{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YY5MUQ7NKALWQLK6G62TWKOGZE","short_pith_number":"pith:YY5MUQ7N","canonical_record":{"source":{"id":"2505.23008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T02:34:36Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"22e33bae4fe5452031f77e89ce44ca271471ee452cb3716252872eda9356872f","abstract_canon_sha256":"e1faa2e4e3afb7ff70984e3fec11a8aaec4f6b92ebcf984520bb39523d01cc09"},"schema_version":"1.0"},"canonical_sha256":"c63aca43ed5017682d5e37b53b29c6c93a0e5c4583dc2fad6b470e19aa010ed6","source":{"kind":"arxiv","id":"2505.23008","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23008","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23008v1","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23008","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"YY5MUQ7NKALW","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"YY5MUQ7NKALWQLK6","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"YY5MUQ7N","created_at":"2026-07-05T11:11:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YY5MUQ7NKALWQLK6G62TWKOGZE","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T02:34:36Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"22e33bae4fe5452031f77e89ce44ca271471ee452cb3716252872eda9356872f","abstract_canon_sha256":"e1faa2e4e3afb7ff70984e3fec11a8aaec4f6b92ebcf984520bb39523d01cc09"},"schema_version":"1.0"},"canonical_sha256":"c63aca43ed5017682d5e37b53b29c6c93a0e5c4583dc2fad6b470e19aa010ed6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:53.400917Z","signature_b64":"oQJjrAVi/ZJnfuuF9JUTVUmwajwtGZHhDLdWVXLgHzXam21CKEtuh+PoRjw9QaE8ZE0EGSVWfVGTeu+z79XVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c63aca43ed5017682d5e37b53b29c6c93a0e5c4583dc2fad6b470e19aa010ed6","last_reissued_at":"2026-07-05T11:11:53.400425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:53.400425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23008","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":"2026-07-05T11:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5GwY9M+nY+2/j0U51RFtKv9BINPcEjC1ft52AP6d87MuB15C9682Jl1V3I7Q+8/aV0ukcJxMDbokiY0/tpcwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:55:20.570552Z"},"content_sha256":"49fb119f5aa1c0340b553145bfab5e5aa6b9e440f274701d94232abd0629956b","schema_version":"1.0","event_id":"sha256:49fb119f5aa1c0340b553145bfab5e5aa6b9e440f274701d94232abd0629956b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YY5MUQ7NKALWQLK6G62TWKOGZE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthetic Document Question Answering in Hungarian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Edward Ma, Etash Guha, Fenglu Hong, Jonathan Li, Nidhi Hiremath, Urmish Thakker, Zoltan Csaki","submitted_at":"2025-05-29T02:34:36Z","abstract_excerpt":"Modern VLMs have achieved near-saturation accuracy in English document visual question-answering (VQA). However, this task remains challenging in lower resource languages due to a dearth of suitable training and evaluation data. In this paper we present scalable methods for curating such datasets by focusing on Hungarian, approximately the 17th highest resource language on the internet. Specifically, we present HuDocVQA and HuDocVQA-manual, document VQA datasets that modern VLMs significantly underperform on compared to English DocVQA. HuDocVQA-manual is a small manually curated dataset based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23008","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/2505.23008/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":"2026-07-05T11:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+1u9sXWJZAbBDVXlm7zdgxEH2+kGhvhuicf6oZgUQWA0RHgyRGK3GwUzn5012eqFfU5LJtdknnJd3zvYClKjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:55:20.570923Z"},"content_sha256":"0d1374a2aa98a682441af09fde9a8893d2381d637933fb8184677ffec1954197","schema_version":"1.0","event_id":"sha256:0d1374a2aa98a682441af09fde9a8893d2381d637933fb8184677ffec1954197"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YY5MUQ7NKALWQLK6G62TWKOGZE/bundle.json","state_url":"https://pith.science/pith/YY5MUQ7NKALWQLK6G62TWKOGZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YY5MUQ7NKALWQLK6G62TWKOGZE/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":"2026-07-07T07:55:20Z","links":{"resolver":"https://pith.science/pith/YY5MUQ7NKALWQLK6G62TWKOGZE","bundle":"https://pith.science/pith/YY5MUQ7NKALWQLK6G62TWKOGZE/bundle.json","state":"https://pith.science/pith/YY5MUQ7NKALWQLK6G62TWKOGZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YY5MUQ7NKALWQLK6G62TWKOGZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YY5MUQ7NKALWQLK6G62TWKOGZE","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":"e1faa2e4e3afb7ff70984e3fec11a8aaec4f6b92ebcf984520bb39523d01cc09","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T02:34:36Z","title_canon_sha256":"22e33bae4fe5452031f77e89ce44ca271471ee452cb3716252872eda9356872f"},"schema_version":"1.0","source":{"id":"2505.23008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23008","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23008v1","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23008","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"YY5MUQ7NKALW","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"YY5MUQ7NKALWQLK6","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"YY5MUQ7N","created_at":"2026-07-05T11:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:0d1374a2aa98a682441af09fde9a8893d2381d637933fb8184677ffec1954197","target":"graph","created_at":"2026-07-05T11:11:53Z","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/2505.23008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern VLMs have achieved near-saturation accuracy in English document visual question-answering (VQA). However, this task remains challenging in lower resource languages due to a dearth of suitable training and evaluation data. In this paper we present scalable methods for curating such datasets by focusing on Hungarian, approximately the 17th highest resource language on the internet. Specifically, we present HuDocVQA and HuDocVQA-manual, document VQA datasets that modern VLMs significantly underperform on compared to English DocVQA. HuDocVQA-manual is a small manually curated dataset based ","authors_text":"Edward Ma, Etash Guha, Fenglu Hong, Jonathan Li, Nidhi Hiremath, Urmish Thakker, Zoltan Csaki","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T02:34:36Z","title":"Synthetic Document Question Answering in Hungarian"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23008","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":"sha256:49fb119f5aa1c0340b553145bfab5e5aa6b9e440f274701d94232abd0629956b","target":"record","created_at":"2026-07-05T11:11:53Z","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":"e1faa2e4e3afb7ff70984e3fec11a8aaec4f6b92ebcf984520bb39523d01cc09","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T02:34:36Z","title_canon_sha256":"22e33bae4fe5452031f77e89ce44ca271471ee452cb3716252872eda9356872f"},"schema_version":"1.0","source":{"id":"2505.23008","kind":"arxiv","version":1}},"canonical_sha256":"c63aca43ed5017682d5e37b53b29c6c93a0e5c4583dc2fad6b470e19aa010ed6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c63aca43ed5017682d5e37b53b29c6c93a0e5c4583dc2fad6b470e19aa010ed6","first_computed_at":"2026-07-05T11:11:53.400425Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:53.400425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oQJjrAVi/ZJnfuuF9JUTVUmwajwtGZHhDLdWVXLgHzXam21CKEtuh+PoRjw9QaE8ZE0EGSVWfVGTeu+z79XVCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:53.400917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49fb119f5aa1c0340b553145bfab5e5aa6b9e440f274701d94232abd0629956b","sha256:0d1374a2aa98a682441af09fde9a8893d2381d637933fb8184677ffec1954197"],"state_sha256":"a8216131273edfd08f3e5be724d13307ee3d2d6a008df7a039328b7faee7e729"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aTF/uAYIKSafEO/BfR5rW8DwzMHogXskj0xG3SmUFRUTqv0xUPhpf4Kc35CGhl6YrZO87bPhMJcgkycMIQuaCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:55:20.573100Z","bundle_sha256":"0e9bb049dfc075d0f2da7d8b644efbab84970a84d27de3179c1d25705588853e"}}