{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZIUFXITXU2DLWHVZXIDCLPF36Q","short_pith_number":"pith:ZIUFXITX","canonical_record":{"source":{"id":"2305.02677","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T09:48:22Z","cross_cats_sorted":[],"title_canon_sha256":"9f965cde20478faf4513e8b05379cb1e92d3c5152ab9de081ea5c669dd07b5f3","abstract_canon_sha256":"ec24662e239e6349a3646ff9ace15f0c9e7b2e5c5185511bc3ab35477d794df5"},"schema_version":"1.0"},"canonical_sha256":"ca285ba277a686bb1eb9ba0625bcbbf433cb1a587e4670b00a61043ca51bcedd","source":{"kind":"arxiv","id":"2305.02677","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZIUFXITXU2DLWHVZXIDCLPF36Q","target":"record","payload":{"canonical_record":{"source":{"id":"2305.02677","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T09:48:22Z","cross_cats_sorted":[],"title_canon_sha256":"9f965cde20478faf4513e8b05379cb1e92d3c5152ab9de081ea5c669dd07b5f3","abstract_canon_sha256":"ec24662e239e6349a3646ff9ace15f0c9e7b2e5c5185511bc3ab35477d794df5"},"schema_version":"1.0"},"canonical_sha256":"ca285ba277a686bb1eb9ba0625bcbbf433cb1a587e4670b00a61043ca51bcedd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:18.167643Z","signature_b64":"aaVwx0baCC0kIFtOxwU/GkdCzzWuhrvyJM3ma4aY6R9nfrTtc9fg2eC8Xodc0T0OT1DNhSxRiysTqM6uNiBlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca285ba277a686bb1eb9ba0625bcbbf433cb1a587e4670b00a61043ca51bcedd","last_reissued_at":"2026-07-05T06:28:18.167211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:18.167211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.02677","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:28:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ksm96ewLlIBMf5Rkn0UL+4H931W7IjdkYL5NA8csMDWzRJ0aS2LfgrBulh2xh7Ze0sjVhEzt4RqSAMS226gaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T09:47:57.414278Z"},"content_sha256":"a623d4ffa9438a892e2ad9417cfba039ecdc8e6fc3166ec6b9fa9f45a58f226b","schema_version":"1.0","event_id":"sha256:a623d4ffa9438a892e2ad9417cfba039ecdc8e6fc3166ec6b9fa9f45a58f226b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZIUFXITXU2DLWHVZXIDCLPF36Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zheng, Jinrui Zhang, Junjie Fei, Mingqi Gao, Shanshan Zhao, Teng Wang, Yunlong Tang, Zhe Li","submitted_at":"2023-05-04T09:48:22Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02677","kind":"arxiv","version":3},"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/2305.02677/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":"2026-07-05T06:28:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dOaToICg3+VLQ1YmZijkOFHZU8euPmlPKuhOAmrn9fgTmUcZEYPI3OLXZOBN0yh64skuR+SSWKuFWiwHcHBnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T09:47:57.414661Z"},"content_sha256":"05d24f8fcc4e03889553e76d7bdf80ceb27cbab9fb3f1709a5c13352be673753","schema_version":"1.0","event_id":"sha256:05d24f8fcc4e03889553e76d7bdf80ceb27cbab9fb3f1709a5c13352be673753"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZIUFXITXU2DLWHVZXIDCLPF36Q/bundle.json","state_url":"https://pith.science/pith/ZIUFXITXU2DLWHVZXIDCLPF36Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZIUFXITXU2DLWHVZXIDCLPF36Q/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":"2026-07-10T09:47:57Z","links":{"resolver":"https://pith.science/pith/ZIUFXITXU2DLWHVZXIDCLPF36Q","bundle":"https://pith.science/pith/ZIUFXITXU2DLWHVZXIDCLPF36Q/bundle.json","state":"https://pith.science/pith/ZIUFXITXU2DLWHVZXIDCLPF36Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZIUFXITXU2DLWHVZXIDCLPF36Q/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y5Lp0vpqGQDwnJ9l6tGcSvpiZPUDk+f/tKhbsQhM7Qwkyoj6r6by7s+1jjhxlAdI5NrjWm1sv8/Xw1NVGEITCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T09:47:57.416541Z","bundle_sha256":"0027be9b83af29d77eebb0399d1d2eb73a45e48cfba893da3b023476cf521c5a"}}