{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2PG5B4HFYXMOVJD356TGQRNVJO","short_pith_number":"pith:2PG5B4HF","schema_version":"1.0","canonical_sha256":"d3cdd0f0e5c5d8eaa47befa66845b54b833d1e78c05d28e8edfd0715032f9948","source":{"kind":"arxiv","id":"2507.18616","version":1},"attestation_state":"computed","paper":{"title":"SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong-Jin Kim, MinJu Jeon, Si-Woo Kim, Soeun Lee, Taewhan Kim, Ye-Chan Kim","submitted_at":"2025-07-24T17:53:26Z","abstract_excerpt":"Zero-shot Image Captioning (ZIC) increasingly utilizes synthetic datasets generated by text-to-image (T2I) models to mitigate the need for costly manual annotation. However, these T2I models often produce images that exhibit semantic misalignments with their corresponding input captions (e.g., missing objects, incorrect attributes), resulting in noisy synthetic image-caption pairs that can hinder model training. Existing dataset pruning techniques are largely designed for removing noisy text in web-crawled data. However, these methods are ill-suited for the distinct challenges of synthetic dat"},"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":"2507.18616","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-24T17:53:26Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"9484094e53180955bde8cbc1d56408c3450793c06c5e62a8f413031f4f635c9a","abstract_canon_sha256":"aded9498fe8367c987ee5e777cf8fcc5742a642fc92d16458d40625b91bfe5be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:51.124142Z","signature_b64":"2TqWnCyztAXkoghtNkjMOi5yUP5pTJI1GWlV7x7I9SxOGH9+xtDK9/29Yhqst/qJ1t+2goHMVPbP5RJRkbP6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3cdd0f0e5c5d8eaa47befa66845b54b833d1e78c05d28e8edfd0715032f9948","last_reissued_at":"2026-07-05T11:42:51.123582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:51.123582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong-Jin Kim, MinJu Jeon, Si-Woo Kim, Soeun Lee, Taewhan Kim, Ye-Chan Kim","submitted_at":"2025-07-24T17:53:26Z","abstract_excerpt":"Zero-shot Image Captioning (ZIC) increasingly utilizes synthetic datasets generated by text-to-image (T2I) models to mitigate the need for costly manual annotation. However, these T2I models often produce images that exhibit semantic misalignments with their corresponding input captions (e.g., missing objects, incorrect attributes), resulting in noisy synthetic image-caption pairs that can hinder model training. Existing dataset pruning techniques are largely designed for removing noisy text in web-crawled data. However, these methods are ill-suited for the distinct challenges of synthetic dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18616","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/2507.18616/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":"2507.18616","created_at":"2026-07-05T11:42:51.123647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18616v1","created_at":"2026-07-05T11:42:51.123647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18616","created_at":"2026-07-05T11:42:51.123647+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PG5B4HFYXMO","created_at":"2026-07-05T11:42:51.123647+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PG5B4HFYXMOVJD3","created_at":"2026-07-05T11:42:51.123647+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PG5B4HF","created_at":"2026-07-05T11:42:51.123647+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04602","citing_title":"Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PG5B4HFYXMOVJD356TGQRNVJO","json":"https://pith.science/pith/2PG5B4HFYXMOVJD356TGQRNVJO.json","graph_json":"https://pith.science/api/pith-number/2PG5B4HFYXMOVJD356TGQRNVJO/graph.json","events_json":"https://pith.science/api/pith-number/2PG5B4HFYXMOVJD356TGQRNVJO/events.json","paper":"https://pith.science/paper/2PG5B4HF"},"agent_actions":{"view_html":"https://pith.science/pith/2PG5B4HFYXMOVJD356TGQRNVJO","download_json":"https://pith.science/pith/2PG5B4HFYXMOVJD356TGQRNVJO.json","view_paper":"https://pith.science/paper/2PG5B4HF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18616&json=true","fetch_graph":"https://pith.science/api/pith-number/2PG5B4HFYXMOVJD356TGQRNVJO/graph.json","fetch_events":"https://pith.science/api/pith-number/2PG5B4HFYXMOVJD356TGQRNVJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PG5B4HFYXMOVJD356TGQRNVJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PG5B4HFYXMOVJD356TGQRNVJO/action/storage_attestation","attest_author":"https://pith.science/pith/2PG5B4HFYXMOVJD356TGQRNVJO/action/author_attestation","sign_citation":"https://pith.science/pith/2PG5B4HFYXMOVJD356TGQRNVJO/action/citation_signature","submit_replication":"https://pith.science/pith/2PG5B4HFYXMOVJD356TGQRNVJO/action/replication_record"}},"created_at":"2026-07-05T11:42:51.123647+00:00","updated_at":"2026-07-05T11:42:51.123647+00:00"}