{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H5GEAT5Q47NTGSPSAA6JP5PPDE","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":"c65f61a2f07033e5842675815b9b645049a494e059f4d7de43bd0e69e1f8c2c7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T11:02:47Z","title_canon_sha256":"3c19aa379d366c7cab940f6b80fe2397febb3cb02ba1cf965c851b4db5fe4c8a"},"schema_version":"1.0","source":{"id":"2303.03032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03032","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03032v1","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03032","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"pith_short_12","alias_value":"H5GEAT5Q47NT","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"pith_short_16","alias_value":"H5GEAT5Q47NTGSPS","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"pith_short_8","alias_value":"H5GEAT5Q","created_at":"2026-07-05T05:48:18Z"}],"graph_snapshots":[{"event_id":"sha256:652013b80f242acf5b80e8b66a59b78ba1ded2c0895db76dab5079affeaa1ad6","target":"graph","created_at":"2026-07-05T05:48:18Z","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/2303.03032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale pre-trained multi-modal models (e.g., CLIP) demonstrate strong zero-shot transfer capability in many discriminative tasks. Their adaptation to zero-shot image-conditioned text generation tasks has drawn increasing interest. Prior arts approach to zero-shot captioning by either utilizing the existing large language models (e.g., GPT-2) or pre-training the encoder-decoder network in an end-to-end manner. In this work, we propose a simple framework, named DeCap, for zero-shot captioning. We introduce a lightweight visual-aware language decoder. This decoder is both data-efficient and ","authors_text":"Linchao Zhu, Longyin Wen, Wei Li, Yi Yang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T11:02:47Z","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03032","kind":"arxiv","version":1},"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":"sha256:1ccd3ea31c447b74482f36fc3916671b7e91a2ebcaea851e162f8d5db0e4c521","target":"record","created_at":"2026-07-05T05:48:18Z","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":"c65f61a2f07033e5842675815b9b645049a494e059f4d7de43bd0e69e1f8c2c7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T11:02:47Z","title_canon_sha256":"3c19aa379d366c7cab940f6b80fe2397febb3cb02ba1cf965c851b4db5fe4c8a"},"schema_version":"1.0","source":{"id":"2303.03032","kind":"arxiv","version":1}},"canonical_sha256":"3f4c404fb0e7db3349f2003c97f5ef19107dff86e5c77acbc37d46151587c346","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f4c404fb0e7db3349f2003c97f5ef19107dff86e5c77acbc37d46151587c346","first_computed_at":"2026-07-05T05:48:18.461693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:18.461693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d6QDkdp35rp1/vKKURT/C1o6QJ9KEfcphdp3ZYqXlVIxtnVD9QgivHCV44qKcKb4DzDSbTk1LPcx9YDlQA+tCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:18.462072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.03032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ccd3ea31c447b74482f36fc3916671b7e91a2ebcaea851e162f8d5db0e4c521","sha256:652013b80f242acf5b80e8b66a59b78ba1ded2c0895db76dab5079affeaa1ad6"],"state_sha256":"094e1334f256a0191bd17c621902479ac9d4b8a36054f4af2d51490ea506651c"}