{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VIXTLRIF4ZGFXELTBI77VHBLSM","short_pith_number":"pith:VIXTLRIF","canonical_record":{"source":{"id":"2402.07270","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-11T18:26:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3bfa1fd5bc4f900af3f58ecfc6a4f69621afdfb75448abcf7cf73c70211d6416","abstract_canon_sha256":"7c1e0858c8cadded7b61a3954df2e30e442095b637bec1e229186956523d4725"},"schema_version":"1.0"},"canonical_sha256":"aa2f35c505e64c5b91730a3ffa9c2b933b83f5518da45b16adddd6c2de248212","source":{"kind":"arxiv","id":"2402.07270","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07270","created_at":"2026-07-05T08:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07270v2","created_at":"2026-07-05T08:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07270","created_at":"2026-07-05T08:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"VIXTLRIF4ZGF","created_at":"2026-07-05T08:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"VIXTLRIF4ZGFXELT","created_at":"2026-07-05T08:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"VIXTLRIF","created_at":"2026-07-05T08:15:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VIXTLRIF4ZGFXELTBI77VHBLSM","target":"record","payload":{"canonical_record":{"source":{"id":"2402.07270","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-11T18:26:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3bfa1fd5bc4f900af3f58ecfc6a4f69621afdfb75448abcf7cf73c70211d6416","abstract_canon_sha256":"7c1e0858c8cadded7b61a3954df2e30e442095b637bec1e229186956523d4725"},"schema_version":"1.0"},"canonical_sha256":"aa2f35c505e64c5b91730a3ffa9c2b933b83f5518da45b16adddd6c2de248212","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:45.215279Z","signature_b64":"htKFNdjSu6E4r0rM1hbMIegJK2DQEVrh0mFrvXDW7Xkn9YmhcWDscqpY40b+h9ELt11aQL7wf0VOuv1KVJU8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa2f35c505e64c5b91730a3ffa9c2b933b83f5518da45b16adddd6c2de248212","last_reissued_at":"2026-07-05T08:15:45.214864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:45.214864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.07270","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":"2026-07-05T08:15:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xaPMZvTOw1K7jXQjHdlhr29YczD0eAqf8d+VrISlKL5qJ3owE4+VdVBN19uMIsvOKPMXvs89x292Glpe6s9RBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:17:36.797638Z"},"content_sha256":"45cdb44322e28c3adbaec3dc8e9bb1152368406140b3df1e1782df61d15face8","schema_version":"1.0","event_id":"sha256:45cdb44322e28c3adbaec3dc8e9bb1152368406140b3df1e1782df61d15face8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VIXTLRIF4ZGFXELTBI77VHBLSM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Mar\\'ia A. Bravo, Simon Ging, Thomas Brox","submitted_at":"2024-02-11T18:26:18Z","abstract_excerpt":"The evaluation of text-generative vision-language models is a challenging yet crucial endeavor. By addressing the limitations of existing Visual Question Answering (VQA) benchmarks and proposing innovative evaluation methodologies, our research seeks to advance our understanding of these models' capabilities. We propose a novel VQA benchmark based on well-known visual classification datasets which allows a granular evaluation of text-generative vision-language models and their comparison with discriminative vision-language models. To improve the assessment of coarse answers on fine-grained cla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07270","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/2402.07270/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":"2026-07-05T08:15:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n+87JBXQ6I5b6CrlGueQMtZ0bNM93K3mEqUaT/g+H02YRw1XakhmOw+wfpEFUndKxAeOzf9YiocC21rWV1OwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:17:36.798283Z"},"content_sha256":"fe22c98ce849b813c7e9faffe324da9cf30cc764938887460e85906a6cef1044","schema_version":"1.0","event_id":"sha256:fe22c98ce849b813c7e9faffe324da9cf30cc764938887460e85906a6cef1044"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VIXTLRIF4ZGFXELTBI77VHBLSM/bundle.json","state_url":"https://pith.science/pith/VIXTLRIF4ZGFXELTBI77VHBLSM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VIXTLRIF4ZGFXELTBI77VHBLSM/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":"2026-08-08T15:17:36Z","links":{"resolver":"https://pith.science/pith/VIXTLRIF4ZGFXELTBI77VHBLSM","bundle":"https://pith.science/pith/VIXTLRIF4ZGFXELTBI77VHBLSM/bundle.json","state":"https://pith.science/pith/VIXTLRIF4ZGFXELTBI77VHBLSM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VIXTLRIF4ZGFXELTBI77VHBLSM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VIXTLRIF4ZGFXELTBI77VHBLSM","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":"7c1e0858c8cadded7b61a3954df2e30e442095b637bec1e229186956523d4725","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-11T18:26:18Z","title_canon_sha256":"3bfa1fd5bc4f900af3f58ecfc6a4f69621afdfb75448abcf7cf73c70211d6416"},"schema_version":"1.0","source":{"id":"2402.07270","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07270","created_at":"2026-07-05T08:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07270v2","created_at":"2026-07-05T08:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07270","created_at":"2026-07-05T08:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"VIXTLRIF4ZGF","created_at":"2026-07-05T08:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"VIXTLRIF4ZGFXELT","created_at":"2026-07-05T08:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"VIXTLRIF","created_at":"2026-07-05T08:15:45Z"}],"graph_snapshots":[{"event_id":"sha256:fe22c98ce849b813c7e9faffe324da9cf30cc764938887460e85906a6cef1044","target":"graph","created_at":"2026-07-05T08:15:45Z","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/2402.07270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The evaluation of text-generative vision-language models is a challenging yet crucial endeavor. By addressing the limitations of existing Visual Question Answering (VQA) benchmarks and proposing innovative evaluation methodologies, our research seeks to advance our understanding of these models' capabilities. We propose a novel VQA benchmark based on well-known visual classification datasets which allows a granular evaluation of text-generative vision-language models and their comparison with discriminative vision-language models. To improve the assessment of coarse answers on fine-grained cla","authors_text":"Mar\\'ia A. Bravo, Simon Ging, Thomas Brox","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-11T18:26:18Z","title":"Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07270","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":"sha256:45cdb44322e28c3adbaec3dc8e9bb1152368406140b3df1e1782df61d15face8","target":"record","created_at":"2026-07-05T08:15:45Z","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":"7c1e0858c8cadded7b61a3954df2e30e442095b637bec1e229186956523d4725","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-11T18:26:18Z","title_canon_sha256":"3bfa1fd5bc4f900af3f58ecfc6a4f69621afdfb75448abcf7cf73c70211d6416"},"schema_version":"1.0","source":{"id":"2402.07270","kind":"arxiv","version":2}},"canonical_sha256":"aa2f35c505e64c5b91730a3ffa9c2b933b83f5518da45b16adddd6c2de248212","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa2f35c505e64c5b91730a3ffa9c2b933b83f5518da45b16adddd6c2de248212","first_computed_at":"2026-07-05T08:15:45.214864Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:45.214864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"htKFNdjSu6E4r0rM1hbMIegJK2DQEVrh0mFrvXDW7Xkn9YmhcWDscqpY40b+h9ELt11aQL7wf0VOuv1KVJU8Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:45.215279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07270","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45cdb44322e28c3adbaec3dc8e9bb1152368406140b3df1e1782df61d15face8","sha256:fe22c98ce849b813c7e9faffe324da9cf30cc764938887460e85906a6cef1044"],"state_sha256":"19349bc4330b5a703fffce35274ba8b59cec840ca5daedd57932becfa096a3eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WnXeRTZwlYl1JqpyfL6zfOkGS6HVk6cpyfIqF42PCc06yAPcG5Ida3FS8R1WiY95MANqQ5vR/aHnc2mgHRIQAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:17:36.802677Z","bundle_sha256":"f2d7351f287420d8e44f1f44e725d6dcaadc35e869afbabb0b0fc8ccbf829632"}}