{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZYBUVTCANFCX74EBNIYHI3B5E3","short_pith_number":"pith:ZYBUVTCA","canonical_record":{"source":{"id":"2305.14218","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T16:34:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fedcce906a22943e45d7108c4daf48c2c001fd6eccf92623ef042212f43ffc32","abstract_canon_sha256":"9b205e4cf118ca6c815782f837c89c630d99d6fc7d3a8e150d8e63f561b06828"},"schema_version":"1.0"},"canonical_sha256":"ce034acc4069457ff0816a30746c3d26c037072135591d6aafe63c8f4da35a57","source":{"kind":"arxiv","id":"2305.14218","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14218","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14218v4","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14218","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZYBUVTCANFCX","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZYBUVTCANFCX74EB","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZYBUVTCA","created_at":"2026-07-05T07:05:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZYBUVTCANFCX74EBNIYHI3B5E3","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14218","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T16:34:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fedcce906a22943e45d7108c4daf48c2c001fd6eccf92623ef042212f43ffc32","abstract_canon_sha256":"9b205e4cf118ca6c815782f837c89c630d99d6fc7d3a8e150d8e63f561b06828"},"schema_version":"1.0"},"canonical_sha256":"ce034acc4069457ff0816a30746c3d26c037072135591d6aafe63c8f4da35a57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:43.329406Z","signature_b64":"BHglXj2gKC7KA4M+u937AvTxngdrMgHNjTqGF/aXpNLH58xrpIgmc5SfiUpzz9xsDrRq+RGIYvILngteYUX1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce034acc4069457ff0816a30746c3d26c037072135591d6aafe63c8f4da35a57","last_reissued_at":"2026-07-05T07:05:43.328907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:43.328907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14218","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RfJiHJ8jXh/X4xu0DgViP+pZjC0Sraj4LA7tfsTrzupytZK7CeMjUE/TnaKhzkxmWshYdqEXIJgCjtE/hA+MBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:24:28.551405Z"},"content_sha256":"5d5937c738046d779180a952fd9cbf76f28f9df557fb8614ec60991dd988c525","schema_version":"1.0","event_id":"sha256:5d5937c738046d779180a952fd9cbf76f28f9df557fb8614ec60991dd988c525"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZYBUVTCANFCX74EBNIYHI3B5E3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DUBLIN -- Document Understanding By Language-Image Network","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aditi Khandelwal, Hardik Hansrajbhai Chauhan, Kriti Aggarwal, Kumar Tanmay, Monojit Choudhury, Owais Mohammed Khan, Qiang Liu, Saurabh Tiwary, Subhojit Som, Vishrav Chaudhary","submitted_at":"2023-05-23T16:34:09Z","abstract_excerpt":"Visual document understanding is a complex task that involves analyzing both the text and the visual elements in document images. Existing models often rely on manual feature engineering or domain-specific pipelines, which limit their generalization ability across different document types and languages. In this paper, we propose DUBLIN, which is pretrained on web pages using three novel objectives: Masked Document Text Generation Task, Bounding Box Task, and Rendered Question Answering Task, that leverage both the spatial and semantic information in the document images. Our model achieves comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14218","kind":"arxiv","version":4},"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/2305.14218/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":"2026-07-05T07:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AdGvy+EBit/pxLcMBIBoLNwM275fKcclcdaSBrstk00T0Nx/5+nAkSIu0C84+KsbfPGE5vgQaY4Hle0TpC8oAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:24:28.551915Z"},"content_sha256":"27855f75311d3eac411f0e9aac3b96cb8228a0e019a7539ebc7ed7e3e976db67","schema_version":"1.0","event_id":"sha256:27855f75311d3eac411f0e9aac3b96cb8228a0e019a7539ebc7ed7e3e976db67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYBUVTCANFCX74EBNIYHI3B5E3/bundle.json","state_url":"https://pith.science/pith/ZYBUVTCANFCX74EBNIYHI3B5E3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYBUVTCANFCX74EBNIYHI3B5E3/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":"2026-08-20T17:24:28Z","links":{"resolver":"https://pith.science/pith/ZYBUVTCANFCX74EBNIYHI3B5E3","bundle":"https://pith.science/pith/ZYBUVTCANFCX74EBNIYHI3B5E3/bundle.json","state":"https://pith.science/pith/ZYBUVTCANFCX74EBNIYHI3B5E3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYBUVTCANFCX74EBNIYHI3B5E3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZYBUVTCANFCX74EBNIYHI3B5E3","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":"9b205e4cf118ca6c815782f837c89c630d99d6fc7d3a8e150d8e63f561b06828","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T16:34:09Z","title_canon_sha256":"fedcce906a22943e45d7108c4daf48c2c001fd6eccf92623ef042212f43ffc32"},"schema_version":"1.0","source":{"id":"2305.14218","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14218","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14218v4","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14218","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZYBUVTCANFCX","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZYBUVTCANFCX74EB","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZYBUVTCA","created_at":"2026-07-05T07:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:27855f75311d3eac411f0e9aac3b96cb8228a0e019a7539ebc7ed7e3e976db67","target":"graph","created_at":"2026-07-05T07:05:43Z","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/2305.14218/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual document understanding is a complex task that involves analyzing both the text and the visual elements in document images. Existing models often rely on manual feature engineering or domain-specific pipelines, which limit their generalization ability across different document types and languages. In this paper, we propose DUBLIN, which is pretrained on web pages using three novel objectives: Masked Document Text Generation Task, Bounding Box Task, and Rendered Question Answering Task, that leverage both the spatial and semantic information in the document images. Our model achieves comp","authors_text":"Aditi Khandelwal, Hardik Hansrajbhai Chauhan, Kriti Aggarwal, Kumar Tanmay, Monojit Choudhury, Owais Mohammed Khan, Qiang Liu, Saurabh Tiwary, Subhojit Som, Vishrav Chaudhary","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T16:34:09Z","title":"DUBLIN -- Document Understanding By Language-Image Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14218","kind":"arxiv","version":4},"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":"sha256:5d5937c738046d779180a952fd9cbf76f28f9df557fb8614ec60991dd988c525","target":"record","created_at":"2026-07-05T07:05:43Z","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":"9b205e4cf118ca6c815782f837c89c630d99d6fc7d3a8e150d8e63f561b06828","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T16:34:09Z","title_canon_sha256":"fedcce906a22943e45d7108c4daf48c2c001fd6eccf92623ef042212f43ffc32"},"schema_version":"1.0","source":{"id":"2305.14218","kind":"arxiv","version":4}},"canonical_sha256":"ce034acc4069457ff0816a30746c3d26c037072135591d6aafe63c8f4da35a57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce034acc4069457ff0816a30746c3d26c037072135591d6aafe63c8f4da35a57","first_computed_at":"2026-07-05T07:05:43.328907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:43.328907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BHglXj2gKC7KA4M+u937AvTxngdrMgHNjTqGF/aXpNLH58xrpIgmc5SfiUpzz9xsDrRq+RGIYvILngteYUX1Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:43.329406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14218","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d5937c738046d779180a952fd9cbf76f28f9df557fb8614ec60991dd988c525","sha256:27855f75311d3eac411f0e9aac3b96cb8228a0e019a7539ebc7ed7e3e976db67"],"state_sha256":"07351a5d688a58a3cccd9e9077988ef65797dda62b69b1fc69cc2c1afc412d15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HlnZe6267/bzctA0ajCb6NTAPfL1zLEyUypL/XIugmBxYaYRXp1OfWaR7kcPRHKlExus4mXpUsOv/edgZ2aZCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T17:24:28.557227Z","bundle_sha256":"1930ef052f025b689e051f5f720e71c0c8240b0dfb9763e3644ba61aeac02ca9"}}