{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZIUFXITXU2DLWHVZXIDCLPF36Q","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":"ec24662e239e6349a3646ff9ace15f0c9e7b2e5c5185511bc3ab35477d794df5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T09:48:22Z","title_canon_sha256":"9f965cde20478faf4513e8b05379cb1e92d3c5152ab9de081ea5c669dd07b5f3"},"schema_version":"1.0","source":{"id":"2305.02677","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02677","created_at":"2026-07-05T06:28:18Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02677v3","created_at":"2026-07-05T06:28:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02677","created_at":"2026-07-05T06:28:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZIUFXITXU2DL","created_at":"2026-07-05T06:28:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZIUFXITXU2DLWHVZ","created_at":"2026-07-05T06:28:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZIUFXITX","created_at":"2026-07-05T06:28:18Z"}],"graph_snapshots":[{"event_id":"sha256:05d24f8fcc4e03889553e76d7bdf80ceb27cbab9fb3f1709a5c13352be673753","target":"graph","created_at":"2026-07-05T06:28:18Z","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/2305.02677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Controllable image captioning is an emerging multimodal topic that aims to describe the image with natural language following human purpose, $\\textit{e.g.}$, looking at the specified regions or telling in a particular text style. State-of-the-art methods are trained on annotated pairs of input controls and output captions. However, the scarcity of such well-annotated multimodal data largely limits their usability and scalability for interactive AI systems. Leveraging unimodal instruction-following foundation models is a promising alternative that benefits from broader sources of data. In this ","authors_text":"Hao Zheng, Jinrui Zhang, Junjie Fei, Mingqi Gao, Shanshan Zhao, Teng Wang, Yunlong Tang, Zhe Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T09:48:22Z","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02677","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:a623d4ffa9438a892e2ad9417cfba039ecdc8e6fc3166ec6b9fa9f45a58f226b","target":"record","created_at":"2026-07-05T06:28:18Z","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":"ec24662e239e6349a3646ff9ace15f0c9e7b2e5c5185511bc3ab35477d794df5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T09:48:22Z","title_canon_sha256":"9f965cde20478faf4513e8b05379cb1e92d3c5152ab9de081ea5c669dd07b5f3"},"schema_version":"1.0","source":{"id":"2305.02677","kind":"arxiv","version":3}},"canonical_sha256":"ca285ba277a686bb1eb9ba0625bcbbf433cb1a587e4670b00a61043ca51bcedd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca285ba277a686bb1eb9ba0625bcbbf433cb1a587e4670b00a61043ca51bcedd","first_computed_at":"2026-07-05T06:28:18.167211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:18.167211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aaVwx0baCC0kIFtOxwU/GkdCzzWuhrvyJM3ma4aY6R9nfrTtc9fg2eC8Xodc0T0OT1DNhSxRiysTqM6uNiBlDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:18.167643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.02677","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a623d4ffa9438a892e2ad9417cfba039ecdc8e6fc3166ec6b9fa9f45a58f226b","sha256:05d24f8fcc4e03889553e76d7bdf80ceb27cbab9fb3f1709a5c13352be673753"],"state_sha256":"88173467198ab248d61b8c9ca97aa07de79c2e034e9b5c3dbc08eb1417be622f"}