{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TRFYAOALFKREQEET76HLWSZF5B","short_pith_number":"pith:TRFYAOAL","canonical_record":{"source":{"id":"2404.12720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-19T09:00:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4cccfa1ab07cf477563b81ab8513cc7b1bb968b1d58a5a7e91787fe9db2fc7da","abstract_canon_sha256":"2dfcae25a3e650ae68089106ded9a290788790ca416b457699ac8b264ceb16e2"},"schema_version":"1.0"},"canonical_sha256":"9c4b80380b2aa2481093ff8ebb4b25e87a2b5f89e79ea801cfb4fcdb071fb555","source":{"kind":"arxiv","id":"2404.12720","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12720","created_at":"2026-07-05T08:09:58Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12720v1","created_at":"2026-07-05T08:09:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12720","created_at":"2026-07-05T08:09:58Z"},{"alias_kind":"pith_short_12","alias_value":"TRFYAOALFKRE","created_at":"2026-07-05T08:09:58Z"},{"alias_kind":"pith_short_16","alias_value":"TRFYAOALFKREQEET","created_at":"2026-07-05T08:09:58Z"},{"alias_kind":"pith_short_8","alias_value":"TRFYAOAL","created_at":"2026-07-05T08:09:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TRFYAOALFKREQEET76HLWSZF5B","target":"record","payload":{"canonical_record":{"source":{"id":"2404.12720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-19T09:00:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4cccfa1ab07cf477563b81ab8513cc7b1bb968b1d58a5a7e91787fe9db2fc7da","abstract_canon_sha256":"2dfcae25a3e650ae68089106ded9a290788790ca416b457699ac8b264ceb16e2"},"schema_version":"1.0"},"canonical_sha256":"9c4b80380b2aa2481093ff8ebb4b25e87a2b5f89e79ea801cfb4fcdb071fb555","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:58.195963Z","signature_b64":"J3nZY2klTxeoZq6G1dkqo8Q+Ff6UmuoQ3LcQQLRNWUcknLpyEaizAyTAOeiKKpbusU1Tccu1NeeEDQlN1OfNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c4b80380b2aa2481093ff8ebb4b25e87a2b5f89e79ea801cfb4fcdb071fb555","last_reissued_at":"2026-07-05T08:09:58.195475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:58.195475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.12720","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":"2026-07-05T08:09:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EadYzQSJXMvqwVjn1uFDTRLQtaVuxF6bwemafqBla2TnQT2tpeDrHRfdV0nUAyW7v6LDS26Ltw6GbW74JpCiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:05:14.971992Z"},"content_sha256":"f76982729d91b8bc6f8832366703d7e4c28879576a730ae669d7959124427672","schema_version":"1.0","event_id":"sha256:f76982729d91b8bc6f8832366703d7e4c28879576a730ae669d7959124427672"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TRFYAOALFKREQEET76HLWSZF5B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiabin Huang, Kaixuan Ren, Siwen Luo, Soyeon Caren Han, Yihao Ding","submitted_at":"2024-04-19T09:00:05Z","abstract_excerpt":"Document Question Answering (QA) presents a challenge in understanding visually-rich documents (VRD), particularly those dominated by lengthy textual content like research journal articles. Existing studies primarily focus on real-world documents with sparse text, while challenges persist in comprehending the hierarchical semantic relations among multiple pages to locate multimodal components. To address this gap, we propose PDF-MVQA, which is tailored for research journal articles, encompassing multiple pages and multimodal information retrieval. Unlike traditional machine reading comprehensi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12720","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/2404.12720/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":"2026-07-05T08:09:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iQogfnKmZw/ZXqPJD8U3CcK6swNZS/UFp5T1yvtB1FOowSpWvAw1BxwMzBGDg7q98EvaNwuFesw5is3vYGPTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:05:14.972627Z"},"content_sha256":"66c1bafe839afc37af00e0d84dd4ad2d2ceb195bb1a9f52ace7a5e9794b1c2b5","schema_version":"1.0","event_id":"sha256:66c1bafe839afc37af00e0d84dd4ad2d2ceb195bb1a9f52ace7a5e9794b1c2b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TRFYAOALFKREQEET76HLWSZF5B/bundle.json","state_url":"https://pith.science/pith/TRFYAOALFKREQEET76HLWSZF5B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TRFYAOALFKREQEET76HLWSZF5B/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":"2026-08-07T08:05:14Z","links":{"resolver":"https://pith.science/pith/TRFYAOALFKREQEET76HLWSZF5B","bundle":"https://pith.science/pith/TRFYAOALFKREQEET76HLWSZF5B/bundle.json","state":"https://pith.science/pith/TRFYAOALFKREQEET76HLWSZF5B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TRFYAOALFKREQEET76HLWSZF5B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TRFYAOALFKREQEET76HLWSZF5B","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":"2dfcae25a3e650ae68089106ded9a290788790ca416b457699ac8b264ceb16e2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-19T09:00:05Z","title_canon_sha256":"4cccfa1ab07cf477563b81ab8513cc7b1bb968b1d58a5a7e91787fe9db2fc7da"},"schema_version":"1.0","source":{"id":"2404.12720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12720","created_at":"2026-07-05T08:09:58Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12720v1","created_at":"2026-07-05T08:09:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12720","created_at":"2026-07-05T08:09:58Z"},{"alias_kind":"pith_short_12","alias_value":"TRFYAOALFKRE","created_at":"2026-07-05T08:09:58Z"},{"alias_kind":"pith_short_16","alias_value":"TRFYAOALFKREQEET","created_at":"2026-07-05T08:09:58Z"},{"alias_kind":"pith_short_8","alias_value":"TRFYAOAL","created_at":"2026-07-05T08:09:58Z"}],"graph_snapshots":[{"event_id":"sha256:66c1bafe839afc37af00e0d84dd4ad2d2ceb195bb1a9f52ace7a5e9794b1c2b5","target":"graph","created_at":"2026-07-05T08:09:58Z","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/2404.12720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document Question Answering (QA) presents a challenge in understanding visually-rich documents (VRD), particularly those dominated by lengthy textual content like research journal articles. Existing studies primarily focus on real-world documents with sparse text, while challenges persist in comprehending the hierarchical semantic relations among multiple pages to locate multimodal components. To address this gap, we propose PDF-MVQA, which is tailored for research journal articles, encompassing multiple pages and multimodal information retrieval. Unlike traditional machine reading comprehensi","authors_text":"Jiabin Huang, Kaixuan Ren, Siwen Luo, Soyeon Caren Han, Yihao Ding","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-19T09:00:05Z","title":"PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12720","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:f76982729d91b8bc6f8832366703d7e4c28879576a730ae669d7959124427672","target":"record","created_at":"2026-07-05T08:09:58Z","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":"2dfcae25a3e650ae68089106ded9a290788790ca416b457699ac8b264ceb16e2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-19T09:00:05Z","title_canon_sha256":"4cccfa1ab07cf477563b81ab8513cc7b1bb968b1d58a5a7e91787fe9db2fc7da"},"schema_version":"1.0","source":{"id":"2404.12720","kind":"arxiv","version":1}},"canonical_sha256":"9c4b80380b2aa2481093ff8ebb4b25e87a2b5f89e79ea801cfb4fcdb071fb555","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c4b80380b2aa2481093ff8ebb4b25e87a2b5f89e79ea801cfb4fcdb071fb555","first_computed_at":"2026-07-05T08:09:58.195475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:58.195475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J3nZY2klTxeoZq6G1dkqo8Q+Ff6UmuoQ3LcQQLRNWUcknLpyEaizAyTAOeiKKpbusU1Tccu1NeeEDQlN1OfNBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:58.195963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.12720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f76982729d91b8bc6f8832366703d7e4c28879576a730ae669d7959124427672","sha256:66c1bafe839afc37af00e0d84dd4ad2d2ceb195bb1a9f52ace7a5e9794b1c2b5"],"state_sha256":"461d74c1c42b7d0cc22aa1f452bfb3739f82431b10e6861fe76f0ffa91d762ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RjwT8ymFWV8GG01fRnS29h8mUrZHmEOrMlAM4YCyxpV+c6PdJMczXjF8wjg70VXV8ItzN8fYakS69cjoNf+yBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T08:05:14.977689Z","bundle_sha256":"bc71fd127cd33a70171e0d719e0d00a70b87268436707a4cd4e069c1e084007c"}}