{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MPPSSBA3K6PPIILDTIFDABO5MZ","short_pith_number":"pith:MPPSSBA3","schema_version":"1.0","canonical_sha256":"63df29041b579ef421639a0a3005dd6649bf01cf6ebcaa0be58351a06bb51c9c","source":{"kind":"arxiv","id":"2403.03715","version":1},"attestation_state":"computed","paper":{"title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Chen, Chiyu Chen, Hao Zhang, Yan Xie, Zequn Zeng, Zhengjue Wang","submitted_at":"2024-03-06T14:00:31Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.03715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-06T14:00:31Z","cross_cats_sorted":[],"title_canon_sha256":"15a259f2ae1f62c8fcddcb1ab65a62356b517133adebf6885945871478365266","abstract_canon_sha256":"9f7fb73c72d9132f41d08443f3e338f2220b0deb2711ff646e1123f88bde4816"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:52.064423Z","signature_b64":"upvd31KTr7j1UMAEd/rdoKDD3TZh4XBmdrtjSfXLIayEL8JK79PGOvpbUpm5fpXtfUczlluEapcxo69hFxqLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63df29041b579ef421639a0a3005dd6649bf01cf6ebcaa0be58351a06bb51c9c","last_reissued_at":"2026-07-05T07:52:52.064066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:52.064066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Chen, Chiyu Chen, Hao Zhang, Yan Xie, Zequn Zeng, Zhengjue Wang","submitted_at":"2024-03-06T14:00:31Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03715","kind":"arxiv","version":1},"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/2403.03715/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.03715","created_at":"2026-07-05T07:52:52.064123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03715v1","created_at":"2026-07-05T07:52:52.064123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03715","created_at":"2026-07-05T07:52:52.064123+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPPSSBA3K6PP","created_at":"2026-07-05T07:52:52.064123+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPPSSBA3K6PPIILD","created_at":"2026-07-05T07:52:52.064123+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPPSSBA3","created_at":"2026-07-05T07:52:52.064123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MPPSSBA3K6PPIILDTIFDABO5MZ","json":"https://pith.science/pith/MPPSSBA3K6PPIILDTIFDABO5MZ.json","graph_json":"https://pith.science/api/pith-number/MPPSSBA3K6PPIILDTIFDABO5MZ/graph.json","events_json":"https://pith.science/api/pith-number/MPPSSBA3K6PPIILDTIFDABO5MZ/events.json","paper":"https://pith.science/paper/MPPSSBA3"},"agent_actions":{"view_html":"https://pith.science/pith/MPPSSBA3K6PPIILDTIFDABO5MZ","download_json":"https://pith.science/pith/MPPSSBA3K6PPIILDTIFDABO5MZ.json","view_paper":"https://pith.science/paper/MPPSSBA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03715&json=true","fetch_graph":"https://pith.science/api/pith-number/MPPSSBA3K6PPIILDTIFDABO5MZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MPPSSBA3K6PPIILDTIFDABO5MZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPPSSBA3K6PPIILDTIFDABO5MZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPPSSBA3K6PPIILDTIFDABO5MZ/action/storage_attestation","attest_author":"https://pith.science/pith/MPPSSBA3K6PPIILDTIFDABO5MZ/action/author_attestation","sign_citation":"https://pith.science/pith/MPPSSBA3K6PPIILDTIFDABO5MZ/action/citation_signature","submit_replication":"https://pith.science/pith/MPPSSBA3K6PPIILDTIFDABO5MZ/action/replication_record"}},"created_at":"2026-07-05T07:52:52.064123+00:00","updated_at":"2026-07-05T07:52:52.064123+00:00"}