{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6V7CRQMNNIPT4KNMFGPCBQATUV","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":"a9d6640714f4186a4adb4830f84b352bbf1d7146533376b4adcb8263265af7df","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-10T15:35:11Z","title_canon_sha256":"4e0e2a131c58553bd51325357cddbf9086f3ce9537f820c94108556427562984"},"schema_version":"1.0","source":{"id":"2303.05983","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.05983","created_at":"2026-07-05T07:46:16Z"},{"alias_kind":"arxiv_version","alias_value":"2303.05983v3","created_at":"2026-07-05T07:46:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05983","created_at":"2026-07-05T07:46:16Z"},{"alias_kind":"pith_short_12","alias_value":"6V7CRQMNNIPT","created_at":"2026-07-05T07:46:16Z"},{"alias_kind":"pith_short_16","alias_value":"6V7CRQMNNIPT4KNM","created_at":"2026-07-05T07:46:16Z"},{"alias_kind":"pith_short_8","alias_value":"6V7CRQMN","created_at":"2026-07-05T07:46:16Z"}],"graph_snapshots":[{"event_id":"sha256:225b7f77c8ef05d31dadc91a7c15331e6fba104ae5455610d6d45b49a6299a02","target":"graph","created_at":"2026-07-05T07:46:16Z","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/2303.05983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent success of ChatGPT and GPT-4 has drawn widespread attention to multimodal dialogue systems. However, there is a lack of datasets in the academic community that can effectively evaluate the multimodal generation capabilities of Visual Language Models (VLMs) in textual-visual chat tasks. In this paper, we address this gap by introducing two novel multimodal datasets: the synthetic CLEVR-ATVC dataset (620K) and the manually pictured Fruit-ATVC dataset (50K). These datasets incorporate both visual and text-based inputs and outputs. Furthermore, to facilitate the accountability of multim","authors_text":"Yuliang Liu, Zhiwei Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-10T15:35:11Z","title":"Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05983","kind":"arxiv","version":3},"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":"sha256:22c8073522605b20232a5eb4ae7daf7a96f763f54a5b3f6978e253dd21765ab8","target":"record","created_at":"2026-07-05T07:46:16Z","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":"a9d6640714f4186a4adb4830f84b352bbf1d7146533376b4adcb8263265af7df","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-10T15:35:11Z","title_canon_sha256":"4e0e2a131c58553bd51325357cddbf9086f3ce9537f820c94108556427562984"},"schema_version":"1.0","source":{"id":"2303.05983","kind":"arxiv","version":3}},"canonical_sha256":"f57e28c18d6a1f3e29ac299e20c013a567e3a2d91e59db14b672c458aea8af05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f57e28c18d6a1f3e29ac299e20c013a567e3a2d91e59db14b672c458aea8af05","first_computed_at":"2026-07-05T07:46:16.586258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:16.586258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WnQbYRiMAvdnGNRTK7ViLjDvqTZNZuB6n1l3p1oPOwKvmNEmz2uWa6XQLcphJ5Mu8kGofyar1G+NhrCbJfJYDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:16.586771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.05983","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22c8073522605b20232a5eb4ae7daf7a96f763f54a5b3f6978e253dd21765ab8","sha256:225b7f77c8ef05d31dadc91a7c15331e6fba104ae5455610d6d45b49a6299a02"],"state_sha256":"0b88d9baddfff98b906e0ee3188e931f06189b04f2f09c26d653ca2034ec7ad8"}