{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZQMQYV3YQIGGNK3YYPEKIXYFUV","short_pith_number":"pith:ZQMQYV3Y","canonical_record":{"source":{"id":"2404.06918","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T11:10:50Z","cross_cats_sorted":[],"title_canon_sha256":"a175dc93f8d1c0ca2403212b31ba743c618dddaecc74c6c271f25acf8546ef3e","abstract_canon_sha256":"2557709e1f926303cc7d4134d2c9890bacbd3da6c883c5d953f469394675d961"},"schema_version":"1.0"},"canonical_sha256":"cc190c5778820c66ab78c3c8a45f05a56d87c0c33ccd910c53dc5306ffb8eeba","source":{"kind":"arxiv","id":"2404.06918","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06918","created_at":"2026-07-05T08:06:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06918v1","created_at":"2026-07-05T08:06:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06918","created_at":"2026-07-05T08:06:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZQMQYV3YQIGG","created_at":"2026-07-05T08:06:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZQMQYV3YQIGGNK3Y","created_at":"2026-07-05T08:06:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZQMQYV3Y","created_at":"2026-07-05T08:06:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZQMQYV3YQIGGNK3YYPEKIXYFUV","target":"record","payload":{"canonical_record":{"source":{"id":"2404.06918","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T11:10:50Z","cross_cats_sorted":[],"title_canon_sha256":"a175dc93f8d1c0ca2403212b31ba743c618dddaecc74c6c271f25acf8546ef3e","abstract_canon_sha256":"2557709e1f926303cc7d4134d2c9890bacbd3da6c883c5d953f469394675d961"},"schema_version":"1.0"},"canonical_sha256":"cc190c5778820c66ab78c3c8a45f05a56d87c0c33ccd910c53dc5306ffb8eeba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:32.231620Z","signature_b64":"HSW5mCzYKSFLSAFAgpmVGDePm2yXspnjj9gCcRj+KEnSXOVTknXqRt6GPtiF/O/xufC4iVt1zfLJTqO+wAnqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc190c5778820c66ab78c3c8a45f05a56d87c0c33ccd910c53dc5306ffb8eeba","last_reissued_at":"2026-07-05T08:06:32.231163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:32.231163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.06918","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":"2026-07-05T08:06:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VvuwLlhq94dE2zpMH5W7PaskSXuav7qsS+KklCRoqYwUCm0R6ME1mGrZ7VFTtH1ryufuhOdNTSyOVe0gvNEqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:39:24.622469Z"},"content_sha256":"1b348161d68af8968819abe5a8824ea528f39aab9c9b5c19dce1a7f14e0c214c","schema_version":"1.0","event_id":"sha256:1b348161d68af8968819abe5a8824ea528f39aab9c9b5c19dce1a7f14e0c214c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZQMQYV3YQIGGNK3YYPEKIXYFUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HRVDA: High-Resolution Visual Document Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaohu Liu, Deqiang Jiang, Haoyu Cao, Kun Yin, Linli Xu, Xinghua Jiang, Xing Sun, Xin Li, Yinsong Liu","submitted_at":"2024-04-10T11:10:50Z","abstract_excerpt":"Leveraging vast training data, multimodal large language models (MLLMs) have demonstrated formidable general visual comprehension capabilities and achieved remarkable performance across various tasks. However, their performance in visual document understanding still leaves much room for improvement. This discrepancy is primarily attributed to the fact that visual document understanding is a fine-grained prediction task. In natural scenes, MLLMs typically use low-resolution images, leading to a substantial loss of visual information. Furthermore, general-purpose MLLMs do not excel in handling d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06918","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/2404.06918/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":"2026-07-05T08:06:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2rJJx0usWkwfMQXGktUWWLdb5fK1l9SabNaDTYMgKsh5wfGMyAqDLN7b2LC4GUg+5M0VdROe/kHk4MRCJ4LNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:39:24.622843Z"},"content_sha256":"1338daf0ec2cb830b91608558cf26988283d367ded581ba0aa3b861ffb753388","schema_version":"1.0","event_id":"sha256:1338daf0ec2cb830b91608558cf26988283d367ded581ba0aa3b861ffb753388"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQMQYV3YQIGGNK3YYPEKIXYFUV/bundle.json","state_url":"https://pith.science/pith/ZQMQYV3YQIGGNK3YYPEKIXYFUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQMQYV3YQIGGNK3YYPEKIXYFUV/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":"2026-07-07T15:39:24Z","links":{"resolver":"https://pith.science/pith/ZQMQYV3YQIGGNK3YYPEKIXYFUV","bundle":"https://pith.science/pith/ZQMQYV3YQIGGNK3YYPEKIXYFUV/bundle.json","state":"https://pith.science/pith/ZQMQYV3YQIGGNK3YYPEKIXYFUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQMQYV3YQIGGNK3YYPEKIXYFUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZQMQYV3YQIGGNK3YYPEKIXYFUV","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":"2557709e1f926303cc7d4134d2c9890bacbd3da6c883c5d953f469394675d961","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T11:10:50Z","title_canon_sha256":"a175dc93f8d1c0ca2403212b31ba743c618dddaecc74c6c271f25acf8546ef3e"},"schema_version":"1.0","source":{"id":"2404.06918","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06918","created_at":"2026-07-05T08:06:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06918v1","created_at":"2026-07-05T08:06:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06918","created_at":"2026-07-05T08:06:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZQMQYV3YQIGG","created_at":"2026-07-05T08:06:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZQMQYV3YQIGGNK3Y","created_at":"2026-07-05T08:06:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZQMQYV3Y","created_at":"2026-07-05T08:06:32Z"}],"graph_snapshots":[{"event_id":"sha256:1338daf0ec2cb830b91608558cf26988283d367ded581ba0aa3b861ffb753388","target":"graph","created_at":"2026-07-05T08:06:32Z","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/2404.06918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Leveraging vast training data, multimodal large language models (MLLMs) have demonstrated formidable general visual comprehension capabilities and achieved remarkable performance across various tasks. However, their performance in visual document understanding still leaves much room for improvement. This discrepancy is primarily attributed to the fact that visual document understanding is a fine-grained prediction task. In natural scenes, MLLMs typically use low-resolution images, leading to a substantial loss of visual information. Furthermore, general-purpose MLLMs do not excel in handling d","authors_text":"Chaohu Liu, Deqiang Jiang, Haoyu Cao, Kun Yin, Linli Xu, Xinghua Jiang, Xing Sun, Xin Li, Yinsong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T11:10:50Z","title":"HRVDA: High-Resolution Visual Document Assistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06918","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":"sha256:1b348161d68af8968819abe5a8824ea528f39aab9c9b5c19dce1a7f14e0c214c","target":"record","created_at":"2026-07-05T08:06:32Z","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":"2557709e1f926303cc7d4134d2c9890bacbd3da6c883c5d953f469394675d961","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T11:10:50Z","title_canon_sha256":"a175dc93f8d1c0ca2403212b31ba743c618dddaecc74c6c271f25acf8546ef3e"},"schema_version":"1.0","source":{"id":"2404.06918","kind":"arxiv","version":1}},"canonical_sha256":"cc190c5778820c66ab78c3c8a45f05a56d87c0c33ccd910c53dc5306ffb8eeba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc190c5778820c66ab78c3c8a45f05a56d87c0c33ccd910c53dc5306ffb8eeba","first_computed_at":"2026-07-05T08:06:32.231163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:32.231163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HSW5mCzYKSFLSAFAgpmVGDePm2yXspnjj9gCcRj+KEnSXOVTknXqRt6GPtiF/O/xufC4iVt1zfLJTqO+wAnqBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:32.231620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06918","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b348161d68af8968819abe5a8824ea528f39aab9c9b5c19dce1a7f14e0c214c","sha256:1338daf0ec2cb830b91608558cf26988283d367ded581ba0aa3b861ffb753388"],"state_sha256":"024fc47cfa32a5ffe0baf7ed4a4b15bd872c8a2510732b23afab589e5425e1b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ECI+Y7uRqCK0aMOwvpUijPzMRFYmqExz4lMbYrJHJM8JaaJJDMbhrQaWk/j16qCmLqKi04AuIHZc40rCeptBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:39:24.624796Z","bundle_sha256":"26758e7581a4a04e6a40f23bd6539d311d560ccfc936f1228fd212a8015581b4"}}