{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:K6MHR2YGVIJ7FSQFVMB7FBDQZ3","short_pith_number":"pith:K6MHR2YG","canonical_record":{"source":{"id":"2309.11419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T15:50:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"485f368a1332e176d880a286a97950896fca232e698e9fc87884487507f0a335","abstract_canon_sha256":"fab71a5db0f36c757aa19c3ec3d0d6bd10ba71a34ab580caa8bcedeee099006c"},"schema_version":"1.0"},"canonical_sha256":"579878eb06aa13f2ca05ab03f28470cef0681fdc1702e970f905162bb9c758d1","source":{"kind":"arxiv","id":"2309.11419","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11419","created_at":"2026-07-05T08:57:34Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11419v2","created_at":"2026-07-05T08:57:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11419","created_at":"2026-07-05T08:57:34Z"},{"alias_kind":"pith_short_12","alias_value":"K6MHR2YGVIJ7","created_at":"2026-07-05T08:57:34Z"},{"alias_kind":"pith_short_16","alias_value":"K6MHR2YGVIJ7FSQF","created_at":"2026-07-05T08:57:34Z"},{"alias_kind":"pith_short_8","alias_value":"K6MHR2YG","created_at":"2026-07-05T08:57:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:K6MHR2YGVIJ7FSQFVMB7FBDQZ3","target":"record","payload":{"canonical_record":{"source":{"id":"2309.11419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T15:50:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"485f368a1332e176d880a286a97950896fca232e698e9fc87884487507f0a335","abstract_canon_sha256":"fab71a5db0f36c757aa19c3ec3d0d6bd10ba71a34ab580caa8bcedeee099006c"},"schema_version":"1.0"},"canonical_sha256":"579878eb06aa13f2ca05ab03f28470cef0681fdc1702e970f905162bb9c758d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:34.052440Z","signature_b64":"nVwskUJI/2LcsU+ao91L+HlvyA0oIG2x4VmDQtA8JnbtosFUTgWUeDmek9S+ATPp4Li2ZTKhYxMVQ1pCKgOWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"579878eb06aa13f2ca05ab03f28470cef0681fdc1702e970f905162bb9c758d1","last_reissued_at":"2026-07-05T08:57:34.051946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:34.051946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.11419","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":"2026-07-05T08:57:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R5NF2fJg8e292faaLslA2+5J4roFyH/Txkp06VhVROokS8wNWnrmM4K8QGQwAEXQqAouaeloZQXZ2htJbp5qDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T21:20:33.629498Z"},"content_sha256":"8c7dcc719b53c1f8fcb6d4d0d6e5ffc7b7dc5203457ccf9a00579cb66a86616e","schema_version":"1.0","event_id":"sha256:8c7dcc719b53c1f8fcb6d4d0d6e5ffc7b7dc5203457ccf9a00579cb66a86616e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:K6MHR2YGVIJ7FSQFVMB7FBDQZ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KOSMOS-2.5: A Multimodal Literate Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Cha Zhang, Furu Wei, Guoxin Wang, Jingye Chen, Lei Cui, Li Dong, Shaohan Huang, Shaoxiang Wu, Shuming Ma, Tengchao Lv, Weiyao Luo, Wenhui Wang, Yaoyao Chang, Yilin Jia, Yupan Huang, Yuzhong Zhao","submitted_at":"2023-09-20T15:50:08Z","abstract_excerpt":"The automatic reading of text-intensive images represents a significant advancement toward achieving Artificial General Intelligence (AGI). In this paper we present KOSMOS-2.5, a multimodal literate model for machine reading of text-intensive images. Pre-trained on a large-scale corpus of text-intensive images, KOSMOS-2.5 excels in two distinct yet complementary transcription tasks: (1) generating spatially-aware text blocks, where each block of text is assigned spatial coordinates within the image, and (2) producing structured text output that captures both style and structure in markdown for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11419","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/2309.11419/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":"2026-07-05T08:57:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Egg72yhIo0wfrGuFyNfHJFE05+OU+EbQAPUPMk8jpMnG/zwLnotI6P7NnoxdejESPlzTXyLHDspaSy53TH1dBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T21:20:33.629871Z"},"content_sha256":"2d75a07ca9cf6135da7ed59a332565d6021dec6067ef9371c90eddad87e2b38d","schema_version":"1.0","event_id":"sha256:2d75a07ca9cf6135da7ed59a332565d6021dec6067ef9371c90eddad87e2b38d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6MHR2YGVIJ7FSQFVMB7FBDQZ3/bundle.json","state_url":"https://pith.science/pith/K6MHR2YGVIJ7FSQFVMB7FBDQZ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6MHR2YGVIJ7FSQFVMB7FBDQZ3/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":"2026-07-21T21:20:33Z","links":{"resolver":"https://pith.science/pith/K6MHR2YGVIJ7FSQFVMB7FBDQZ3","bundle":"https://pith.science/pith/K6MHR2YGVIJ7FSQFVMB7FBDQZ3/bundle.json","state":"https://pith.science/pith/K6MHR2YGVIJ7FSQFVMB7FBDQZ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6MHR2YGVIJ7FSQFVMB7FBDQZ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K6MHR2YGVIJ7FSQFVMB7FBDQZ3","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":"fab71a5db0f36c757aa19c3ec3d0d6bd10ba71a34ab580caa8bcedeee099006c","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T15:50:08Z","title_canon_sha256":"485f368a1332e176d880a286a97950896fca232e698e9fc87884487507f0a335"},"schema_version":"1.0","source":{"id":"2309.11419","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11419","created_at":"2026-07-05T08:57:34Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11419v2","created_at":"2026-07-05T08:57:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11419","created_at":"2026-07-05T08:57:34Z"},{"alias_kind":"pith_short_12","alias_value":"K6MHR2YGVIJ7","created_at":"2026-07-05T08:57:34Z"},{"alias_kind":"pith_short_16","alias_value":"K6MHR2YGVIJ7FSQF","created_at":"2026-07-05T08:57:34Z"},{"alias_kind":"pith_short_8","alias_value":"K6MHR2YG","created_at":"2026-07-05T08:57:34Z"}],"graph_snapshots":[{"event_id":"sha256:2d75a07ca9cf6135da7ed59a332565d6021dec6067ef9371c90eddad87e2b38d","target":"graph","created_at":"2026-07-05T08:57:34Z","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/2309.11419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The automatic reading of text-intensive images represents a significant advancement toward achieving Artificial General Intelligence (AGI). In this paper we present KOSMOS-2.5, a multimodal literate model for machine reading of text-intensive images. Pre-trained on a large-scale corpus of text-intensive images, KOSMOS-2.5 excels in two distinct yet complementary transcription tasks: (1) generating spatially-aware text blocks, where each block of text is assigned spatial coordinates within the image, and (2) producing structured text output that captures both style and structure in markdown for","authors_text":"Cha Zhang, Furu Wei, Guoxin Wang, Jingye Chen, Lei Cui, Li Dong, Shaohan Huang, Shaoxiang Wu, Shuming Ma, Tengchao Lv, Weiyao Luo, Wenhui Wang, Yaoyao Chang, Yilin Jia, Yupan Huang, Yuzhong Zhao","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T15:50:08Z","title":"KOSMOS-2.5: A Multimodal Literate Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11419","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":"sha256:8c7dcc719b53c1f8fcb6d4d0d6e5ffc7b7dc5203457ccf9a00579cb66a86616e","target":"record","created_at":"2026-07-05T08:57:34Z","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":"fab71a5db0f36c757aa19c3ec3d0d6bd10ba71a34ab580caa8bcedeee099006c","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T15:50:08Z","title_canon_sha256":"485f368a1332e176d880a286a97950896fca232e698e9fc87884487507f0a335"},"schema_version":"1.0","source":{"id":"2309.11419","kind":"arxiv","version":2}},"canonical_sha256":"579878eb06aa13f2ca05ab03f28470cef0681fdc1702e970f905162bb9c758d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"579878eb06aa13f2ca05ab03f28470cef0681fdc1702e970f905162bb9c758d1","first_computed_at":"2026-07-05T08:57:34.051946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:34.051946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nVwskUJI/2LcsU+ao91L+HlvyA0oIG2x4VmDQtA8JnbtosFUTgWUeDmek9S+ATPp4Li2ZTKhYxMVQ1pCKgOWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:34.052440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.11419","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c7dcc719b53c1f8fcb6d4d0d6e5ffc7b7dc5203457ccf9a00579cb66a86616e","sha256:2d75a07ca9cf6135da7ed59a332565d6021dec6067ef9371c90eddad87e2b38d"],"state_sha256":"d53690e864abcb31d5c85fa27e9cb649f14d847a9aea59cd5c6f082a33938616"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xh6wbAKCT4GKtkukRF6snWHMrImWzJkowoYS1+6MB4hKpuLyqzY2j04CZUvm6yinWdecgiGQO5vAYi+AEKAPCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T21:20:33.631912Z","bundle_sha256":"1e9312151346e5ae277451a22193bd496960d32165e8c45a88481eac02533083"}}