{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:25VVJVO7LFYZZ674NI2PATX3IY","short_pith_number":"pith:25VVJVO7","canonical_record":{"source":{"id":"2403.12895","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T16:48:40Z","cross_cats_sorted":[],"title_canon_sha256":"e6bdb2a13a8c6f06c328294afd80c83e5ff0ae6e102e81af8f9223352706e5db","abstract_canon_sha256":"77a6ac34505e688ad2d20d7354cc029ac0f33ca0d2fa882e216f4acaa5f56f72"},"schema_version":"1.0"},"canonical_sha256":"d76b54d5df59719cfbfc6a34f04efb4616c0dfc9842252e62709a19515c11a9d","source":{"kind":"arxiv","id":"2403.12895","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12895","created_at":"2026-07-05T07:58:09Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12895v1","created_at":"2026-07-05T07:58:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12895","created_at":"2026-07-05T07:58:09Z"},{"alias_kind":"pith_short_12","alias_value":"25VVJVO7LFYZ","created_at":"2026-07-05T07:58:09Z"},{"alias_kind":"pith_short_16","alias_value":"25VVJVO7LFYZZ674","created_at":"2026-07-05T07:58:09Z"},{"alias_kind":"pith_short_8","alias_value":"25VVJVO7","created_at":"2026-07-05T07:58:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:25VVJVO7LFYZZ674NI2PATX3IY","target":"record","payload":{"canonical_record":{"source":{"id":"2403.12895","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T16:48:40Z","cross_cats_sorted":[],"title_canon_sha256":"e6bdb2a13a8c6f06c328294afd80c83e5ff0ae6e102e81af8f9223352706e5db","abstract_canon_sha256":"77a6ac34505e688ad2d20d7354cc029ac0f33ca0d2fa882e216f4acaa5f56f72"},"schema_version":"1.0"},"canonical_sha256":"d76b54d5df59719cfbfc6a34f04efb4616c0dfc9842252e62709a19515c11a9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:09.207344Z","signature_b64":"STyNugaVD0Jxey1Wl5cYKyHkfsUSrIL2DOv2vmwxFZBezJcbV5vBFve4TsSDyhwvH331D8zCwMMqiq8LPL6jBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d76b54d5df59719cfbfc6a34f04efb4616c0dfc9842252e62709a19515c11a9d","last_reissued_at":"2026-07-05T07:58:09.206603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:09.206603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.12895","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":"2026-07-05T07:58:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"caKIy+O1RPSL6E34scE1PjkD3vxEjZ7RRwdHoQ0L/zmD0iQ15U0irtqQOsYJHYgHgZYglqEnArTG2jmRPC1OAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:01:53.747931Z"},"content_sha256":"2b26826cda1dc26739e12a8ef26fc101771211e329e5cc0415453230a28e3d53","schema_version":"1.0","event_id":"sha256:2b26826cda1dc26739e12a8ef26fc101771211e329e5cc0415453230a28e3d53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:25VVJVO7LFYZZ674NI2PATX3IY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anwen Hu, Bo Zhang, Chen Li, Fei Huang, Haiyang Xu, Jiabo Ye, Jingren Zhou, Ji Zhang, Liang Zhang, Ming Yan, Qin Jin","submitted_at":"2024-03-19T16:48:40Z","abstract_excerpt":"Structure information is critical for understanding the semantics of text-rich images, such as documents, tables, and charts. Existing Multimodal Large Language Models (MLLMs) for Visual Document Understanding are equipped with text recognition ability but lack general structure understanding abilities for text-rich document images. In this work, we emphasize the importance of structure information in Visual Document Understanding and propose the Unified Structure Learning to boost the performance of MLLMs. Our Unified Structure Learning comprises structure-aware parsing tasks and multi-graine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12895","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/2403.12895/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":"2026-07-05T07:58:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"35RuK+Sg7i49knWutgidkkLAoNssOJjM1fJFqbrd4EUHANar2kPW2Sq6rVRNnmiVo8j8m14okgMb7tdDurinAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:01:53.748548Z"},"content_sha256":"e1a3361c920112cd2e3cbbb3bcb6d3f3dd56f2bb57d9c7a2008e1aff5ad8eb0d","schema_version":"1.0","event_id":"sha256:e1a3361c920112cd2e3cbbb3bcb6d3f3dd56f2bb57d9c7a2008e1aff5ad8eb0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/25VVJVO7LFYZZ674NI2PATX3IY/bundle.json","state_url":"https://pith.science/pith/25VVJVO7LFYZZ674NI2PATX3IY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/25VVJVO7LFYZZ674NI2PATX3IY/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":"2026-08-06T06:01:53Z","links":{"resolver":"https://pith.science/pith/25VVJVO7LFYZZ674NI2PATX3IY","bundle":"https://pith.science/pith/25VVJVO7LFYZZ674NI2PATX3IY/bundle.json","state":"https://pith.science/pith/25VVJVO7LFYZZ674NI2PATX3IY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/25VVJVO7LFYZZ674NI2PATX3IY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:25VVJVO7LFYZZ674NI2PATX3IY","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":"77a6ac34505e688ad2d20d7354cc029ac0f33ca0d2fa882e216f4acaa5f56f72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T16:48:40Z","title_canon_sha256":"e6bdb2a13a8c6f06c328294afd80c83e5ff0ae6e102e81af8f9223352706e5db"},"schema_version":"1.0","source":{"id":"2403.12895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12895","created_at":"2026-07-05T07:58:09Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12895v1","created_at":"2026-07-05T07:58:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12895","created_at":"2026-07-05T07:58:09Z"},{"alias_kind":"pith_short_12","alias_value":"25VVJVO7LFYZ","created_at":"2026-07-05T07:58:09Z"},{"alias_kind":"pith_short_16","alias_value":"25VVJVO7LFYZZ674","created_at":"2026-07-05T07:58:09Z"},{"alias_kind":"pith_short_8","alias_value":"25VVJVO7","created_at":"2026-07-05T07:58:09Z"}],"graph_snapshots":[{"event_id":"sha256:e1a3361c920112cd2e3cbbb3bcb6d3f3dd56f2bb57d9c7a2008e1aff5ad8eb0d","target":"graph","created_at":"2026-07-05T07:58:09Z","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/2403.12895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Structure information is critical for understanding the semantics of text-rich images, such as documents, tables, and charts. Existing Multimodal Large Language Models (MLLMs) for Visual Document Understanding are equipped with text recognition ability but lack general structure understanding abilities for text-rich document images. In this work, we emphasize the importance of structure information in Visual Document Understanding and propose the Unified Structure Learning to boost the performance of MLLMs. Our Unified Structure Learning comprises structure-aware parsing tasks and multi-graine","authors_text":"Anwen Hu, Bo Zhang, Chen Li, Fei Huang, Haiyang Xu, Jiabo Ye, Jingren Zhou, Ji Zhang, Liang Zhang, Ming Yan, Qin Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T16:48:40Z","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12895","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":"sha256:2b26826cda1dc26739e12a8ef26fc101771211e329e5cc0415453230a28e3d53","target":"record","created_at":"2026-07-05T07:58:09Z","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":"77a6ac34505e688ad2d20d7354cc029ac0f33ca0d2fa882e216f4acaa5f56f72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T16:48:40Z","title_canon_sha256":"e6bdb2a13a8c6f06c328294afd80c83e5ff0ae6e102e81af8f9223352706e5db"},"schema_version":"1.0","source":{"id":"2403.12895","kind":"arxiv","version":1}},"canonical_sha256":"d76b54d5df59719cfbfc6a34f04efb4616c0dfc9842252e62709a19515c11a9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d76b54d5df59719cfbfc6a34f04efb4616c0dfc9842252e62709a19515c11a9d","first_computed_at":"2026-07-05T07:58:09.206603Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:09.206603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"STyNugaVD0Jxey1Wl5cYKyHkfsUSrIL2DOv2vmwxFZBezJcbV5vBFve4TsSDyhwvH331D8zCwMMqiq8LPL6jBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:09.207344Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b26826cda1dc26739e12a8ef26fc101771211e329e5cc0415453230a28e3d53","sha256:e1a3361c920112cd2e3cbbb3bcb6d3f3dd56f2bb57d9c7a2008e1aff5ad8eb0d"],"state_sha256":"99ea2d7d9c4fbcca037f182bb8a088f630e6cf17dbd11fdbb2a01f708745f5e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CRLPcXjR3/IhMO/XUQ+VoyYMdsxVvl/IUB+taSqsr03GY64Mnoq6IfZ9L/QpsEzEQVTcssp5K0yVHDT49LswBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:01:53.754054Z","bundle_sha256":"80ae315ec3ac84ee41127105f6551ad2e2411b022a668a44a48f1ef76eb75aed"}}