{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IW4ZWFO6WICIDDYJIDAFFUTMZP","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":"935ec59c068cf0dee099fe39e1a98fe329fdad9b37b6e29df0bf85f4ce592929","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-19T08:41:21Z","title_canon_sha256":"6c3a8ed5acf96cbb91144a3806ce9d45f67f5b5dd5895137bcd38f749408293a"},"schema_version":"1.0","source":{"id":"2409.12568","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12568","created_at":"2026-07-05T09:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12568v1","created_at":"2026-07-05T09:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12568","created_at":"2026-07-05T09:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"IW4ZWFO6WICI","created_at":"2026-07-05T09:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"IW4ZWFO6WICIDDYJ","created_at":"2026-07-05T09:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"IW4ZWFO6","created_at":"2026-07-05T09:09:08Z"}],"graph_snapshots":[{"event_id":"sha256:5edd67e59c2647b6028bcacff1b8eb164f5f95ca7ab6f1ee228af9d775b8fa44","target":"graph","created_at":"2026-07-05T09:09:08Z","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/2409.12568/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training on large-scale, high-quality datasets is crucial for enhancing the reasoning capabilities of Large Language Models (LLMs), especially in specialized domains such as mathematics. Despite the recognized importance, the Multimodal LLMs (MLLMs) field currently lacks a comprehensive open-source pre-training dataset specifically designed for mathematical reasoning. To address this gap, we introduce InfiMM-WebMath-40B, a high-quality dataset of interleaved image-text documents. It comprises 24 million web pages, 85 million associated image URLs, and 40 billion text tokens, all meticulous","authors_text":"Haogeng Liu, Huaibo Huang, Qihang Fan, Quanzeng You, Ran He, Xiaotian Han, Xuefeng Hu, Yiqi Wang, Yiren Jian, Yuang Ai, Zhenheng Yang","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-19T08:41:21Z","title":"InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12568","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":"sha256:75685b303170bd2b6e502c032ab5ac228e51e7af37cadb21ead18e6c4d0a789a","target":"record","created_at":"2026-07-05T09:09:08Z","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":"935ec59c068cf0dee099fe39e1a98fe329fdad9b37b6e29df0bf85f4ce592929","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-19T08:41:21Z","title_canon_sha256":"6c3a8ed5acf96cbb91144a3806ce9d45f67f5b5dd5895137bcd38f749408293a"},"schema_version":"1.0","source":{"id":"2409.12568","kind":"arxiv","version":1}},"canonical_sha256":"45b99b15deb204818f0940c052d26ccbe35be8bb468dce3955552619a4e269ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45b99b15deb204818f0940c052d26ccbe35be8bb468dce3955552619a4e269ea","first_computed_at":"2026-07-05T09:09:08.970389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:08.970389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x+vQatVs8gK0f1PwVcARVLOe1Om72m4u229alhz5G+6ZUn0vqBDcXkrD4urTtM3vYwqctZAqoeuxfrJB5GkTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:08.970803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12568","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75685b303170bd2b6e502c032ab5ac228e51e7af37cadb21ead18e6c4d0a789a","sha256:5edd67e59c2647b6028bcacff1b8eb164f5f95ca7ab6f1ee228af9d775b8fa44"],"state_sha256":"8abf4a67bd9e977305e91d62a001324942404a8523d35f7eabf47bd1a3218507"}