{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GOB26I4FL4XGLIXQWI26K2USJ7","short_pith_number":"pith:GOB26I4F","schema_version":"1.0","canonical_sha256":"3383af23855f2e65a2f0b235e56a924ff257e4de2957ecdb447531e6fc44e8dc","source":{"kind":"arxiv","id":"2010.03743","version":3},"attestation_state":"computed","paper":{"title":"Visual News: Benchmark and Challenges in News Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuxiao Liu, Tianlu Wang, Vicente Ordonez, Yinghan Wang","submitted_at":"2020-10-08T03:07:00Z","abstract_excerpt":"We propose Visual News Captioner, an entity-aware model for the task of news image captioning. We also introduce Visual News, a large-scale benchmark consisting of more than one million news images along with associated news articles, image captions, author information, and other metadata. Unlike the standard image captioning task, news images depict situations where people, locations, and events are of paramount importance. Our proposed method can effectively combine visual and textual features to generate captions with richer information such as events and entities. More specifically, built "},"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":"2010.03743","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-08T03:07:00Z","cross_cats_sorted":[],"title_canon_sha256":"d0c7e9559573b6b60bf5745f600df25a598945af6003db5c7ae6ff6d1eeec2a0","abstract_canon_sha256":"c022486932c53b3caedcdfa5d38502a02c0436902cf97e07d5d7587e61bec834"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:48.265757Z","signature_b64":"abXH8hhfagOSp+TJ3JMh2qk0lAmv8ZET3eNZrawxZ7//nke/ttHB9s9MtgTNBFx8/Pg2w/3vvD54DjHls6XsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3383af23855f2e65a2f0b235e56a924ff257e4de2957ecdb447531e6fc44e8dc","last_reissued_at":"2026-07-05T03:13:48.265266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:48.265266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual News: Benchmark and Challenges in News Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuxiao Liu, Tianlu Wang, Vicente Ordonez, Yinghan Wang","submitted_at":"2020-10-08T03:07:00Z","abstract_excerpt":"We propose Visual News Captioner, an entity-aware model for the task of news image captioning. We also introduce Visual News, a large-scale benchmark consisting of more than one million news images along with associated news articles, image captions, author information, and other metadata. Unlike the standard image captioning task, news images depict situations where people, locations, and events are of paramount importance. Our proposed method can effectively combine visual and textual features to generate captions with richer information such as events and entities. More specifically, built "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03743","kind":"arxiv","version":3},"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/2010.03743/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":"2010.03743","created_at":"2026-07-05T03:13:48.265324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.03743v3","created_at":"2026-07-05T03:13:48.265324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03743","created_at":"2026-07-05T03:13:48.265324+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOB26I4FL4XG","created_at":"2026-07-05T03:13:48.265324+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOB26I4FL4XGLIXQ","created_at":"2026-07-05T03:13:48.265324+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOB26I4F","created_at":"2026-07-05T03:13:48.265324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24627","citing_title":"The Warrant Gap: Claim-Conditioned Re-scoring for Fact-Checking","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18361","citing_title":"COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2410.05160","citing_title":"VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2310.14566","citing_title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2306.14565","citing_title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOB26I4FL4XGLIXQWI26K2USJ7","json":"https://pith.science/pith/GOB26I4FL4XGLIXQWI26K2USJ7.json","graph_json":"https://pith.science/api/pith-number/GOB26I4FL4XGLIXQWI26K2USJ7/graph.json","events_json":"https://pith.science/api/pith-number/GOB26I4FL4XGLIXQWI26K2USJ7/events.json","paper":"https://pith.science/paper/GOB26I4F"},"agent_actions":{"view_html":"https://pith.science/pith/GOB26I4FL4XGLIXQWI26K2USJ7","download_json":"https://pith.science/pith/GOB26I4FL4XGLIXQWI26K2USJ7.json","view_paper":"https://pith.science/paper/GOB26I4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.03743&json=true","fetch_graph":"https://pith.science/api/pith-number/GOB26I4FL4XGLIXQWI26K2USJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/GOB26I4FL4XGLIXQWI26K2USJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOB26I4FL4XGLIXQWI26K2USJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOB26I4FL4XGLIXQWI26K2USJ7/action/storage_attestation","attest_author":"https://pith.science/pith/GOB26I4FL4XGLIXQWI26K2USJ7/action/author_attestation","sign_citation":"https://pith.science/pith/GOB26I4FL4XGLIXQWI26K2USJ7/action/citation_signature","submit_replication":"https://pith.science/pith/GOB26I4FL4XGLIXQWI26K2USJ7/action/replication_record"}},"created_at":"2026-07-05T03:13:48.265324+00:00","updated_at":"2026-07-05T03:13:48.265324+00:00"}