{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ERJFW4HUVQ5DIRH33WEVSXXVRL","short_pith_number":"pith:ERJFW4HU","canonical_record":{"source":{"id":"2212.05935","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-07T10:09:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d00b2de65841d90833156f16ec374cdbf5ce41ae53f059071d3758f304ec353b","abstract_canon_sha256":"a3afc1c41059e058f33b742ac2479f3c871de777bfb24685db8531d9a1daa841"},"schema_version":"1.0"},"canonical_sha256":"24525b70f4ac3a3444fbdd89595ef58af6ddc72275c0530f4ee5ec1b93a3bd36","source":{"kind":"arxiv","id":"2212.05935","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.05935","created_at":"2026-07-05T05:57:34Z"},{"alias_kind":"arxiv_version","alias_value":"2212.05935v2","created_at":"2026-07-05T05:57:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05935","created_at":"2026-07-05T05:57:34Z"},{"alias_kind":"pith_short_12","alias_value":"ERJFW4HUVQ5D","created_at":"2026-07-05T05:57:34Z"},{"alias_kind":"pith_short_16","alias_value":"ERJFW4HUVQ5DIRH3","created_at":"2026-07-05T05:57:34Z"},{"alias_kind":"pith_short_8","alias_value":"ERJFW4HU","created_at":"2026-07-05T05:57:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ERJFW4HUVQ5DIRH33WEVSXXVRL","target":"record","payload":{"canonical_record":{"source":{"id":"2212.05935","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-07T10:09:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d00b2de65841d90833156f16ec374cdbf5ce41ae53f059071d3758f304ec353b","abstract_canon_sha256":"a3afc1c41059e058f33b742ac2479f3c871de777bfb24685db8531d9a1daa841"},"schema_version":"1.0"},"canonical_sha256":"24525b70f4ac3a3444fbdd89595ef58af6ddc72275c0530f4ee5ec1b93a3bd36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:34.768743Z","signature_b64":"0Pxxw9e9V/Bm9IrMrA39+kk7EVw5lsa6y8/3+60FupkQaYEXPSD8mmG58Z3A6Z0msdUW0QjLusaA5lVQcDSLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24525b70f4ac3a3444fbdd89595ef58af6ddc72275c0530f4ee5ec1b93a3bd36","last_reissued_at":"2026-07-05T05:57:34.768298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:34.768298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.05935","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:57:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nM04iu6Wm45NuGJM6UMMQo2CBr7MFq5G+WZOKxwznTAg5vSJ7b7eab66lWX+G2U7NweHcrmsYBjaI6dBV6bWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:06:50.081014Z"},"content_sha256":"8e24f360b22aa9d806b91b71fa89cfa62854c4c1a264709e2e38d8c04854fca7","schema_version":"1.0","event_id":"sha256:8e24f360b22aa9d806b91b71fa89cfa62854c4c1a264709e2e38d8c04854fca7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ERJFW4HUVQ5DIRH33WEVSXXVRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical multimodal transformers for Multi-Page DocVQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dimosthenis Karatzas, Ernest Valveny, Rub\\`en Tito","submitted_at":"2022-12-07T10:09:49Z","abstract_excerpt":"Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple pages that should be processed altogether. In this work we extend DocVQA to the multi-page scenario. For that, we first create a new dataset, MP-DocVQA, where questions are posed over multi-page documents instead of single pages. Second, we propose a new hierarchical method, Hi-VT5, based on the T5 architecture, that overcomes the limitations of current metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05935","kind":"arxiv","version":2},"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/2212.05935/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":"2026-07-05T05:57:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"22MvWjHi82Ena3urAQQs4KObjiKwR+xGbHPaf8Oh5H0OTh7aXwltLdvzwhG8aBsC5+ue7dNPRs20KBTEQkvrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:06:50.082056Z"},"content_sha256":"4ea71aa1ba55ec1b92931b6f05a94946b5d8582bfc42a9d926369c3ab7871380","schema_version":"1.0","event_id":"sha256:4ea71aa1ba55ec1b92931b6f05a94946b5d8582bfc42a9d926369c3ab7871380"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ERJFW4HUVQ5DIRH33WEVSXXVRL/bundle.json","state_url":"https://pith.science/pith/ERJFW4HUVQ5DIRH33WEVSXXVRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ERJFW4HUVQ5DIRH33WEVSXXVRL/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":"2026-08-04T15:06:50Z","links":{"resolver":"https://pith.science/pith/ERJFW4HUVQ5DIRH33WEVSXXVRL","bundle":"https://pith.science/pith/ERJFW4HUVQ5DIRH33WEVSXXVRL/bundle.json","state":"https://pith.science/pith/ERJFW4HUVQ5DIRH33WEVSXXVRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ERJFW4HUVQ5DIRH33WEVSXXVRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ERJFW4HUVQ5DIRH33WEVSXXVRL","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":"a3afc1c41059e058f33b742ac2479f3c871de777bfb24685db8531d9a1daa841","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-07T10:09:49Z","title_canon_sha256":"d00b2de65841d90833156f16ec374cdbf5ce41ae53f059071d3758f304ec353b"},"schema_version":"1.0","source":{"id":"2212.05935","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.05935","created_at":"2026-07-05T05:57:34Z"},{"alias_kind":"arxiv_version","alias_value":"2212.05935v2","created_at":"2026-07-05T05:57:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05935","created_at":"2026-07-05T05:57:34Z"},{"alias_kind":"pith_short_12","alias_value":"ERJFW4HUVQ5D","created_at":"2026-07-05T05:57:34Z"},{"alias_kind":"pith_short_16","alias_value":"ERJFW4HUVQ5DIRH3","created_at":"2026-07-05T05:57:34Z"},{"alias_kind":"pith_short_8","alias_value":"ERJFW4HU","created_at":"2026-07-05T05:57:34Z"}],"graph_snapshots":[{"event_id":"sha256:4ea71aa1ba55ec1b92931b6f05a94946b5d8582bfc42a9d926369c3ab7871380","target":"graph","created_at":"2026-07-05T05:57:34Z","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/2212.05935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple pages that should be processed altogether. In this work we extend DocVQA to the multi-page scenario. For that, we first create a new dataset, MP-DocVQA, where questions are posed over multi-page documents instead of single pages. Second, we propose a new hierarchical method, Hi-VT5, based on the T5 architecture, that overcomes the limitations of current metho","authors_text":"Dimosthenis Karatzas, Ernest Valveny, Rub\\`en Tito","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-07T10:09:49Z","title":"Hierarchical multimodal transformers for Multi-Page DocVQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05935","kind":"arxiv","version":2},"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":"sha256:8e24f360b22aa9d806b91b71fa89cfa62854c4c1a264709e2e38d8c04854fca7","target":"record","created_at":"2026-07-05T05:57:34Z","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":"a3afc1c41059e058f33b742ac2479f3c871de777bfb24685db8531d9a1daa841","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-07T10:09:49Z","title_canon_sha256":"d00b2de65841d90833156f16ec374cdbf5ce41ae53f059071d3758f304ec353b"},"schema_version":"1.0","source":{"id":"2212.05935","kind":"arxiv","version":2}},"canonical_sha256":"24525b70f4ac3a3444fbdd89595ef58af6ddc72275c0530f4ee5ec1b93a3bd36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24525b70f4ac3a3444fbdd89595ef58af6ddc72275c0530f4ee5ec1b93a3bd36","first_computed_at":"2026-07-05T05:57:34.768298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:57:34.768298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Pxxw9e9V/Bm9IrMrA39+kk7EVw5lsa6y8/3+60FupkQaYEXPSD8mmG58Z3A6Z0msdUW0QjLusaA5lVQcDSLAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:57:34.768743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.05935","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e24f360b22aa9d806b91b71fa89cfa62854c4c1a264709e2e38d8c04854fca7","sha256:4ea71aa1ba55ec1b92931b6f05a94946b5d8582bfc42a9d926369c3ab7871380"],"state_sha256":"e2aa928b29095fb9bc60de5bc40d89410312354a2ce49b78ed77464944ad19f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SW1XBpBl/pEmTndjbq9jCewd2CclVFPkhdffoGCQ3LMtyJs8lYdYm6MyMBSLydp0KPptYdQ7DAlB+P8qu96LDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:06:50.088462Z","bundle_sha256":"4c7a7ddc68d08add8a90916aca6a01ec87ff15ebaf6fa024d728c24915c0cb52"}}