{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MPPSSBA3K6PPIILDTIFDABO5MZ","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":"9f7fb73c72d9132f41d08443f3e338f2220b0deb2711ff646e1123f88bde4816","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-06T14:00:31Z","title_canon_sha256":"15a259f2ae1f62c8fcddcb1ab65a62356b517133adebf6885945871478365266"},"schema_version":"1.0","source":{"id":"2403.03715","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03715","created_at":"2026-07-05T07:52:52Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03715v1","created_at":"2026-07-05T07:52:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03715","created_at":"2026-07-05T07:52:52Z"},{"alias_kind":"pith_short_12","alias_value":"MPPSSBA3K6PP","created_at":"2026-07-05T07:52:52Z"},{"alias_kind":"pith_short_16","alias_value":"MPPSSBA3K6PPIILD","created_at":"2026-07-05T07:52:52Z"},{"alias_kind":"pith_short_8","alias_value":"MPPSSBA3","created_at":"2026-07-05T07:52:52Z"}],"graph_snapshots":[{"event_id":"sha256:ad69033e2d7fa0d5fb5475997e18fa0076b4bc403c806bef31487fc82ee78c66","target":"graph","created_at":"2026-07-05T07:52:52Z","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/2403.03715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot image captioning (IC) without well-paired image-text data can be divided into two categories, training-free and text-only-training. Generally, these two types of methods realize zero-shot IC by integrating pretrained vision-language models like CLIP for image-text similarity evaluation and a pre-trained language model (LM) for caption generation. The main difference between them is whether using a textual corpus to train the LM. Though achieving attractive performance w.r.t. some metrics, existing methods often exhibit some common drawbacks. Training-free methods tend to produce hall","authors_text":"Bo Chen, Chiyu Chen, Hao Zhang, Yan Xie, Zequn Zeng, Zhengjue Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-06T14:00:31Z","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03715","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:d6d2ec6867566fdca8354ae371f7dd2da6641f70146cf95faae808bad4f04984","target":"record","created_at":"2026-07-05T07:52:52Z","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":"9f7fb73c72d9132f41d08443f3e338f2220b0deb2711ff646e1123f88bde4816","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-06T14:00:31Z","title_canon_sha256":"15a259f2ae1f62c8fcddcb1ab65a62356b517133adebf6885945871478365266"},"schema_version":"1.0","source":{"id":"2403.03715","kind":"arxiv","version":1}},"canonical_sha256":"63df29041b579ef421639a0a3005dd6649bf01cf6ebcaa0be58351a06bb51c9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63df29041b579ef421639a0a3005dd6649bf01cf6ebcaa0be58351a06bb51c9c","first_computed_at":"2026-07-05T07:52:52.064066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:52.064066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"upvd31KTr7j1UMAEd/rdoKDD3TZh4XBmdrtjSfXLIayEL8JK79PGOvpbUpm5fpXtfUczlluEapcxo69hFxqLDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:52.064423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03715","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6d2ec6867566fdca8354ae371f7dd2da6641f70146cf95faae808bad4f04984","sha256:ad69033e2d7fa0d5fb5475997e18fa0076b4bc403c806bef31487fc82ee78c66"],"state_sha256":"ef75caa6f3b8c342fe3ba5bd3bed7307d9973b9d22ba3089c4e41ddb14f937bc"}