV3GHGEB7VX3OAUW/bundle.json","state_url":"https://pith.science/pith/MBAUTBXOUIEV3GHGEB7VX3OAUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MBAUTBXOUIEV3GHGEB7VX3OAUW/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":"2026-08-03T19:57:12Z","links":{"resolver":"https://pith.science/pith/MBAUTBXOUIEV3GHGEB7VX3OAUW","bundle":"https://pith.science/pith/MBAUTBXOUIEV3GHGEB7VX3OAUW/bundle.json","state":"https://pith.science/pith/MBAUTBXOUIEV3GHGEB7VX3OAUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MBAUTBXOUIEV3GHGEB7VX3OAUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MBAUTBXOUIEV3GHGEB7VX3OAUW","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":"b9542b1bf326a7046beaf3fbd275c1f8908e2d8df1cd4e00408c599cf7c1f1ec","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-10T16:57:28Z","title_canon_sha256":"12f9c75d5a58248e376ddc174f914d1b54b6f14a8d81f55a35313e4b3f69737d"},"schema_version":"1.0","source":{"id":"2310.06786","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06786","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06786v1","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06786","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_12","alias_value":"MBAUTBXOUIEV","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_16","alias_value":"MBAUTBXOUIEV3GHG","created_at":"2026-07-05T06:59:23Z"},{"alias_kind":"pith_short_8","alias_value":"MBAUTBXO","created_at":"2026-07-05T06:59:23Z"}],"graph_snapshots":[{"event_id":"sha256:a08c783b5e7b7a6548b6804afbb229a1c257ffb64a95c571f455b3c0d04a3422","target":"graph","created_at":"2026-07-05T06:59:23Z","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/2310.06786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is growing evidence that pretraining on high quality, carefully thought-out tokens such as code or mathematics plays an important role in improving the reasoning abilities of large language models. For example, Minerva, a PaLM model finetuned on billions of tokens of mathematical documents from arXiv and the web, reported dramatically improved performance on problems that require quantitative reasoning. However, because all known open source web datasets employ preprocessing that does not faithfully preserve mathematical notation, the benefits of large scale training on quantitive web do","authors_text":"Jimmy Ba, Keiran Paster, Marco Dos Santos, Zhangir Azerbayev","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-10T16:57:28Z","title":"OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06786","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:c5a8d7fcc8701029d82c70e74bab3d4e362c82adc3f7bf5e1a65243d3e881759","target":"record","created_at":"2026-07-05T06:59:23Z","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":"b9542b1bf326a7046beaf3fbd275c1f8908e2d8df1cd4e00408c599cf7c1f1ec","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-10T16:57:28Z","title_canon_sha256":"12f9c75d5a58248e376ddc174f914d1b54b6f14a8d81f55a35313e4b3f69737d"},"schema_version":"1.0","source":{"id":"2310.06786","kind":"arxiv","version":1}},"canonical_sha256":"60414986eea2095d98e6207f5bedc0a5b326125f1fedc7001c9e83454eb0bb50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60414986eea2095d98e6207f5bedc0a5b326125f1fedc7001c9e83454eb0bb50","first_computed_at":"2026-07-05T06:59:23.946670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:23.946670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8nRDFwMSYttnNYQelKrD2CrPGMctnRXEdgEtdqGEWNwVGMUzgTLXWtmtpUTtgrz5yTqmzkMTw6GnzuJU4DZpCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:23.947107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06786","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5a8d7fcc8701029d82c70e74bab3d4e362c82adc3f7bf5e1a65243d3e881759","sha256:a08c783b5e7b7a6548b6804afbb229a1c257ffb64a95c571f455b3c0d04a3422"],"state_sha256":"0d12ba917f421c584431e2fda75ed2d9ad01b990872124409a32ceab21901b0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LefXvvUyBBKs2LEbGAHyPS/a7XtQnS+6DAzLgsDIHK59fw0nhbOJwgepf6YdI3OahDVZkOd6WdQHfQV3ScrpAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:57:12.058904Z","bundle_sha256":"d3309b88ca00f2a5f859e4b08222110fd4b84138ea00ab711e14e2ffb7f2feef"}}