{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NDLC6ZRVNVUNHET3UY22E6TO7V","short_pith_number":"pith:NDLC6ZRV","canonical_record":{"source":{"id":"2607.11562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-13T13:43:39Z","cross_cats_sorted":[],"title_canon_sha256":"5ae7015983c6e33aa74968fe790422f26e4e3294f5c43c81d4bf9e504216d2fe","abstract_canon_sha256":"25d05e12407822f2cd839fd8b23d6b5c563765d6b2d2f1bc0aa789ebb99971fc"},"schema_version":"1.0"},"canonical_sha256":"68d62f66356d68d3927ba635a27a6efd605242100f672650abee9b68f74775ad","source":{"kind":"arxiv","id":"2607.11562","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11562","created_at":"2026-07-14T02:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11562v1","created_at":"2026-07-14T02:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11562","created_at":"2026-07-14T02:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"NDLC6ZRVNVUN","created_at":"2026-07-14T02:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"NDLC6ZRVNVUNHET3","created_at":"2026-07-14T02:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"NDLC6ZRV","created_at":"2026-07-14T02:22:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NDLC6ZRVNVUNHET3UY22E6TO7V","target":"record","payload":{"canonical_record":{"source":{"id":"2607.11562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-13T13:43:39Z","cross_cats_sorted":[],"title_canon_sha256":"5ae7015983c6e33aa74968fe790422f26e4e3294f5c43c81d4bf9e504216d2fe","abstract_canon_sha256":"25d05e12407822f2cd839fd8b23d6b5c563765d6b2d2f1bc0aa789ebb99971fc"},"schema_version":"1.0"},"canonical_sha256":"68d62f66356d68d3927ba635a27a6efd605242100f672650abee9b68f74775ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:22:12.129691Z","signature_b64":"i/OS0uLRx9GSFin3Y6Yptai47rGvFMnKOt2QvPWfsPhmb63gVYwWAh6k1D5QgKNyNOYkKizm3oVSk2gmae9bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68d62f66356d68d3927ba635a27a6efd605242100f672650abee9b68f74775ad","last_reissued_at":"2026-07-14T02:22:12.128880Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:22:12.128880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.11562","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":"2026-07-14T02:22:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zrjbHIBoVPvQ+823uhXrb805kSeClRAiLLI6EU31SWcTnB9YG2neeLJSlQUrw80PR6UHxLc7C3Olem0F+MQmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:11:26.334344Z"},"content_sha256":"4f590ca24aa75ce111fc89ed863f78ae07cf46650af21d1ca154130b0a28221c","schema_version":"1.0","event_id":"sha256:4f590ca24aa75ce111fc89ed863f78ae07cf46650af21d1ca154130b0a28221c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NDLC6ZRVNVUNHET3UY22E6TO7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang Luo, Handong Zheng, Jiajun Song, Jiarui Zhang, Qiang Liu, Shuo Zhang, Xiang Bai, Xinhan Wang, Yang Liu, Yuliang Liu, Zhang Li, Zhiyin Ma, Zidun Guo, Ziyang Zhang","submitted_at":"2026-07-13T13:43:39Z","abstract_excerpt":"Mainstream visual encoders are pretrained on natural images and cannot be effectively applied to document images without document-oriented adaptation, as dense text and fine-grained character strokes demand character-level visual perception. We present MonkeyOCRv2, a visual-text pretrained model for document AI. First, we construct MonkeyDoc v2, to our knowledge the largest document-image pretraining corpus, comprising 113 million images spanning 17 languages. Second, we propose a pretraining strategy that jointly learns image-to-text generation and pixel-level document reconstruction: the for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11562","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/2607.11562/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":"2026-07-14T02:22:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5KQ3hNx5ynxxtSMediEAMYUJyX+xR8qCCRYFDcpTYSexDDbMimp7da6bVfTPLhScq2BhmG52upV19aXXQaOUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:11:26.335021Z"},"content_sha256":"30972b1c22b8af2b91dc74661f460b0b706d81eb4cd1dbdd5b65d9c5c570e031","schema_version":"1.0","event_id":"sha256:30972b1c22b8af2b91dc74661f460b0b706d81eb4cd1dbdd5b65d9c5c570e031"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDLC6ZRVNVUNHET3UY22E6TO7V/bundle.json","state_url":"https://pith.science/pith/NDLC6ZRVNVUNHET3UY22E6TO7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDLC6ZRVNVUNHET3UY22E6TO7V/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":"2026-08-04T01:11:26Z","links":{"resolver":"https://pith.science/pith/NDLC6ZRVNVUNHET3UY22E6TO7V","bundle":"https://pith.science/pith/NDLC6ZRVNVUNHET3UY22E6TO7V/bundle.json","state":"https://pith.science/pith/NDLC6ZRVNVUNHET3UY22E6TO7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDLC6ZRVNVUNHET3UY22E6TO7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NDLC6ZRVNVUNHET3UY22E6TO7V","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":"25d05e12407822f2cd839fd8b23d6b5c563765d6b2d2f1bc0aa789ebb99971fc","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-13T13:43:39Z","title_canon_sha256":"5ae7015983c6e33aa74968fe790422f26e4e3294f5c43c81d4bf9e504216d2fe"},"schema_version":"1.0","source":{"id":"2607.11562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11562","created_at":"2026-07-14T02:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11562v1","created_at":"2026-07-14T02:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11562","created_at":"2026-07-14T02:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"NDLC6ZRVNVUN","created_at":"2026-07-14T02:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"NDLC6ZRVNVUNHET3","created_at":"2026-07-14T02:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"NDLC6ZRV","created_at":"2026-07-14T02:22:12Z"}],"graph_snapshots":[{"event_id":"sha256:30972b1c22b8af2b91dc74661f460b0b706d81eb4cd1dbdd5b65d9c5c570e031","target":"graph","created_at":"2026-07-14T02:22:12Z","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/2607.11562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mainstream visual encoders are pretrained on natural images and cannot be effectively applied to document images without document-oriented adaptation, as dense text and fine-grained character strokes demand character-level visual perception. We present MonkeyOCRv2, a visual-text pretrained model for document AI. First, we construct MonkeyDoc v2, to our knowledge the largest document-image pretraining corpus, comprising 113 million images spanning 17 languages. Second, we propose a pretraining strategy that jointly learns image-to-text generation and pixel-level document reconstruction: the for","authors_text":"Dongliang Luo, Handong Zheng, Jiajun Song, Jiarui Zhang, Qiang Liu, Shuo Zhang, Xiang Bai, Xinhan Wang, Yang Liu, Yuliang Liu, Zhang Li, Zhiyin Ma, Zidun Guo, Ziyang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-13T13:43:39Z","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11562","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":"sha256:4f590ca24aa75ce111fc89ed863f78ae07cf46650af21d1ca154130b0a28221c","target":"record","created_at":"2026-07-14T02:22:12Z","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":"25d05e12407822f2cd839fd8b23d6b5c563765d6b2d2f1bc0aa789ebb99971fc","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-13T13:43:39Z","title_canon_sha256":"5ae7015983c6e33aa74968fe790422f26e4e3294f5c43c81d4bf9e504216d2fe"},"schema_version":"1.0","source":{"id":"2607.11562","kind":"arxiv","version":1}},"canonical_sha256":"68d62f66356d68d3927ba635a27a6efd605242100f672650abee9b68f74775ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68d62f66356d68d3927ba635a27a6efd605242100f672650abee9b68f74775ad","first_computed_at":"2026-07-14T02:22:12.128880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T02:22:12.128880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i/OS0uLRx9GSFin3Y6Yptai47rGvFMnKOt2QvPWfsPhmb63gVYwWAh6k1D5QgKNyNOYkKizm3oVSk2gmae9bAA==","signature_status":"signed_v1","signed_at":"2026-07-14T02:22:12.129691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.11562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f590ca24aa75ce111fc89ed863f78ae07cf46650af21d1ca154130b0a28221c","sha256:30972b1c22b8af2b91dc74661f460b0b706d81eb4cd1dbdd5b65d9c5c570e031"],"state_sha256":"1b54c21d44d13aa191cf433811fe38584a479f38ea93bcfe0c828ec210a4b4e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uq8h627tYNQnznrsTndGmFhidRMeUdtxzvu2YeOsjf8wjgBkyJdHRsbIrrTsdCs2oiQeiGrfQ984pGVpb8qlBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T01:11:26.339607Z","bundle_sha256":"800f83e3f12d515d26ba3f328ebaaac21d50ac0e0bcf4e3134ac32b27b9e8b93"}}