{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V5PTIYMVHPFATLEEJRQANBX5NL","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":"c32493794ae921ca2e57ab64f73f3af039a49379ed0e9bbd2a8993f66025e00e","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T16:47:32Z","title_canon_sha256":"ed589b8b88ec15aae02064d53bc62b91001cc3d5a24ed458add025257f23b0a8"},"schema_version":"1.0","source":{"id":"2409.18046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18046","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18046v1","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18046","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"V5PTIYMVHPFA","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"pith_short_16","alias_value":"V5PTIYMVHPFATLEE","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"pith_short_8","alias_value":"V5PTIYMV","created_at":"2026-07-05T09:12:19Z"}],"graph_snapshots":[{"event_id":"sha256:ac22684d9e32a5a5a67adbdd7443a704d601289dc31e8a6cd15d922e8ad9823c","target":"graph","created_at":"2026-07-05T09:12:19Z","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/2409.18046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in image captioning have explored text-only training methods to overcome the limitations of paired image-text data. However, existing text-only training methods often overlook the modality gap between using text data during training and employing images during inference. To address this issue, we propose a novel approach called Image-like Retrieval, which aligns text features with visually relevant features to mitigate the modality gap. Our method further enhances the accuracy of generated captions by designing a Fusion Module that integrates retrieved captions with input f","authors_text":"Dong-Jin Kim, Si-Woo Kim, Soeun Lee, Taewhan Kim","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T16:47:32Z","title":"IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18046","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":"sha256:29347964c6499730da4f18af34e88e3be2f2f2608a6e2318a29bca0fc82c9c44","target":"record","created_at":"2026-07-05T09:12:19Z","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":"c32493794ae921ca2e57ab64f73f3af039a49379ed0e9bbd2a8993f66025e00e","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T16:47:32Z","title_canon_sha256":"ed589b8b88ec15aae02064d53bc62b91001cc3d5a24ed458add025257f23b0a8"},"schema_version":"1.0","source":{"id":"2409.18046","kind":"arxiv","version":1}},"canonical_sha256":"af5f3461953bca09ac844c600686fd6ae2ebb0ecea47f66b1ddd4b0addc6dac5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af5f3461953bca09ac844c600686fd6ae2ebb0ecea47f66b1ddd4b0addc6dac5","first_computed_at":"2026-07-05T09:12:19.779451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:19.779451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R90L14MRfEjk9YPW7R1FlJiCEVJ5ja/fA+riRubh6nI9PWM/VpPJRbu6kNHSV4lsAL+8KthKqXpvLNqAmnpMBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:19.780036Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.18046","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29347964c6499730da4f18af34e88e3be2f2f2608a6e2318a29bca0fc82c9c44","sha256:ac22684d9e32a5a5a67adbdd7443a704d601289dc31e8a6cd15d922e8ad9823c"],"state_sha256":"da823cb790d6bd5f0add95d44b8ad3c2733a1548b4d6cb2ad3adaed13cd0cf7a"}