{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Q6LORKQV4CJZHW2F7UDSMVKW3E","short_pith_number":"pith:Q6LORKQV","canonical_record":{"source":{"id":"2308.11592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-08-19T17:32:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0cf8a5d56a2081bf43791d4ae73cacf127e60f33b08861674fa832be776bfe0a","abstract_canon_sha256":"6ead6ff465e25062c5bc2ec6d7fad440f0be2f9d16a5c72466a5a214cedef6bf"},"schema_version":"1.0"},"canonical_sha256":"8796e8aa15e09393db45fd07265556d91a3a4581e9b599fcece40cd27eef044d","source":{"kind":"arxiv","id":"2308.11592","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11592","created_at":"2026-07-05T06:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11592v2","created_at":"2026-07-05T06:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11592","created_at":"2026-07-05T06:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"Q6LORKQV4CJZ","created_at":"2026-07-05T06:47:02Z"},{"alias_kind":"pith_short_16","alias_value":"Q6LORKQV4CJZHW2F","created_at":"2026-07-05T06:47:02Z"},{"alias_kind":"pith_short_8","alias_value":"Q6LORKQV","created_at":"2026-07-05T06:47:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Q6LORKQV4CJZHW2F7UDSMVKW3E","target":"record","payload":{"canonical_record":{"source":{"id":"2308.11592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-08-19T17:32:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0cf8a5d56a2081bf43791d4ae73cacf127e60f33b08861674fa832be776bfe0a","abstract_canon_sha256":"6ead6ff465e25062c5bc2ec6d7fad440f0be2f9d16a5c72466a5a214cedef6bf"},"schema_version":"1.0"},"canonical_sha256":"8796e8aa15e09393db45fd07265556d91a3a4581e9b599fcece40cd27eef044d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:02.558717Z","signature_b64":"wspQT3IfI+gpwQztUlRmNe133gtt2Jd0aRmmakI03/oQZu0ugLJLBAGBY+oGZnZx7nhhXQu85J0lNKMFAeYVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8796e8aa15e09393db45fd07265556d91a3a4581e9b599fcece40cd27eef044d","last_reissued_at":"2026-07-05T06:47:02.558268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:02.558268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.11592","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":"2026-07-05T06:47:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+uoCUWH6eB4n7rvEdsPBfymdb5/KtQGmW/i3gOGnfjX4QDZN6O8VOjojFXjT/gcV4QCg2Sj6E3dD/aBXhgcsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:59:14.093384Z"},"content_sha256":"36eea9663b063447ac2c28346ed26dd8c316773a13ddabaa0757f1129b43dd57","schema_version":"1.0","event_id":"sha256:36eea9663b063447ac2c28346ed26dd8c316773a13ddabaa0757f1129b43dd57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Q6LORKQV4CJZHW2F7UDSMVKW3E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Can Huang, Hao Feng, Houqiang Li, Jinghui Lu, Jingqun Tang, Wengang Zhou, Zijian Wang","submitted_at":"2023-08-19T17:32:34Z","abstract_excerpt":"In the era of Large Language Models (LLMs), tremendous strides have been made in the field of multimodal understanding. However, existing advanced algorithms are limited to effectively utilizing the immense representation capabilities and rich world knowledge inherent to these large pre-trained models, and the beneficial connections among tasks within the context of text-rich scenarios have not been sufficiently explored. In this work, we introduce UniDoc, a novel multimodal model equipped with text detection and recognition capabilities, which are deficient in existing approaches. Moreover, U"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11592","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/2308.11592/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":"2026-07-05T06:47:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EA55h97GWB7UkEOBq3TK7JCz3bjSIDoKuJslsb2zyfzML5xbcyCZDB5RDfbNesvKTWo4UpiH14C8HuykcB9wBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:59:14.093955Z"},"content_sha256":"8889fdee47d37ac8a380813e5f01f9762dbb8b0496d5f6ad32045a92d2f8efea","schema_version":"1.0","event_id":"sha256:8889fdee47d37ac8a380813e5f01f9762dbb8b0496d5f6ad32045a92d2f8efea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6LORKQV4CJZHW2F7UDSMVKW3E/bundle.json","state_url":"https://pith.science/pith/Q6LORKQV4CJZHW2F7UDSMVKW3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6LORKQV4CJZHW2F7UDSMVKW3E/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":"2026-08-17T16:59:14Z","links":{"resolver":"https://pith.science/pith/Q6LORKQV4CJZHW2F7UDSMVKW3E","bundle":"https://pith.science/pith/Q6LORKQV4CJZHW2F7UDSMVKW3E/bundle.json","state":"https://pith.science/pith/Q6LORKQV4CJZHW2F7UDSMVKW3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6LORKQV4CJZHW2F7UDSMVKW3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q6LORKQV4CJZHW2F7UDSMVKW3E","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":"6ead6ff465e25062c5bc2ec6d7fad440f0be2f9d16a5c72466a5a214cedef6bf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-08-19T17:32:34Z","title_canon_sha256":"0cf8a5d56a2081bf43791d4ae73cacf127e60f33b08861674fa832be776bfe0a"},"schema_version":"1.0","source":{"id":"2308.11592","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11592","created_at":"2026-07-05T06:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11592v2","created_at":"2026-07-05T06:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11592","created_at":"2026-07-05T06:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"Q6LORKQV4CJZ","created_at":"2026-07-05T06:47:02Z"},{"alias_kind":"pith_short_16","alias_value":"Q6LORKQV4CJZHW2F","created_at":"2026-07-05T06:47:02Z"},{"alias_kind":"pith_short_8","alias_value":"Q6LORKQV","created_at":"2026-07-05T06:47:02Z"}],"graph_snapshots":[{"event_id":"sha256:8889fdee47d37ac8a380813e5f01f9762dbb8b0496d5f6ad32045a92d2f8efea","target":"graph","created_at":"2026-07-05T06:47:02Z","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/2308.11592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the era of Large Language Models (LLMs), tremendous strides have been made in the field of multimodal understanding. However, existing advanced algorithms are limited to effectively utilizing the immense representation capabilities and rich world knowledge inherent to these large pre-trained models, and the beneficial connections among tasks within the context of text-rich scenarios have not been sufficiently explored. In this work, we introduce UniDoc, a novel multimodal model equipped with text detection and recognition capabilities, which are deficient in existing approaches. Moreover, U","authors_text":"Can Huang, Hao Feng, Houqiang Li, Jinghui Lu, Jingqun Tang, Wengang Zhou, Zijian Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-08-19T17:32:34Z","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11592","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":"sha256:36eea9663b063447ac2c28346ed26dd8c316773a13ddabaa0757f1129b43dd57","target":"record","created_at":"2026-07-05T06:47:02Z","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":"6ead6ff465e25062c5bc2ec6d7fad440f0be2f9d16a5c72466a5a214cedef6bf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-08-19T17:32:34Z","title_canon_sha256":"0cf8a5d56a2081bf43791d4ae73cacf127e60f33b08861674fa832be776bfe0a"},"schema_version":"1.0","source":{"id":"2308.11592","kind":"arxiv","version":2}},"canonical_sha256":"8796e8aa15e09393db45fd07265556d91a3a4581e9b599fcece40cd27eef044d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8796e8aa15e09393db45fd07265556d91a3a4581e9b599fcece40cd27eef044d","first_computed_at":"2026-07-05T06:47:02.558268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:02.558268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wspQT3IfI+gpwQztUlRmNe133gtt2Jd0aRmmakI03/oQZu0ugLJLBAGBY+oGZnZx7nhhXQu85J0lNKMFAeYVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:02.558717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.11592","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36eea9663b063447ac2c28346ed26dd8c316773a13ddabaa0757f1129b43dd57","sha256:8889fdee47d37ac8a380813e5f01f9762dbb8b0496d5f6ad32045a92d2f8efea"],"state_sha256":"52a1f3ad61761d47ba1ae51c1049b17f3c6c39045bedc6a81ff0691fb3361cfd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nt4ZB/8kQbSlTFIZDZmAeL9dVhTYVywB1Gx+0dGpFAWB9KTm69WE5uDB3rkXxO6u8R6bD/os13bUKqZdKP+iDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T16:59:14.102812Z","bundle_sha256":"472a8cd900c252d92df3d58d4013a7849c96e3492a9d472a96edd743c22467c0"}}