{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3MZKSOADVQZAPTFSGJYSUHF63T","short_pith_number":"pith:3MZKSOAD","canonical_record":{"source":{"id":"2410.21311","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T16:00:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4aca1a95a9636a078425906a28ee0f6afe9412aefeb289b87f0089078efcf19","abstract_canon_sha256":"06f44b2a98d057c70ed7bc3ad2638caac716722d68aa426ec2008365a2b7575d"},"schema_version":"1.0"},"canonical_sha256":"db32a93803ac3207ccb232712a1cbedccf206d8716f6aea330c8c3a3900554a4","source":{"kind":"arxiv","id":"2410.21311","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21311","created_at":"2026-07-05T09:27:26Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21311v1","created_at":"2026-07-05T09:27:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21311","created_at":"2026-07-05T09:27:26Z"},{"alias_kind":"pith_short_12","alias_value":"3MZKSOADVQZA","created_at":"2026-07-05T09:27:26Z"},{"alias_kind":"pith_short_16","alias_value":"3MZKSOADVQZAPTFS","created_at":"2026-07-05T09:27:26Z"},{"alias_kind":"pith_short_8","alias_value":"3MZKSOAD","created_at":"2026-07-05T09:27:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3MZKSOADVQZAPTFSGJYSUHF63T","target":"record","payload":{"canonical_record":{"source":{"id":"2410.21311","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T16:00:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4aca1a95a9636a078425906a28ee0f6afe9412aefeb289b87f0089078efcf19","abstract_canon_sha256":"06f44b2a98d057c70ed7bc3ad2638caac716722d68aa426ec2008365a2b7575d"},"schema_version":"1.0"},"canonical_sha256":"db32a93803ac3207ccb232712a1cbedccf206d8716f6aea330c8c3a3900554a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:26.583220Z","signature_b64":"Yd50lZMtXNzBcQ2OfvGBIxHHX2iFk82RfPWFGsBulIsOsrvDtF7zSBRfG2WIVSzM/zwtYXfqc22ACWESh9TtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db32a93803ac3207ccb232712a1cbedccf206d8716f6aea330c8c3a3900554a4","last_reissued_at":"2026-07-05T09:27:26.582760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:26.582760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.21311","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":"2026-07-05T09:27:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xHxwYQr4c3b5BxRU4Y/N05OqtJqMQzh8yzBBfofjdYFG7EO0ciSDH2n85x/+AsbFibvrEjuiLfykJ/6NbDEiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:47:42.474432Z"},"content_sha256":"8a09f5c60b4168bedf01997339e5df2712c13afd983768f55fb7904d973d419d","schema_version":"1.0","event_id":"sha256:8a09f5c60b4168bedf01997339e5df2712c13afd983768f55fb7904d973d419d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3MZKSOADVQZAPTFSGJYSUHF63T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Wang, Fengbin Zhu, Fuli Feng, Haohui Wu, Huanbo Luan, Tat Seng Chua, Wenjie Wang, Xiang Yao Ng, Ziyang Liu","submitted_at":"2024-10-25T16:00:55Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have achieved remarkable performance in many vision-language tasks, yet their capabilities in fine-grained visual understanding remain insufficiently evaluated. Existing benchmarks either contain limited fine-grained evaluation samples that are mixed with other data, or are confined to object-level assessments in natural images. To holistically assess LVLMs' fine-grained visual understanding capabilities, we propose using document images with multi-granularity and multi-modal information to supplement natural images. In this light, we construct MMDocBench, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21311","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/2410.21311/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":"2026-07-05T09:27:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xan+BFCkrScZrveTFyZalIXAYBlnc3/+vU4rQsrsPg1jmCt5/VSupPiFIi/PwVEdeP2oPMKUzgmYzXTGdboQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:47:42.474982Z"},"content_sha256":"d014771f32afba4f3ba340223bdd606b40000592b31fba03c989a1f0a846ee66","schema_version":"1.0","event_id":"sha256:d014771f32afba4f3ba340223bdd606b40000592b31fba03c989a1f0a846ee66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3MZKSOADVQZAPTFSGJYSUHF63T/bundle.json","state_url":"https://pith.science/pith/3MZKSOADVQZAPTFSGJYSUHF63T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3MZKSOADVQZAPTFSGJYSUHF63T/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":"2026-08-09T09:47:42Z","links":{"resolver":"https://pith.science/pith/3MZKSOADVQZAPTFSGJYSUHF63T","bundle":"https://pith.science/pith/3MZKSOADVQZAPTFSGJYSUHF63T/bundle.json","state":"https://pith.science/pith/3MZKSOADVQZAPTFSGJYSUHF63T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3MZKSOADVQZAPTFSGJYSUHF63T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3MZKSOADVQZAPTFSGJYSUHF63T","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":"06f44b2a98d057c70ed7bc3ad2638caac716722d68aa426ec2008365a2b7575d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T16:00:55Z","title_canon_sha256":"a4aca1a95a9636a078425906a28ee0f6afe9412aefeb289b87f0089078efcf19"},"schema_version":"1.0","source":{"id":"2410.21311","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21311","created_at":"2026-07-05T09:27:26Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21311v1","created_at":"2026-07-05T09:27:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21311","created_at":"2026-07-05T09:27:26Z"},{"alias_kind":"pith_short_12","alias_value":"3MZKSOADVQZA","created_at":"2026-07-05T09:27:26Z"},{"alias_kind":"pith_short_16","alias_value":"3MZKSOADVQZAPTFS","created_at":"2026-07-05T09:27:26Z"},{"alias_kind":"pith_short_8","alias_value":"3MZKSOAD","created_at":"2026-07-05T09:27:26Z"}],"graph_snapshots":[{"event_id":"sha256:d014771f32afba4f3ba340223bdd606b40000592b31fba03c989a1f0a846ee66","target":"graph","created_at":"2026-07-05T09:27:26Z","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/2410.21311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) have achieved remarkable performance in many vision-language tasks, yet their capabilities in fine-grained visual understanding remain insufficiently evaluated. Existing benchmarks either contain limited fine-grained evaluation samples that are mixed with other data, or are confined to object-level assessments in natural images. To holistically assess LVLMs' fine-grained visual understanding capabilities, we propose using document images with multi-granularity and multi-modal information to supplement natural images. In this light, we construct MMDocBench, ","authors_text":"Chao Wang, Fengbin Zhu, Fuli Feng, Haohui Wu, Huanbo Luan, Tat Seng Chua, Wenjie Wang, Xiang Yao Ng, Ziyang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T16:00:55Z","title":"MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21311","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":"sha256:8a09f5c60b4168bedf01997339e5df2712c13afd983768f55fb7904d973d419d","target":"record","created_at":"2026-07-05T09:27:26Z","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":"06f44b2a98d057c70ed7bc3ad2638caac716722d68aa426ec2008365a2b7575d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T16:00:55Z","title_canon_sha256":"a4aca1a95a9636a078425906a28ee0f6afe9412aefeb289b87f0089078efcf19"},"schema_version":"1.0","source":{"id":"2410.21311","kind":"arxiv","version":1}},"canonical_sha256":"db32a93803ac3207ccb232712a1cbedccf206d8716f6aea330c8c3a3900554a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db32a93803ac3207ccb232712a1cbedccf206d8716f6aea330c8c3a3900554a4","first_computed_at":"2026-07-05T09:27:26.582760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:26.582760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yd50lZMtXNzBcQ2OfvGBIxHHX2iFk82RfPWFGsBulIsOsrvDtF7zSBRfG2WIVSzM/zwtYXfqc22ACWESh9TtDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:26.583220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21311","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a09f5c60b4168bedf01997339e5df2712c13afd983768f55fb7904d973d419d","sha256:d014771f32afba4f3ba340223bdd606b40000592b31fba03c989a1f0a846ee66"],"state_sha256":"4fba876efd7f4c05ff99473dc37c450217de83a30f50eb1a1cc0fa54528cdb6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9YCiPaGrvfptkbNia9gFm/bUbaYKenTI6wVX9zWTnMokXl4ezO24VjaJ1mqNVECpB7oZHzdZ+EAmnRsl7phECA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:47:42.483997Z","bundle_sha256":"a4a13ed0a33b180c2f2fa5201017b02e8a7933f58ff9b8bfe5def4e39e00b9b4"}}