{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:F4AWAUDD3QMEEA3OKOTZUACEFK","short_pith_number":"pith:F4AWAUDD","canonical_record":{"source":{"id":"2307.09329","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-18T15:11:40Z","cross_cats_sorted":[],"title_canon_sha256":"39660925b7c588f997cebd0bf6c9bd82842228033ba82334403ac52ad98afd61","abstract_canon_sha256":"d031bb5f1e62c6360001c731fc30e57ab79108cc28b0f6318f5f242e86133bc0"},"schema_version":"1.0"},"canonical_sha256":"2f01605063dc1842036e53a79a00442ab87967ebb55b45110769f984f7e3c826","source":{"kind":"arxiv","id":"2307.09329","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.09329","created_at":"2026-07-05T06:35:28Z"},{"alias_kind":"arxiv_version","alias_value":"2307.09329v2","created_at":"2026-07-05T06:35:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09329","created_at":"2026-07-05T06:35:28Z"},{"alias_kind":"pith_short_12","alias_value":"F4AWAUDD3QME","created_at":"2026-07-05T06:35:28Z"},{"alias_kind":"pith_short_16","alias_value":"F4AWAUDD3QMEEA3O","created_at":"2026-07-05T06:35:28Z"},{"alias_kind":"pith_short_8","alias_value":"F4AWAUDD","created_at":"2026-07-05T06:35:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:F4AWAUDD3QMEEA3OKOTZUACEFK","target":"record","payload":{"canonical_record":{"source":{"id":"2307.09329","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-18T15:11:40Z","cross_cats_sorted":[],"title_canon_sha256":"39660925b7c588f997cebd0bf6c9bd82842228033ba82334403ac52ad98afd61","abstract_canon_sha256":"d031bb5f1e62c6360001c731fc30e57ab79108cc28b0f6318f5f242e86133bc0"},"schema_version":"1.0"},"canonical_sha256":"2f01605063dc1842036e53a79a00442ab87967ebb55b45110769f984f7e3c826","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:28.620745Z","signature_b64":"btMl2fRVcueGDsP+UqY/LuSZ/WYPWCcl/55HMppN4CIm6GmVReSQm1Lm7WfZgFOFErsKXcsUt74V5mLqAMo+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f01605063dc1842036e53a79a00442ab87967ebb55b45110769f984f7e3c826","last_reissued_at":"2026-07-05T06:35:28.620250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:28.620250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.09329","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":"2026-07-05T06:35:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E9JgliVbYuj0HCUTrSzFOvi8h/n56ZAgs3DNQqBkFdCiMAuJXV11AiyNvKKuJUJ4eyJPXBhV6sFMXr6q10NHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T14:16:09.864608Z"},"content_sha256":"ea3862acae28a5df86cc3968a92958eb8e7128c941293e9ed8fc4740077a4beb","schema_version":"1.0","event_id":"sha256:ea3862acae28a5df86cc3968a92958eb8e7128c941293e9ed8fc4740077a4beb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:F4AWAUDD3QMEEA3OKOTZUACEFK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards a performance analysis on pre-trained Visual Question Answering models for autonomous driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ciar\\'an Eising, Ganesh Sistu, Kaavya Rekanar, Martin Hayes","submitted_at":"2023-07-18T15:11:40Z","abstract_excerpt":"This short paper presents a preliminary analysis of three popular Visual Question Answering (VQA) models, namely ViLBERT, ViLT, and LXMERT, in the context of answering questions relating to driving scenarios. The performance of these models is evaluated by comparing the similarity of responses to reference answers provided by computer vision experts. Model selection is predicated on the analysis of transformer utilization in multimodal architectures. The results indicate that models incorporating cross-modal attention and late fusion techniques exhibit promising potential for generating improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09329","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/2307.09329/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":"2026-07-05T06:35:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bDIaTFnTHRz0Jy9mjDZbr9N2UeZd/2b1lW6GVcG4fCUGhKEuLWkoR0KhsFEs/d5du5SIdrjQB2Xb4AzUUwQBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T14:16:09.864994Z"},"content_sha256":"eb488313af602fb634e5af69764ef4ab3073b76a424cee7ad555877ff05ccbf6","schema_version":"1.0","event_id":"sha256:eb488313af602fb634e5af69764ef4ab3073b76a424cee7ad555877ff05ccbf6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4AWAUDD3QMEEA3OKOTZUACEFK/bundle.json","state_url":"https://pith.science/pith/F4AWAUDD3QMEEA3OKOTZUACEFK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4AWAUDD3QMEEA3OKOTZUACEFK/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":"2026-07-18T14:16:09Z","links":{"resolver":"https://pith.science/pith/F4AWAUDD3QMEEA3OKOTZUACEFK","bundle":"https://pith.science/pith/F4AWAUDD3QMEEA3OKOTZUACEFK/bundle.json","state":"https://pith.science/pith/F4AWAUDD3QMEEA3OKOTZUACEFK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4AWAUDD3QMEEA3OKOTZUACEFK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F4AWAUDD3QMEEA3OKOTZUACEFK","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":"d031bb5f1e62c6360001c731fc30e57ab79108cc28b0f6318f5f242e86133bc0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-18T15:11:40Z","title_canon_sha256":"39660925b7c588f997cebd0bf6c9bd82842228033ba82334403ac52ad98afd61"},"schema_version":"1.0","source":{"id":"2307.09329","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.09329","created_at":"2026-07-05T06:35:28Z"},{"alias_kind":"arxiv_version","alias_value":"2307.09329v2","created_at":"2026-07-05T06:35:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09329","created_at":"2026-07-05T06:35:28Z"},{"alias_kind":"pith_short_12","alias_value":"F4AWAUDD3QME","created_at":"2026-07-05T06:35:28Z"},{"alias_kind":"pith_short_16","alias_value":"F4AWAUDD3QMEEA3O","created_at":"2026-07-05T06:35:28Z"},{"alias_kind":"pith_short_8","alias_value":"F4AWAUDD","created_at":"2026-07-05T06:35:28Z"}],"graph_snapshots":[{"event_id":"sha256:eb488313af602fb634e5af69764ef4ab3073b76a424cee7ad555877ff05ccbf6","target":"graph","created_at":"2026-07-05T06:35:28Z","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/2307.09329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This short paper presents a preliminary analysis of three popular Visual Question Answering (VQA) models, namely ViLBERT, ViLT, and LXMERT, in the context of answering questions relating to driving scenarios. The performance of these models is evaluated by comparing the similarity of responses to reference answers provided by computer vision experts. Model selection is predicated on the analysis of transformer utilization in multimodal architectures. The results indicate that models incorporating cross-modal attention and late fusion techniques exhibit promising potential for generating improv","authors_text":"Ciar\\'an Eising, Ganesh Sistu, Kaavya Rekanar, Martin Hayes","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-18T15:11:40Z","title":"Towards a performance analysis on pre-trained Visual Question Answering models for autonomous driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09329","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:ea3862acae28a5df86cc3968a92958eb8e7128c941293e9ed8fc4740077a4beb","target":"record","created_at":"2026-07-05T06:35:28Z","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":"d031bb5f1e62c6360001c731fc30e57ab79108cc28b0f6318f5f242e86133bc0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-18T15:11:40Z","title_canon_sha256":"39660925b7c588f997cebd0bf6c9bd82842228033ba82334403ac52ad98afd61"},"schema_version":"1.0","source":{"id":"2307.09329","kind":"arxiv","version":2}},"canonical_sha256":"2f01605063dc1842036e53a79a00442ab87967ebb55b45110769f984f7e3c826","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f01605063dc1842036e53a79a00442ab87967ebb55b45110769f984f7e3c826","first_computed_at":"2026-07-05T06:35:28.620250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:28.620250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"btMl2fRVcueGDsP+UqY/LuSZ/WYPWCcl/55HMppN4CIm6GmVReSQm1Lm7WfZgFOFErsKXcsUt74V5mLqAMo+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:28.620745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.09329","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea3862acae28a5df86cc3968a92958eb8e7128c941293e9ed8fc4740077a4beb","sha256:eb488313af602fb634e5af69764ef4ab3073b76a424cee7ad555877ff05ccbf6"],"state_sha256":"a5d3d4cc7ce9fae71f3e957725bc05b8acf29dfa447de09b2242ce8a47da78c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CzOp8gvRBrkktcPLJZ6+c4K65aC7IXn8D4DIH1wnspcD7B9nlvR3YqH3bXj5eS8waseLsb4hnsyLwEj6VSRcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T14:16:09.867076Z","bundle_sha256":"7433d371a9ac6cd296b9693cc639787c596970aa1b56708ff5f0240bade6aa42"}}