{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QDZG5NRPD3T4CQMQ4EAHA2HD5D","short_pith_number":"pith:QDZG5NRP","canonical_record":{"source":{"id":"2003.13962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-31T05:56:59Z","cross_cats_sorted":[],"title_canon_sha256":"d7125a21409a722e6458ef7decd74ec36ae34092307c5c572b1a67548ff6f4ae","abstract_canon_sha256":"f11b5a14feb08ca83994f02ca30f591b25e120d7bc58d83159cf163c0b2b735f"},"schema_version":"1.0"},"canonical_sha256":"80f26eb62f1ee7c14190e1007068e3e8e3f949b28415e319e5a02bb37b097c75","source":{"kind":"arxiv","id":"2003.13962","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13962","created_at":"2026-07-05T00:51:46Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13962v1","created_at":"2026-07-05T00:51:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13962","created_at":"2026-07-05T00:51:46Z"},{"alias_kind":"pith_short_12","alias_value":"QDZG5NRPD3T4","created_at":"2026-07-05T00:51:46Z"},{"alias_kind":"pith_short_16","alias_value":"QDZG5NRPD3T4CQMQ","created_at":"2026-07-05T00:51:46Z"},{"alias_kind":"pith_short_8","alias_value":"QDZG5NRP","created_at":"2026-07-05T00:51:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QDZG5NRPD3T4CQMQ4EAHA2HD5D","target":"record","payload":{"canonical_record":{"source":{"id":"2003.13962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-31T05:56:59Z","cross_cats_sorted":[],"title_canon_sha256":"d7125a21409a722e6458ef7decd74ec36ae34092307c5c572b1a67548ff6f4ae","abstract_canon_sha256":"f11b5a14feb08ca83994f02ca30f591b25e120d7bc58d83159cf163c0b2b735f"},"schema_version":"1.0"},"canonical_sha256":"80f26eb62f1ee7c14190e1007068e3e8e3f949b28415e319e5a02bb37b097c75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:46.749873Z","signature_b64":"5KXkJOvjx3xX5kLIvQ5eum0Je14QYQCKbc4C+mjTW/r5M+HIg9ag7yxJP9hETnHrz9JxjFd86U1PshLTeflUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80f26eb62f1ee7c14190e1007068e3e8e3f949b28415e319e5a02bb37b097c75","last_reissued_at":"2026-07-05T00:51:46.749531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:46.749531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.13962","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":"2026-07-05T00:51:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sN39z8IYjgItSrMDV8Y6Q6R96dzWmv5LK5MxFW2vOdWwzD8v/erDYN/qlES9uAfbo5nepIfis9BF0FF2h4CHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:44:45.419433Z"},"content_sha256":"8b71f398ccebb8cdee6d9e16563f1c158a77b81986012fede1744df7ae78838a","schema_version":"1.0","event_id":"sha256:8b71f398ccebb8cdee6d9e16563f1c158a77b81986012fede1744df7ae78838a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QDZG5NRPD3T4CQMQ4EAHA2HD5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Difei Gao, Ke Li, Ruiping Wang, Shiguang Shan, Xilin Chen","submitted_at":"2020-03-31T05:56:59Z","abstract_excerpt":"Answering questions that require reading texts in an image is challenging for current models. One key difficulty of this task is that rare, polysemous, and ambiguous words frequently appear in images, e.g., names of places, products, and sports teams. To overcome this difficulty, only resorting to pre-trained word embedding models is far from enough. A desired model should utilize the rich information in multiple modalities of the image to help understand the meaning of scene texts, e.g., the prominent text on a bottle is most likely to be the brand. Following this idea, we propose a novel VQA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13962","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/2003.13962/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":"2026-07-05T00:51:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cxzlJsKRYdFMM/v0iUrF16GnoOQfzR+ci0fOTQ1xp9jwsVOIj6pWtgtMLqEoaI0juPQiyfxkTIr12HqKzT3SCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:44:45.419936Z"},"content_sha256":"1bfc0fcb1969ee28263cbfd6515c2f380fb035f61104ef2f1979ecade041c5f4","schema_version":"1.0","event_id":"sha256:1bfc0fcb1969ee28263cbfd6515c2f380fb035f61104ef2f1979ecade041c5f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDZG5NRPD3T4CQMQ4EAHA2HD5D/bundle.json","state_url":"https://pith.science/pith/QDZG5NRPD3T4CQMQ4EAHA2HD5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDZG5NRPD3T4CQMQ4EAHA2HD5D/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":"2026-08-11T20:44:45Z","links":{"resolver":"https://pith.science/pith/QDZG5NRPD3T4CQMQ4EAHA2HD5D","bundle":"https://pith.science/pith/QDZG5NRPD3T4CQMQ4EAHA2HD5D/bundle.json","state":"https://pith.science/pith/QDZG5NRPD3T4CQMQ4EAHA2HD5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDZG5NRPD3T4CQMQ4EAHA2HD5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QDZG5NRPD3T4CQMQ4EAHA2HD5D","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":"f11b5a14feb08ca83994f02ca30f591b25e120d7bc58d83159cf163c0b2b735f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-31T05:56:59Z","title_canon_sha256":"d7125a21409a722e6458ef7decd74ec36ae34092307c5c572b1a67548ff6f4ae"},"schema_version":"1.0","source":{"id":"2003.13962","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13962","created_at":"2026-07-05T00:51:46Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13962v1","created_at":"2026-07-05T00:51:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13962","created_at":"2026-07-05T00:51:46Z"},{"alias_kind":"pith_short_12","alias_value":"QDZG5NRPD3T4","created_at":"2026-07-05T00:51:46Z"},{"alias_kind":"pith_short_16","alias_value":"QDZG5NRPD3T4CQMQ","created_at":"2026-07-05T00:51:46Z"},{"alias_kind":"pith_short_8","alias_value":"QDZG5NRP","created_at":"2026-07-05T00:51:46Z"}],"graph_snapshots":[{"event_id":"sha256:1bfc0fcb1969ee28263cbfd6515c2f380fb035f61104ef2f1979ecade041c5f4","target":"graph","created_at":"2026-07-05T00:51:46Z","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/2003.13962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Answering questions that require reading texts in an image is challenging for current models. One key difficulty of this task is that rare, polysemous, and ambiguous words frequently appear in images, e.g., names of places, products, and sports teams. To overcome this difficulty, only resorting to pre-trained word embedding models is far from enough. A desired model should utilize the rich information in multiple modalities of the image to help understand the meaning of scene texts, e.g., the prominent text on a bottle is most likely to be the brand. Following this idea, we propose a novel VQA","authors_text":"Difei Gao, Ke Li, Ruiping Wang, Shiguang Shan, Xilin Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-31T05:56:59Z","title":"Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13962","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":"sha256:8b71f398ccebb8cdee6d9e16563f1c158a77b81986012fede1744df7ae78838a","target":"record","created_at":"2026-07-05T00:51:46Z","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":"f11b5a14feb08ca83994f02ca30f591b25e120d7bc58d83159cf163c0b2b735f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-31T05:56:59Z","title_canon_sha256":"d7125a21409a722e6458ef7decd74ec36ae34092307c5c572b1a67548ff6f4ae"},"schema_version":"1.0","source":{"id":"2003.13962","kind":"arxiv","version":1}},"canonical_sha256":"80f26eb62f1ee7c14190e1007068e3e8e3f949b28415e319e5a02bb37b097c75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80f26eb62f1ee7c14190e1007068e3e8e3f949b28415e319e5a02bb37b097c75","first_computed_at":"2026-07-05T00:51:46.749531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:51:46.749531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5KXkJOvjx3xX5kLIvQ5eum0Je14QYQCKbc4C+mjTW/r5M+HIg9ag7yxJP9hETnHrz9JxjFd86U1PshLTeflUAw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:51:46.749873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.13962","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b71f398ccebb8cdee6d9e16563f1c158a77b81986012fede1744df7ae78838a","sha256:1bfc0fcb1969ee28263cbfd6515c2f380fb035f61104ef2f1979ecade041c5f4"],"state_sha256":"eea8bdb4b74eabd8b759ffa46aaf09073d1fac07f4943ba2f418bc04d53feeaa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8JRQPbPdqtpd4/G+tPXm2attHw5aB6OcPVpyRrC3b7qJxXx4xwVfwfFJhZwwyCfrNvTcMZM9HJF0cVzXgz4qAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:44:45.424637Z","bundle_sha256":"d481b347d680180231c5156fd0fa51565de5ea45a0ef43f08882920523294f87"}}