{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LZCWOGDDAVCI2TRS3HCQXUBOPQ","short_pith_number":"pith:LZCWOGDD","schema_version":"1.0","canonical_sha256":"5e4567186305448d4e32d9c50bd02e7c2f13b09ed870f67784b48ab134599c69","source":{"kind":"arxiv","id":"2412.01115","version":1},"attestation_state":"computed","paper":{"title":"DIR: Retrieval-Augmented Image Captioning with Comprehensive Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wu, Xiao Sun, Zhihang Zhong","submitted_at":"2024-12-02T04:39:17Z","abstract_excerpt":"Image captioning models often suffer from performance degradation when applied to novel datasets, as they are typically trained on domain-specific data. To enhance generalization in out-of-domain scenarios, retrieval-augmented approaches have garnered increasing attention. However, current methods face two key challenges: (1) image features used for retrieval are often optimized based on ground-truth (GT) captions, which represent the image from a specific perspective and are influenced by annotator biases, and (2) they underutilize the full potential of retrieved text, typically relying on ra"},"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":"2412.01115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T04:39:17Z","cross_cats_sorted":[],"title_canon_sha256":"e850802cebc598bcb03c8a461c5d253b5bc062adda95f9b4470721cb9147edb9","abstract_canon_sha256":"f561cf586d2318e6bfa020a5d0e910cb4633b565b2d2c07c81e8383c3541d0f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:54.119399Z","signature_b64":"RafClzFyNn2dmJ0tlFn2blVaFJAeCqEs2xfLyIp2OKkF8o19LmKU5knpz+8TqCfltx9j69gNb1EzGL6Si2UNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e4567186305448d4e32d9c50bd02e7c2f13b09ed870f67784b48ab134599c69","last_reissued_at":"2026-07-05T09:42:54.118955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:54.118955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIR: Retrieval-Augmented Image Captioning with Comprehensive Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wu, Xiao Sun, Zhihang Zhong","submitted_at":"2024-12-02T04:39:17Z","abstract_excerpt":"Image captioning models often suffer from performance degradation when applied to novel datasets, as they are typically trained on domain-specific data. To enhance generalization in out-of-domain scenarios, retrieval-augmented approaches have garnered increasing attention. However, current methods face two key challenges: (1) image features used for retrieval are often optimized based on ground-truth (GT) captions, which represent the image from a specific perspective and are influenced by annotator biases, and (2) they underutilize the full potential of retrieved text, typically relying on ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01115","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/2412.01115/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":"2412.01115","created_at":"2026-07-05T09:42:54.119015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01115v1","created_at":"2026-07-05T09:42:54.119015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01115","created_at":"2026-07-05T09:42:54.119015+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZCWOGDDAVCI","created_at":"2026-07-05T09:42:54.119015+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZCWOGDDAVCI2TRS","created_at":"2026-07-05T09:42:54.119015+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZCWOGDD","created_at":"2026-07-05T09:42:54.119015+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18553","citing_title":"Hierarchical Multi-Modal Retrieval for Knowledge-Grounded News Image Captioning","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZCWOGDDAVCI2TRS3HCQXUBOPQ","json":"https://pith.science/pith/LZCWOGDDAVCI2TRS3HCQXUBOPQ.json","graph_json":"https://pith.science/api/pith-number/LZCWOGDDAVCI2TRS3HCQXUBOPQ/graph.json","events_json":"https://pith.science/api/pith-number/LZCWOGDDAVCI2TRS3HCQXUBOPQ/events.json","paper":"https://pith.science/paper/LZCWOGDD"},"agent_actions":{"view_html":"https://pith.science/pith/LZCWOGDDAVCI2TRS3HCQXUBOPQ","download_json":"https://pith.science/pith/LZCWOGDDAVCI2TRS3HCQXUBOPQ.json","view_paper":"https://pith.science/paper/LZCWOGDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01115&json=true","fetch_graph":"https://pith.science/api/pith-number/LZCWOGDDAVCI2TRS3HCQXUBOPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LZCWOGDDAVCI2TRS3HCQXUBOPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZCWOGDDAVCI2TRS3HCQXUBOPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZCWOGDDAVCI2TRS3HCQXUBOPQ/action/storage_attestation","attest_author":"https://pith.science/pith/LZCWOGDDAVCI2TRS3HCQXUBOPQ/action/author_attestation","sign_citation":"https://pith.science/pith/LZCWOGDDAVCI2TRS3HCQXUBOPQ/action/citation_signature","submit_replication":"https://pith.science/pith/LZCWOGDDAVCI2TRS3HCQXUBOPQ/action/replication_record"}},"created_at":"2026-07-05T09:42:54.119015+00:00","updated_at":"2026-07-05T09:42:54.119015+00:00"}