{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZS634CX4AKK3MG47J3I3HOQFEL","short_pith_number":"pith:ZS634CX4","canonical_record":{"source":{"id":"2209.06730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T15:37:56Z","cross_cats_sorted":[],"title_canon_sha256":"2c2c3089cba56b8ef492b36d64eb793551a094a9531d80a59e5173964130b3ba","abstract_canon_sha256":"43bc9299623b368e78e583d86eaff6166bebc03c4605fcf75400a5df3a35b5a4"},"schema_version":"1.0"},"canonical_sha256":"ccbdbe0afc0295b61b9f4ed1b3ba0522e5dbffdbbd21f35d538b3cf11dcc97f0","source":{"kind":"arxiv","id":"2209.06730","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06730","created_at":"2026-07-05T04:57:34Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06730v1","created_at":"2026-07-05T04:57:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06730","created_at":"2026-07-05T04:57:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZS634CX4AKK3","created_at":"2026-07-05T04:57:34Z"},{"alias_kind":"pith_short_16","alias_value":"ZS634CX4AKK3MG47","created_at":"2026-07-05T04:57:34Z"},{"alias_kind":"pith_short_8","alias_value":"ZS634CX4","created_at":"2026-07-05T04:57:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZS634CX4AKK3MG47J3I3HOQFEL","target":"record","payload":{"canonical_record":{"source":{"id":"2209.06730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T15:37:56Z","cross_cats_sorted":[],"title_canon_sha256":"2c2c3089cba56b8ef492b36d64eb793551a094a9531d80a59e5173964130b3ba","abstract_canon_sha256":"43bc9299623b368e78e583d86eaff6166bebc03c4605fcf75400a5df3a35b5a4"},"schema_version":"1.0"},"canonical_sha256":"ccbdbe0afc0295b61b9f4ed1b3ba0522e5dbffdbbd21f35d538b3cf11dcc97f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:34.398798Z","signature_b64":"4f9vSRvNtjsXRmL4ZUSvYAnBj5fwEIk+8uWKHhqh/e3A860N4qGxE4AWu2yEumC1/xDn1shgjrumCp0UjQ+9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccbdbe0afc0295b61b9f4ed1b3ba0522e5dbffdbbd21f35d538b3cf11dcc97f0","last_reissued_at":"2026-07-05T04:57:34.398355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:34.398355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.06730","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":"2026-07-05T04:57:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0vP6Hxbu/+ss/fb7Vncgtfb1l1JKkdxADghHoyUZKIbgOo5nIlnmdunqhhur5gkOSvb46EwYKI572RJS8Y4sDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:15:10.839217Z"},"content_sha256":"7675f97f83711ae23f916abcca9f132b026715259b12f6fea7d9c134594ce317","schema_version":"1.0","event_id":"sha256:7675f97f83711ae23f916abcca9f132b026715259b12f6fea7d9c134594ce317"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZS634CX4AKK3MG47J3I3HOQFEL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MUST-VQA: MUltilingual Scene-text VQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Furkan Biten, Andres Mafla, Dimosthenis Karatzas, Emanuele Vivoli, Lluis Gomez","submitted_at":"2022-09-14T15:37:56Z","abstract_excerpt":"In this paper, we present a framework for Multilingual Scene Text Visual Question Answering that deals with new languages in a zero-shot fashion. Specifically, we consider the task of Scene Text Visual Question Answering (STVQA) in which the question can be asked in different languages and it is not necessarily aligned to the scene text language. Thus, we first introduce a natural step towards a more generalized version of STVQA: MUST-VQA. Accounting for this, we discuss two evaluation scenarios in the constrained setting, namely IID and zero-shot and we demonstrate that the models can perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06730","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/2209.06730/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":"2026-07-05T04:57:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uZPLc8mS0qznxbE/5T3q+XjN2tggZM7b++Wkn9MhVcUm6Ekc4FPsxuZxffyR3mKOnDvWGJI6xZR1u3RFsrKzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:15:10.839723Z"},"content_sha256":"47223d2b6e112ed51e8d7f840c73555734796ad09f0a665197f5d7b47fc51269","schema_version":"1.0","event_id":"sha256:47223d2b6e112ed51e8d7f840c73555734796ad09f0a665197f5d7b47fc51269"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZS634CX4AKK3MG47J3I3HOQFEL/bundle.json","state_url":"https://pith.science/pith/ZS634CX4AKK3MG47J3I3HOQFEL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZS634CX4AKK3MG47J3I3HOQFEL/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":"2026-08-06T09:15:10Z","links":{"resolver":"https://pith.science/pith/ZS634CX4AKK3MG47J3I3HOQFEL","bundle":"https://pith.science/pith/ZS634CX4AKK3MG47J3I3HOQFEL/bundle.json","state":"https://pith.science/pith/ZS634CX4AKK3MG47J3I3HOQFEL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZS634CX4AKK3MG47J3I3HOQFEL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZS634CX4AKK3MG47J3I3HOQFEL","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":"43bc9299623b368e78e583d86eaff6166bebc03c4605fcf75400a5df3a35b5a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T15:37:56Z","title_canon_sha256":"2c2c3089cba56b8ef492b36d64eb793551a094a9531d80a59e5173964130b3ba"},"schema_version":"1.0","source":{"id":"2209.06730","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06730","created_at":"2026-07-05T04:57:34Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06730v1","created_at":"2026-07-05T04:57:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06730","created_at":"2026-07-05T04:57:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZS634CX4AKK3","created_at":"2026-07-05T04:57:34Z"},{"alias_kind":"pith_short_16","alias_value":"ZS634CX4AKK3MG47","created_at":"2026-07-05T04:57:34Z"},{"alias_kind":"pith_short_8","alias_value":"ZS634CX4","created_at":"2026-07-05T04:57:34Z"}],"graph_snapshots":[{"event_id":"sha256:47223d2b6e112ed51e8d7f840c73555734796ad09f0a665197f5d7b47fc51269","target":"graph","created_at":"2026-07-05T04:57:34Z","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/2209.06730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a framework for Multilingual Scene Text Visual Question Answering that deals with new languages in a zero-shot fashion. Specifically, we consider the task of Scene Text Visual Question Answering (STVQA) in which the question can be asked in different languages and it is not necessarily aligned to the scene text language. Thus, we first introduce a natural step towards a more generalized version of STVQA: MUST-VQA. Accounting for this, we discuss two evaluation scenarios in the constrained setting, namely IID and zero-shot and we demonstrate that the models can perform","authors_text":"Ali Furkan Biten, Andres Mafla, Dimosthenis Karatzas, Emanuele Vivoli, Lluis Gomez","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T15:37:56Z","title":"MUST-VQA: MUltilingual Scene-text VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06730","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":"sha256:7675f97f83711ae23f916abcca9f132b026715259b12f6fea7d9c134594ce317","target":"record","created_at":"2026-07-05T04:57:34Z","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":"43bc9299623b368e78e583d86eaff6166bebc03c4605fcf75400a5df3a35b5a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T15:37:56Z","title_canon_sha256":"2c2c3089cba56b8ef492b36d64eb793551a094a9531d80a59e5173964130b3ba"},"schema_version":"1.0","source":{"id":"2209.06730","kind":"arxiv","version":1}},"canonical_sha256":"ccbdbe0afc0295b61b9f4ed1b3ba0522e5dbffdbbd21f35d538b3cf11dcc97f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccbdbe0afc0295b61b9f4ed1b3ba0522e5dbffdbbd21f35d538b3cf11dcc97f0","first_computed_at":"2026-07-05T04:57:34.398355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:57:34.398355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4f9vSRvNtjsXRmL4ZUSvYAnBj5fwEIk+8uWKHhqh/e3A860N4qGxE4AWu2yEumC1/xDn1shgjrumCp0UjQ+9CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:57:34.398798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.06730","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7675f97f83711ae23f916abcca9f132b026715259b12f6fea7d9c134594ce317","sha256:47223d2b6e112ed51e8d7f840c73555734796ad09f0a665197f5d7b47fc51269"],"state_sha256":"3e162934d8c771469083a975a5ac514ea951e4e2ce7d7070908d0ef87de72cb8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PSAYyHcoK86a3V9nnDF6esN/470/IYq/3C4MYEPMiURL5VzfXdLFPwRDW2V2YmSnyOXmV7DTyK77CjSweCIEBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:15:10.843446Z","bundle_sha256":"55345293000731d553633c7d14922e4942c1d673a0e1f235f9c3f261ec351617"}}