{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:I7EGHUVSTUEBKVNH6FAL6B6K74","short_pith_number":"pith:I7EGHUVS","canonical_record":{"source":{"id":"2306.09224","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T16:03:01Z","cross_cats_sorted":[],"title_canon_sha256":"ea5525b154aee59dad7b23cfd8eddc770b705f7b1fee82404c88c81ade458ea9","abstract_canon_sha256":"2d5543fc079bfb10a451cfd1a4b73186ed58b4914187b5157969eb168a870f14"},"schema_version":"1.0"},"canonical_sha256":"47c863d2b29d081555a7f140bf07caff1aba93e4d3ce27868bc51b0a83b83113","source":{"kind":"arxiv","id":"2306.09224","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09224","created_at":"2026-07-05T06:33:46Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09224v2","created_at":"2026-07-05T06:33:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09224","created_at":"2026-07-05T06:33:46Z"},{"alias_kind":"pith_short_12","alias_value":"I7EGHUVSTUEB","created_at":"2026-07-05T06:33:46Z"},{"alias_kind":"pith_short_16","alias_value":"I7EGHUVSTUEBKVNH","created_at":"2026-07-05T06:33:46Z"},{"alias_kind":"pith_short_8","alias_value":"I7EGHUVS","created_at":"2026-07-05T06:33:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:I7EGHUVSTUEBKVNH6FAL6B6K74","target":"record","payload":{"canonical_record":{"source":{"id":"2306.09224","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T16:03:01Z","cross_cats_sorted":[],"title_canon_sha256":"ea5525b154aee59dad7b23cfd8eddc770b705f7b1fee82404c88c81ade458ea9","abstract_canon_sha256":"2d5543fc079bfb10a451cfd1a4b73186ed58b4914187b5157969eb168a870f14"},"schema_version":"1.0"},"canonical_sha256":"47c863d2b29d081555a7f140bf07caff1aba93e4d3ce27868bc51b0a83b83113","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:46.115730Z","signature_b64":"hF8meoRGqef/6H86akQfIiAYLvuCBcHxyJS6hKINPx4udDYMq38RkW7W82AQNaEJoizniWZQvBQhrVemNlciCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47c863d2b29d081555a7f140bf07caff1aba93e4d3ce27868bc51b0a83b83113","last_reissued_at":"2026-07-05T06:33:46.115305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:46.115305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.09224","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":"2026-07-05T06:33:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ewXnGQxCk/O0b0tY1KrhAcOwa1bOZml27LS93mfVkweuMTkuSwDoCw9c+v38cVIvU2Kf0ZJDfnQKdUymGgtqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:51:14.294228Z"},"content_sha256":"d5184a5f501d1f1d6fc4a382ff08e2fdd93852fa38baba9138ee48ac67f1b362","schema_version":"1.0","event_id":"sha256:d5184a5f501d1f1d6fc4a382ff08e2fdd93852fa38baba9138ee48ac67f1b362"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:I7EGHUVSTUEBKVNH6FAL6B6K74","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andr\\'e Araujo, Arushi Goel, Fei Sha, Felipe Cadar, Howard Zhou, Jasper Uijlings, Lluis Castrejon, Thomas Mensink, Vittorio Ferrari","submitted_at":"2023-06-15T16:03:01Z","abstract_excerpt":"We propose Encyclopedic-VQA, a large scale visual question answering (VQA) dataset featuring visual questions about detailed properties of fine-grained categories and instances. It contains 221k unique question+answer pairs each matched with (up to) 5 images, resulting in a total of 1M VQA samples. Moreover, our dataset comes with a controlled knowledge base derived from Wikipedia, marking the evidence to support each answer. Empirically, we show that our dataset poses a hard challenge for large vision+language models as they perform poorly on our dataset: PaLI [14] is state-of-the-art on OK-V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09224","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/2306.09224/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":"2026-07-05T06:33:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KqSXwZ8q8z04RVIfn5Ii37jdH5y95dhNOZqxwcQgQjajsokrQj1vLi/PL13B7KirYqhK2n0/BVt3uZv9iFJjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:51:14.294845Z"},"content_sha256":"9306604213c0889f223b0999b5dcd07e51dd54a1926050767bee75288f35be0c","schema_version":"1.0","event_id":"sha256:9306604213c0889f223b0999b5dcd07e51dd54a1926050767bee75288f35be0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I7EGHUVSTUEBKVNH6FAL6B6K74/bundle.json","state_url":"https://pith.science/pith/I7EGHUVSTUEBKVNH6FAL6B6K74/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I7EGHUVSTUEBKVNH6FAL6B6K74/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":"2026-08-03T19:51:14Z","links":{"resolver":"https://pith.science/pith/I7EGHUVSTUEBKVNH6FAL6B6K74","bundle":"https://pith.science/pith/I7EGHUVSTUEBKVNH6FAL6B6K74/bundle.json","state":"https://pith.science/pith/I7EGHUVSTUEBKVNH6FAL6B6K74/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I7EGHUVSTUEBKVNH6FAL6B6K74/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:I7EGHUVSTUEBKVNH6FAL6B6K74","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":"2d5543fc079bfb10a451cfd1a4b73186ed58b4914187b5157969eb168a870f14","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T16:03:01Z","title_canon_sha256":"ea5525b154aee59dad7b23cfd8eddc770b705f7b1fee82404c88c81ade458ea9"},"schema_version":"1.0","source":{"id":"2306.09224","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09224","created_at":"2026-07-05T06:33:46Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09224v2","created_at":"2026-07-05T06:33:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09224","created_at":"2026-07-05T06:33:46Z"},{"alias_kind":"pith_short_12","alias_value":"I7EGHUVSTUEB","created_at":"2026-07-05T06:33:46Z"},{"alias_kind":"pith_short_16","alias_value":"I7EGHUVSTUEBKVNH","created_at":"2026-07-05T06:33:46Z"},{"alias_kind":"pith_short_8","alias_value":"I7EGHUVS","created_at":"2026-07-05T06:33:46Z"}],"graph_snapshots":[{"event_id":"sha256:9306604213c0889f223b0999b5dcd07e51dd54a1926050767bee75288f35be0c","target":"graph","created_at":"2026-07-05T06:33:46Z","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/2306.09224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Encyclopedic-VQA, a large scale visual question answering (VQA) dataset featuring visual questions about detailed properties of fine-grained categories and instances. It contains 221k unique question+answer pairs each matched with (up to) 5 images, resulting in a total of 1M VQA samples. Moreover, our dataset comes with a controlled knowledge base derived from Wikipedia, marking the evidence to support each answer. Empirically, we show that our dataset poses a hard challenge for large vision+language models as they perform poorly on our dataset: PaLI [14] is state-of-the-art on OK-V","authors_text":"Andr\\'e Araujo, Arushi Goel, Fei Sha, Felipe Cadar, Howard Zhou, Jasper Uijlings, Lluis Castrejon, Thomas Mensink, Vittorio Ferrari","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T16:03:01Z","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09224","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:d5184a5f501d1f1d6fc4a382ff08e2fdd93852fa38baba9138ee48ac67f1b362","target":"record","created_at":"2026-07-05T06:33:46Z","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":"2d5543fc079bfb10a451cfd1a4b73186ed58b4914187b5157969eb168a870f14","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T16:03:01Z","title_canon_sha256":"ea5525b154aee59dad7b23cfd8eddc770b705f7b1fee82404c88c81ade458ea9"},"schema_version":"1.0","source":{"id":"2306.09224","kind":"arxiv","version":2}},"canonical_sha256":"47c863d2b29d081555a7f140bf07caff1aba93e4d3ce27868bc51b0a83b83113","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47c863d2b29d081555a7f140bf07caff1aba93e4d3ce27868bc51b0a83b83113","first_computed_at":"2026-07-05T06:33:46.115305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:46.115305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hF8meoRGqef/6H86akQfIiAYLvuCBcHxyJS6hKINPx4udDYMq38RkW7W82AQNaEJoizniWZQvBQhrVemNlciCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:46.115730Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09224","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5184a5f501d1f1d6fc4a382ff08e2fdd93852fa38baba9138ee48ac67f1b362","sha256:9306604213c0889f223b0999b5dcd07e51dd54a1926050767bee75288f35be0c"],"state_sha256":"a254298cd777a3b8bb11a94d9aaf7d33199996cc930d7e0e8e8fabeb31081920"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LZmtIyAwJKW/lXHEqcibUQgy6pOyV2NEgc/DcyfCiYeRgVKXLKVqRZqjVGAsL6SjddevdqiGTlvH5XBLXlC6Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:51:14.300206Z","bundle_sha256":"b96bb7ce49ebc9274d25835a3ea85e3f72193889edc4b85d879dc23bdb051231"}}