{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6GADPGLJBCYHQJJ7LDVB7TFXXQ","short_pith_number":"pith:6GADPGLJ","schema_version":"1.0","canonical_sha256":"f18037996908b078253f58ea1fccb7bc1f30606a95ce24bd6cd6fba9ccd8d39a","source":{"kind":"arxiv","id":"2307.00716","version":2},"attestation_state":"computed","paper":{"title":"JourneyDB: A Benchmark for Generative Image Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aojun Zhou, Haodong Duan, Hao Li, Hongsheng Li, Jifeng Dai, Junting Pan, Keqiang Sun, Limin Wang, Renrui Zhang, Xiaoshi Wu, Yi Wang, Yu Qiao, Yuying Ge, Zipeng Qin","submitted_at":"2023-07-03T02:39:08Z","abstract_excerpt":"While recent advancements in vision-language models have had a transformative impact on multi-modal comprehension, the extent to which these models possess the ability to comprehend generated images remains uncertain. Synthetic images, in comparison to real data, encompass a higher level of diversity in terms of both content and style, thereby presenting significant challenges for the models to fully grasp. In light of this challenge, we introduce a comprehensive dataset, referred to as JourneyDB, that caters to the domain of generative images within the context of multi-modal visual understan"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.00716","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-03T02:39:08Z","cross_cats_sorted":[],"title_canon_sha256":"7a69bbcecf85b125a79d0a0394f39c121ccb769372d0cbff3c01a7f670a6b6de","abstract_canon_sha256":"9cd707af8a5eba48ca1cb1780f45c8269c37f827463dabcb5e5a6cc9a699248e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:31.217403Z","signature_b64":"DPN/Xc5thibyHcHQhlEKk8xqB6pAYEvJBF0vInWmH/hOkDff76zW76Nm9n9Ve5+jjAaXJtUzcPUhh2vyoeXVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f18037996908b078253f58ea1fccb7bc1f30606a95ce24bd6cd6fba9ccd8d39a","last_reissued_at":"2026-07-05T07:06:31.216888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:31.216888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JourneyDB: A Benchmark for Generative Image Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aojun Zhou, Haodong Duan, Hao Li, Hongsheng Li, Jifeng Dai, Junting Pan, Keqiang Sun, Limin Wang, Renrui Zhang, Xiaoshi Wu, Yi Wang, Yu Qiao, Yuying Ge, Zipeng Qin","submitted_at":"2023-07-03T02:39:08Z","abstract_excerpt":"While recent advancements in vision-language models have had a transformative impact on multi-modal comprehension, the extent to which these models possess the ability to comprehend generated images remains uncertain. Synthetic images, in comparison to real data, encompass a higher level of diversity in terms of both content and style, thereby presenting significant challenges for the models to fully grasp. In light of this challenge, we introduce a comprehensive dataset, referred to as JourneyDB, that caters to the domain of generative images within the context of multi-modal visual understan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00716","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/2307.00716/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.00716","created_at":"2026-07-05T07:06:31.216950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00716v2","created_at":"2026-07-05T07:06:31.216950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00716","created_at":"2026-07-05T07:06:31.216950+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GADPGLJBCYH","created_at":"2026-07-05T07:06:31.216950+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GADPGLJBCYHQJJ7","created_at":"2026-07-05T07:06:31.216950+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GADPGLJ","created_at":"2026-07-05T07:06:31.216950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.14396","citing_title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GADPGLJBCYHQJJ7LDVB7TFXXQ","json":"https://pith.science/pith/6GADPGLJBCYHQJJ7LDVB7TFXXQ.json","graph_json":"https://pith.science/api/pith-number/6GADPGLJBCYHQJJ7LDVB7TFXXQ/graph.json","events_json":"https://pith.science/api/pith-number/6GADPGLJBCYHQJJ7LDVB7TFXXQ/events.json","paper":"https://pith.science/paper/6GADPGLJ"},"agent_actions":{"view_html":"https://pith.science/pith/6GADPGLJBCYHQJJ7LDVB7TFXXQ","download_json":"https://pith.science/pith/6GADPGLJBCYHQJJ7LDVB7TFXXQ.json","view_paper":"https://pith.science/paper/6GADPGLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00716&json=true","fetch_graph":"https://pith.science/api/pith-number/6GADPGLJBCYHQJJ7LDVB7TFXXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6GADPGLJBCYHQJJ7LDVB7TFXXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GADPGLJBCYHQJJ7LDVB7TFXXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GADPGLJBCYHQJJ7LDVB7TFXXQ/action/storage_attestation","attest_author":"https://pith.science/pith/6GADPGLJBCYHQJJ7LDVB7TFXXQ/action/author_attestation","sign_citation":"https://pith.science/pith/6GADPGLJBCYHQJJ7LDVB7TFXXQ/action/citation_signature","submit_replication":"https://pith.science/pith/6GADPGLJBCYHQJJ7LDVB7TFXXQ/action/replication_record"}},"created_at":"2026-07-05T07:06:31.216950+00:00","updated_at":"2026-07-05T07:06:31.216950+00:00"}