{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HC4RWVEAFDI2VNIFBPIIIT7574","short_pith_number":"pith:HC4RWVEA","canonical_record":{"source":{"id":"2311.00807","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T19:43:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"648f78389ef93a68ab8311b66ea163fa1f31eaf8c01fc47d2789c1856d38a624","abstract_canon_sha256":"3e4fbee32904acc08e2563e4bd2c7a9b768bc94af7ef7b1c22e10f20977b01d7"},"schema_version":"1.0"},"canonical_sha256":"38b91b548028d1aab5050bd0844ffdff0fef417a96ff960a449049bbe3429b4d","source":{"kind":"arxiv","id":"2311.00807","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00807","created_at":"2026-07-05T07:08:15Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00807v1","created_at":"2026-07-05T07:08:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00807","created_at":"2026-07-05T07:08:15Z"},{"alias_kind":"pith_short_12","alias_value":"HC4RWVEAFDI2","created_at":"2026-07-05T07:08:15Z"},{"alias_kind":"pith_short_16","alias_value":"HC4RWVEAFDI2VNIF","created_at":"2026-07-05T07:08:15Z"},{"alias_kind":"pith_short_8","alias_value":"HC4RWVEA","created_at":"2026-07-05T07:08:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HC4RWVEAFDI2VNIFBPIIIT7574","target":"record","payload":{"canonical_record":{"source":{"id":"2311.00807","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T19:43:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"648f78389ef93a68ab8311b66ea163fa1f31eaf8c01fc47d2789c1856d38a624","abstract_canon_sha256":"3e4fbee32904acc08e2563e4bd2c7a9b768bc94af7ef7b1c22e10f20977b01d7"},"schema_version":"1.0"},"canonical_sha256":"38b91b548028d1aab5050bd0844ffdff0fef417a96ff960a449049bbe3429b4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:15.838665Z","signature_b64":"JoBJGSRf2jYdKS44HRtpxUSpz7/1z/o/dYo82CdwObydtPPzCZTicffoIK7rQMBHnIhILrkKftxVwvo+gb1hDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38b91b548028d1aab5050bd0844ffdff0fef417a96ff960a449049bbe3429b4d","last_reissued_at":"2026-07-05T07:08:15.838255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:15.838255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.00807","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":"2026-07-05T07:08:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Yk8A+GL78L2ijTn1x0tB1eSGDo86zDq7Ofb0Ih111W1Co5AER6wGZojgR5JzeOgVRY01OlXT2blL3W6mMAgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:34:34.206213Z"},"content_sha256":"b2c97b15f99f6eb391614c797163b974cdda66ca32e2b8d3d1d857957caf4e81","schema_version":"1.0","event_id":"sha256:b2c97b15f99f6eb391614c797163b974cdda66ca32e2b8d3d1d857957caf4e81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HC4RWVEAFDI2VNIFBPIIIT7574","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VQA-GEN: A Visual Question Answering Benchmark for Domain Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Huan Liu, Raha Moraffah, Suraj Jyothi Unni","submitted_at":"2023-11-01T19:43:56Z","abstract_excerpt":"Visual question answering (VQA) models are designed to demonstrate visual-textual reasoning capabilities. However, their real-world applicability is hindered by a lack of comprehensive benchmark datasets. Existing domain generalization datasets for VQA exhibit a unilateral focus on textual shifts while VQA being a multi-modal task contains shifts across both visual and textual domains. We propose VQA-GEN, the first ever multi-modal benchmark dataset for distribution shift generated through a shift induced pipeline. Experiments demonstrate VQA-GEN dataset exposes the vulnerability of existing m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00807","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/2311.00807/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":"2026-07-05T07:08:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0zTG6ROGfyIBKKcMvuhiN9OF33AOj8kzyT1/gPcttpYhnMgIMGLIyboDCr3ihffSc3wqAejW69VClYNvoqMNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:34:34.206772Z"},"content_sha256":"739d6cc0918a05c4a8713ae75a4f5979047ac9f89f0fb465d054512407674dcc","schema_version":"1.0","event_id":"sha256:739d6cc0918a05c4a8713ae75a4f5979047ac9f89f0fb465d054512407674dcc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574/bundle.json","state_url":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HC4RWVEAFDI2VNIFBPIIIT7574/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":"2026-08-08T13:34:34Z","links":{"resolver":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574","bundle":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574/bundle.json","state":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HC4RWVEAFDI2VNIFBPIIIT7574/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HC4RWVEAFDI2VNIFBPIIIT7574","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":"3e4fbee32904acc08e2563e4bd2c7a9b768bc94af7ef7b1c22e10f20977b01d7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T19:43:56Z","title_canon_sha256":"648f78389ef93a68ab8311b66ea163fa1f31eaf8c01fc47d2789c1856d38a624"},"schema_version":"1.0","source":{"id":"2311.00807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00807","created_at":"2026-07-05T07:08:15Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00807v1","created_at":"2026-07-05T07:08:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00807","created_at":"2026-07-05T07:08:15Z"},{"alias_kind":"pith_short_12","alias_value":"HC4RWVEAFDI2","created_at":"2026-07-05T07:08:15Z"},{"alias_kind":"pith_short_16","alias_value":"HC4RWVEAFDI2VNIF","created_at":"2026-07-05T07:08:15Z"},{"alias_kind":"pith_short_8","alias_value":"HC4RWVEA","created_at":"2026-07-05T07:08:15Z"}],"graph_snapshots":[{"event_id":"sha256:739d6cc0918a05c4a8713ae75a4f5979047ac9f89f0fb465d054512407674dcc","target":"graph","created_at":"2026-07-05T07:08:15Z","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/2311.00807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual question answering (VQA) models are designed to demonstrate visual-textual reasoning capabilities. However, their real-world applicability is hindered by a lack of comprehensive benchmark datasets. Existing domain generalization datasets for VQA exhibit a unilateral focus on textual shifts while VQA being a multi-modal task contains shifts across both visual and textual domains. We propose VQA-GEN, the first ever multi-modal benchmark dataset for distribution shift generated through a shift induced pipeline. Experiments demonstrate VQA-GEN dataset exposes the vulnerability of existing m","authors_text":"Huan Liu, Raha Moraffah, Suraj Jyothi Unni","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T19:43:56Z","title":"VQA-GEN: A Visual Question Answering Benchmark for Domain Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00807","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:b2c97b15f99f6eb391614c797163b974cdda66ca32e2b8d3d1d857957caf4e81","target":"record","created_at":"2026-07-05T07:08:15Z","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":"3e4fbee32904acc08e2563e4bd2c7a9b768bc94af7ef7b1c22e10f20977b01d7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T19:43:56Z","title_canon_sha256":"648f78389ef93a68ab8311b66ea163fa1f31eaf8c01fc47d2789c1856d38a624"},"schema_version":"1.0","source":{"id":"2311.00807","kind":"arxiv","version":1}},"canonical_sha256":"38b91b548028d1aab5050bd0844ffdff0fef417a96ff960a449049bbe3429b4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38b91b548028d1aab5050bd0844ffdff0fef417a96ff960a449049bbe3429b4d","first_computed_at":"2026-07-05T07:08:15.838255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:15.838255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JoBJGSRf2jYdKS44HRtpxUSpz7/1z/o/dYo82CdwObydtPPzCZTicffoIK7rQMBHnIhILrkKftxVwvo+gb1hDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:15.838665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00807","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2c97b15f99f6eb391614c797163b974cdda66ca32e2b8d3d1d857957caf4e81","sha256:739d6cc0918a05c4a8713ae75a4f5979047ac9f89f0fb465d054512407674dcc"],"state_sha256":"1d43ac24cbfe8af7940c18bcf258d6d3eff49ef5f7e243e5b2b829e4b3e59dca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+E2UNpwjEcaCE+QnoL9yf0J5KdnHJwVa48NEvlt+iUS26p0psnr+LYkNk4PzboB7VzVZH9ylfKOxzSNlxi6CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:34:34.212293Z","bundle_sha256":"a1613340fa33177491ab59168dcdcd1105b40c27f0d343268a21a05d82ba06fb"}}